# AI Engineering

An emerging engineering discipline that combines systems engineering, software engineering, computer science, and human-centered design to create scalable, robust, and secure AI systems.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Why a Computer Scientist Thinks Superintelligence Won't Happen

DevFeed: [Why a Computer Scientist Thinks Superintelligence Won't Happen](<https://devfeed.tech/articles/why-a-computer-scientist-thinks-superintelligence-won-t-happen-145256.md>)

Original publisher: [Read original article](<https://spectrum.ieee.org/ai-superintelligence-debate>)

Author: Cal Newport

Published: 2026-11-19T12:00:03Z

Content type: opinion

Language: en

Sources: [IEEE Spectrum](<https://devfeed.tech/sources/ieee-spectrum.md>)

Topics: [superintelligence](<https://devfeed.tech/topics/superintelligence.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [computational complexity](<https://devfeed.tech/topics/computational-complexity.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [agi](<https://devfeed.tech/tags/agi.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-companies](<https://devfeed.tech/tags/ai-companies.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-ceo-dario-amodei](<https://devfeed.tech/tags/anthropic-ceo-dario-amodei.md>), [artificial-general-intelligence](<https://devfeed.tech/tags/artificial-general-intelligence.md>), [asi](<https://devfeed.tech/tags/asi.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [computer](<https://devfeed.tech/tags/computer.md>), [control](<https://devfeed.tech/tags/control.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [extinction](<https://devfeed.tech/tags/extinction.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [openai](<https://devfeed.tech/tags/openai.md>), [recursive-self-improvement](<https://devfeed.tech/tags/recursive-self-improvement.md>), [rsi](<https://devfeed.tech/tags/rsi.md>), [science](<https://devfeed.tech/tags/science.md>), [singularity](<https://devfeed.tech/tags/singularity.md>), [superintelligence](<https://devfeed.tech/tags/superintelligence.md>)

### AI overview

The author argues that recursive self-improvement leading to superintelligence remains highly speculative: post-training depends on suitable feedback data, major AI advances require substantial scientific work, and compute is finite. Computer science also shows that some problems are unsolvable or practically intractable, while AI progress remains uneven across tasks. The article attributes reported hacking incidents to long-running agents that let LLM outputs guide actions with few constraints, and contrasts these with task-specific systems such as AlphaFold and autonomous driving. It warns that pursuing self-improving systems may still increase risks by making AI harder to understand and control, and calls for more independent scrutiny.

### Source excerpt

Many people were caught off guard this past summer when employees of one of the world's leading AI companies began casually debating whether their products would lead to human extinction. It started when Anthropic researcher Jacob Coxon announced his resignation, warning that his employer and OpenAI were "racing straight to self-improving superintelligence and gambling with our lives." Evan Hubinger, Anthropic's head of alignment science, replied, "Jacob is correct here--we really do earnestly believe AI could kill all humans!" And Anthropic CEO Dario Amodei subsequently told CNN, "I agree with Jacob much more than I disagree with him." These concerns stem from a belief that has circulated in futurist circles for many decades: Once engineers design an AI system capable of improving itself, it will trigger an accelerating cycle of autonomous upgrades known as recursive self-improvement (RSI). The result will be artificial superintelligence (ASI), a system with cognitive capabilities so vastly exceeding those of humans that it will easily evade our control and perhaps even wipe out our species. Artificial superintelligence is, it should be noted, a far more ambitious goal than artificial general intelligence (AGI), which generally refers to AI that can match human capabilities across a broad range of cognitive tasks. These ideas have prompted varied reactions. Some argue that the concept of ASI is being used for marketing or to instigate regulation that will help the incumbent labs squash new competitors. Others focus on the plausibility of such systems killing us all, debating the finer points of specific scenarios such as AI-engineered superviruses. Still others claim that aligning ASI to human interests is feasible and so we should rush ahead to usher in this digital utopia. Amid these conversations, one question has received comparatively little attention: From an engineering perspective, is superintelligence even possible? The answer is important because it can he

## College Board Delivers Another AI Ultimatum: No AI, No AP CS Principles Course

DevFeed: [College Board Delivers Another AI Ultimatum: No AI, No AP CS Principles Course](<https://devfeed.tech/articles/college-board-delivers-another-ai-ultimatum-no-ai-no-ap-cs-principles-course-142916.md>)

Original publisher: [Read original article](<https://news.slashdot.org/story/26/11/19/0628241/college-board-delivers-another-ai-ultimatum-no-ai-no-ap-cs-principles-course>)

Author: BeauHD

Published: 2026-11-19T11:00:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Programming Languages / Compilers](<https://devfeed.tech/topics/programming-languages-compilers.md>), [Blockly](<https://devfeed.tech/topics/blockly.md>)

Tags: [2027](<https://devfeed.tech/tags/2027.md>), [about](<https://devfeed.tech/tags/about.md>), [after](<https://devfeed.tech/tags/after.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [also](<https://devfeed.tech/tags/also.md>), [app](<https://devfeed.tech/tags/app.md>), [application](<https://devfeed.tech/tags/application.md>), [ban](<https://devfeed.tech/tags/ban.md>), [based](<https://devfeed.tech/tags/based.md>), [block](<https://devfeed.tech/tags/block.md>), [blockly](<https://devfeed.tech/tags/blockly.md>), [board](<https://devfeed.tech/tags/board.md>), [build](<https://devfeed.tech/tags/build.md>), [build-with-ai](<https://devfeed.tech/tags/build-with-ai.md>), [college](<https://devfeed.tech/tags/college.md>), [course](<https://devfeed.tech/tags/course.md>), [education](<https://devfeed.tech/tags/education.md>), [principles](<https://devfeed.tech/tags/principles.md>)

### AI overview

The College Board plans to redesign AP Computer Science Principles starting in fall 2027 around responsible AI use. Students will learn to use AI to design, debug, and evaluate code, assess when it is wrong, and build an AI application for an AI Create Project; the exam will include free-response questions about that project. Schools must provide each student with access to a district-approved AI tool that accepts written instructions and returns a response. Starting in 2028-29, project submissions must use one of a limited number of text-based languages. Teachers may continue using block-based tools for instruction, but students must learn an approved text-based language before submitting. The excerpt does not specify the approved tools or languages.

### Source excerpt

Longtime Slashdot reader theodp writes: Just days after news broke of Google's no AI, no Search ultimatum -- prompting school districts to weigh breaking up with Google Search (source paywalled; alternative source) -- the College Board quietly delivered another AI ultimatum to the nation's AP Computer Science Principles teachers, suggesting that their days of teaching AP CSP might be over unless their school districts put an end to their anti-AI ways. "Effective in fall 2027," The College Board explained, "AP Computer Science Principles has been reimagined as the course for teaching students how to work with AI responsibly, safely, and confidently. AI is integral to the world of computer science. Software engineering remains one of the largest professional job categories, and employers now expect software engineers to be fluent in AI. What sets candidates apart is a deeper understanding of AI for designing, debugging, and evaluating code, and the ability to determine when AI is wrong. The redesigned course develops these skills, empowering students to build with AI, not just learn about it. [...] Students also complete an AI Create Project, in which they build an AI application. The AP Exam includes free-response questions about the project, so students who earn a qualifying score for college credit have demonstrated their ability to design, build, and understand an AI-powered application. [...] Students need access to a district-approved AI tool that accepts a student's own written instructions and returns a response. Schools will need to make sure every student has access to one." The College Board also announced a planned ban on the use of block-based programming languages like Snap!, Scratch, Blockly, and MIT App Inventor for students' "AI Create Project" (which replaces the current "Create Performance Task" that counts for 30% of a student's AP exam score): "Beginning with the 2028-29 school year, students will submit their AI Create Project in one of a limited

## Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses

DevFeed: [Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses](<https://devfeed.tech/articles/agentic-harness-engineering-beta-requirement-centered-evolution-of-agent-harnesses-142220.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24924>)

Author: Jiahang Lin, Jiahao Chen, Yiding Wang, Shichun Liu, Chengjun Pan, Shihan Dou, Honglin Guo, Yuyang Hu, Changhao Jiang, Zhenhua Han, Hang Yan, Qi Zhang, Tao Gui, Xuanjing Huang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [base](<https://devfeed.tech/tags/base.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [beta](<https://devfeed.tech/tags/beta.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [change](<https://devfeed.tech/tags/change.md>), [changes](<https://devfeed.tech/tags/changes.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [harness](<https://devfeed.tech/tags/harness.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>)

### AI overview

AHE-Beta evolves agent harnesses around verified user requirements: simulated users raise issues over multiple turns, a team implements generalizable changes, and changes are merged only after resolving a verified requirement and passing review. On held-out tasks, it raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and the abstract reports higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, users preferred it in 31 of 48 valid pairs and rated it higher on all five dimensions. Without further evolution, reported pass@1 gains over Base Harness transferred to GLM-5.3 (15.8%) and DeepSeek-V4.1-Flash (5.3%).

### Source excerpt

arXiv:2611.24924v1 Announce Type: new Abstract: Real-world harness engineering is driven by explicit and implicit user requirements, which guide development and validation. However, existing harness evolution methods often overlook implicit requirements and interaction needs, while using a single evolution agent to modify the harness and benchmark scores to select changes. This process often produces narrow patches and leads to benchmark-specific local optima. We introduce Agentic Harness Engineering Beta (AHE-Beta), a requirement-centered loop that brings real-world engineering practices into harness evolution. The loop consists of three steps: (1) User-driven evaluation lets simulated users raise their requirements as issues while they work with the harness over multiple turns. (2) Team-based modification implements those requirements as generalizable changes rather than task-specific patches. (3) Requirement-driven selection merges a change only when it resolves a verified requirement and passes review. Empirically, on held-out tasks, AHE-Beta raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and achieves higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, real users prefer AHE-Beta in 31 of 48 valid pairs and rate it higher on all five dimensions, matching the directional preference of the user simulator. The human A/B results show that AHE-Beta achieves its goal of aligning harness evolution with real-world user requirements. Without further evolution, the gains transfer to GLM-5.3 and DeepSeek-V4.1-Flash with pass@1 improvements of 15.8% and 5.3% over Base Harness. Together, these results show that requirement-centered harness evolution is a more general method for improving agent capabilities.

## Escaping the Anthropomorphic Trap: Resolving the Cognitive Mismatch in Future AI Software Development

DevFeed: [Escaping the Anthropomorphic Trap: Resolving the Cognitive Mismatch in Future AI Software Development](<https://devfeed.tech/articles/escaping-the-anthropomorphic-trap-resolving-the-cognitive-mismatch-in-future-ai-software-development-142140.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23264>)

Author: Yi Wang, Zheng Jiang, Gaowei Zhang, Min Zhang, Yang Feng

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Tech Debt](<https://devfeed.tech/topics/tech-debt.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-software](<https://devfeed.tech/tags/ai-software.md>), [ai-software-development](<https://devfeed.tech/tags/ai-software-development.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [build](<https://devfeed.tech/tags/build.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [code](<https://devfeed.tech/tags/code.md>), [computational-topology](<https://devfeed.tech/tags/computational-topology.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [emulation](<https://devfeed.tech/tags/emulation.md>), [future](<https://devfeed.tech/tags/future.md>), [software](<https://devfeed.tech/tags/software.md>), [software-development](<https://devfeed.tech/tags/software-development.md>)

### AI overview

The paper argues that software practices designed around human working-memory limits can constrain multi-agent AI, whose reasoning is described as high-dimensional and stateless. It proposes Invisible Software Engineering (Invisible SE), which shifts governance from making agents emulate human workflows to shaping the repository as an active environment. The proposed environment uses topological gradients, temporally weighted memory, and representation-space regularization to guide agent behavior without classical code-level constraints. The abstract presents this as a potential blueprint for coordinating scalable, long-lived software infrastructures; it does not provide evidence of implementation or evaluation.

### Source excerpt

arXiv:2611.23264v1 Announce Type: new Abstract: For more than a half-century, the foundational paradigms of software development-such as modularity, information hiding, and hierarchical labor division-have been engineered to accommodate the strict cognitive limitations of human working memory. However, the rapid emergence of multi-agent artificial intelligence exposes a fundamental cognitive mismatch. Current frameworks attempt to integrate high-dimensional, stateless neural reasoning engines by coercing them to operate within these legacy, human-centric structures, falling into an anthropomorphic trap. This friction generates a novel, highly volatile behavioral entropy defined as AI-software technical debt, wherein amnesic agents hallucinate opaque workarounds to bypass architectural blindfolds. To resolve this, we propose Invisible Software Engineering (Invisible SE), a paradigm shift from agent-centric human emulation to environment-centric stigmergic governance. By reimagining the repository as an active computational topology which utilizes topological gradients, temporally weighted memory, and representation-space regularization, Invisible SE safely guides AI behavior without classical code-level constraints, thus transcending the cognitive horizons of human developers. This environment-centric protocol offers a potential blueprint for orchestrating scalable, long-lived computational infrastructures that transcend the cognitive horizons of human developers and enable autonomous agents to work, coordinate, and scale to build future software systems.

## When Qini Rewards the Wrong Uplift Model, Use Doubly Robust Scores

DevFeed: [When Qini Rewards the Wrong Uplift Model, Use Doubly Robust Scores](<https://devfeed.tech/articles/when-qini-rewards-the-wrong-uplift-model-use-doubly-robust-scores-140795.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/when-qini-rewards-the-wrong-uplift-model-use-doubly-robust-scores/>)

Author: Ivan Gorban

Published: 2026-11-18T13:30:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Inference](<https://devfeed.tech/topics/inference.md>)

Tags: [ate](<https://devfeed.tech/tags/ate.md>), [bias](<https://devfeed.tech/tags/bias.md>), [bootstrap](<https://devfeed.tech/tags/bootstrap.md>), [causal-inference](<https://devfeed.tech/tags/causal-inference.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [dr](<https://devfeed.tech/tags/dr.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [marketing-analytics](<https://devfeed.tech/tags/marketing-analytics.md>), [model](<https://devfeed.tech/tags/model.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [robust](<https://devfeed.tech/tags/robust.md>), [uplift](<https://devfeed.tech/tags/uplift.md>), [uplift-modeling](<https://devfeed.tech/tags/uplift-modeling.md>)

### AI overview

In a simulation of one million customers with selective treatment assignment, treatment/control differences made calibrated Qini favor a Linear DR ranking over the known true-CATE ranking (0.0856 vs. 0.0826), even though the true ranking had greater causal gain. The authors explain that Qini uses observed outcomes and does not remove selection bias; calibration aligns scores at one reference but preserves each metric's model ordering. IPW and doubly robust (DR) gain scores were closer to known gains in the simulation. IPW requires a correct propensity model; DR requires a correct propensity model or both outcome models. Both require consistency, no unmeasured confounding, and overlap, and remain subject to estimation and finite-sample error. In this specific comparison, the authors favor a boosted S-learner as a simple starting point: its DR-gain advantage over DML was small and uncertain, while only its comparison with T showed a paired interval excluding zero. They caution that the bootstrap held fitted models fixed and that the findings come from simulations, not a guarantee for other datasets.

### Source excerpt

On 1 million simulated customers, calibrated Qini scored a Linear DR learner 0.0856 against 0.0826 for the true-CATE ranking that should have won. The post When Qini Rewards the Wrong Uplift Model, Use Doubly Robust Scores appeared first on Towards Data Science.

## The Software Engineering Factory: Engineering Accountability and Control in the Age of Abundant Code

DevFeed: [The Software Engineering Factory: Engineering Accountability and Control in the Age of Abundant Code](<https://devfeed.tech/articles/the-software-engineering-factory-engineering-accountability-and-control-in-the-age-of-abundant-code-139582.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21623>)

Author: Ahmed E. Hassan, Zhe Chen, Amr E. Mohamed, Keheliya Gallaba, Daniel German, Waleed Kadous, Gustavo A. Oliva, Radin Shayanfar, Paul Stack, Haoxiang Zhang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [accountability](<https://devfeed.tech/tags/accountability.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [building](<https://devfeed.tech/tags/building.md>), [changes](<https://devfeed.tech/tags/changes.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [community](<https://devfeed.tech/tags/community.md>), [control](<https://devfeed.tech/tags/control.md>), [controls](<https://devfeed.tech/tags/controls.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dark-factory](<https://devfeed.tech/tags/dark-factory.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [factory](<https://devfeed.tech/tags/factory.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The paper argues that when AI agents produce more code than people can review line by line, accountability should be built into the process rather than rely primarily on final code review. Its Software Engineering Factory uses protocols to define work stages, required evidence, and ownership; a deterministic engine written in conventional code enforces transitions and gates, with human escalation where needed. Humans retain authority by setting delegation scope, boundaries, escalation conditions, and decisions requiring judgment, without supervising every agent action. Drawing on three iterated implementations, two open source, the authors offer ten principles for designing and operating such systems. They present these as a non-exhaustive conceptual scaffold, not the only viable foundation.

### Source excerpt

arXiv:2611.21623v1 Announce Type: new Abstract: AI agents can now plan, write, test, review, and revise code at a volume no human organization can inspect line by line. Final code review therefore cannot remain the primary organizational control for owning code changes. The Software Engineering (SE) Factory moves control into the process that produces the code. The Factory protocols define how work moves, what evidence must exist before it can proceed, and who owns the result. A deterministic protocol engine, implemented in conventional code rather than prompts, enforces those protocols by controlling stage transitions, requiring evidence, and invoking gates and human escalation, where needed, before work can advance. The SE Factory preserves human authority over consequential decisions and makes accountable acceptance possible without requiring humans to supervise every agent action. The SE Factory is not a dark factory. Humans remain in control by defining the scope and granularity of delegation, the boundaries and escalation conditions, and the consequential decisions that require accountable human judgment. We draw on our experience building three distinct SE Factory implementations, all of which have undergone multiple iterations and two of which are publicly available as open-source systems, into ten principles for conceiving, building, and operating SE Factories at scale, grounded in the organizational and technical realities of our implementations. We do not claim that these principles are exhaustive or constitute the only viable foundation for an SE Factory. Rather, we offer them as a conceptual scaffold and shared vocabulary for reasoning about SE Factories, evaluating their designs, and guiding their evolution. Our goal is to catalyze a community-wide dialogue that moves software engineering beyond controls designed for human-scale code production toward a disciplined, scalable, and trustworthy agentic future.

## The Human Side of ML Engineering: Analyzing the Collaboration and Communication Skills in ML Job Postings

DevFeed: [The Human Side of ML Engineering: Analyzing the Collaboration and Communication Skills in ML Job Postings](<https://devfeed.tech/articles/the-human-side-of-ml-engineering-analyzing-the-collaboration-and-communication-skills-in-ml-job-postings-137363.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18915>)

Author: Aidin Azamnouri, Phuong Thao Le, Justus Bogner, Stefan Wagner

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [collaboration](<https://devfeed.tech/tags/collaboration.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [job](<https://devfeed.tech/tags/job.md>), [ml](<https://devfeed.tech/tags/ml.md>), [skills](<https://devfeed.tech/tags/skills.md>)

### AI overview

In a sample of 1,000 job postings from five continents, collaboration appeared in 88.6% of ML postings and communication in 72.2%; about one fifth and one quarter of those requirements, respectively, were expressed only implicitly. The study used a taxonomy and two human annotators plus an LLM to capture context-dependent references. Collaboration mainly meant integrating across role boundaries, while communication was often generic and fewer than half of postings named its intended audience. ML and software engineering postings demanded interpersonal skills at statistically indistinguishable levels but emphasized different forms: presentation and audience-facing interaction in ML, team practices in SE. Within ML, advertised role distinguished interpersonal profiles more sharply than the other dimensions examined.

### Source excerpt

arXiv:2611.18915v1 Announce Type: cross Abstract: Studies of Machine Learning (ML) practice highlight the importance of combining technical expertise with interpersonal capabilities, particularly collaboration and communication. However, evidence on how ML job postings express these skills is scarce, and prior work largely relies on keyword-based analyses that overlook implicit expression. We analyze demand for these skills in ML job postings across regions, industries, and seniority levels, and compare it with software engineering (SE) roles. We collected 1,000 postings (500 ML, 500 SE) from five continents via a semi-automated pipeline. For annotation, we synthesized a taxonomy of collaboration and communication sub-categories from prior work and used an LLM as a third annotator alongside two humans, enabling detection of context-dependent and implicit skill references. Collaboration appeared in 88.6% of ML postings and communication in 72.2%, far above prior keyword-based estimates for AI roles. Roughly one in five collaboration and one in four communication requirements were expressed only implicitly. Decomposing these requirements into the taxonomy's sub-categories reveals what aggregate figures conceal. Collaboration is demanded predominantly as integration across role boundaries rather than team membership. Communication is mostly required in generic terms, with fewer than half of the postings requiring it naming whom the candidate must communicate with. ML and SE postings demand interpersonal competence at statistically indistinguishable levels but orient it differently, SE toward team practices and ML toward presentation and audience-facing interaction. Within ML, the advertised role separates interpersonal profiles more sharply than any other dimension, including the contrast with SE.

## Software engineering after code becomes cheap with Satya Nadella

DevFeed: [Software engineering after code becomes cheap with Satya Nadella](<https://devfeed.tech/articles/software-engineering-after-code-becomes-cheap-with-satya-nadella-136143.md>)

Original publisher: [Read original article](<https://newsletter.pragmaticengineer.com/p/software-engineering-after-code-becomes>)

Author: Gergely Orosz

Published: 2026-11-16T13:33:48Z

Content type: article

Language: en

Sources: [The Pragmatic Engineer](<https://devfeed.tech/sources/the-pragmatic-engineer.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [future of software](<https://devfeed.tech/topics/future-of-software.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accelerated-development](<https://devfeed.tech/tags/ai-accelerated-development.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [azure](<https://devfeed.tech/tags/azure.md>), [careers](<https://devfeed.tech/tags/careers.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [code](<https://devfeed.tech/tags/code.md>), [code-verification](<https://devfeed.tech/tags/code-verification.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [satya-nadella](<https://devfeed.tech/tags/satya-nadella.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Nadella argues that as AI makes code generation cheap, verifying generated code becomes a central, unresolved engineering challenge. He describes teams building "software factories" that use agents to improve existing operations, and says specifications and verification matter more as tools and workflows change quickly. Microsoft's experience with GitHub Copilot falling behind Claude Code illustrates how a shift from IDEs to command-line agents can reshape a product's form factor in months. For AI infrastructure, he recommends keeping the harness, memory, and model replaceable, using private evaluations, and treating agents as insider risks that need separate safeguards. He expects hybrid intelligence to route work between local models and more capable, costly cloud models. The conversation also covers Microsoft's restructuring, slower junior hiring during teams' transition to new workflows, and a PRAISE program pairing experienced engineers with early-career developers. His practical advice is to use AI hands-on and learn through teams doing the work.

### Source excerpt

Microsoft CEO Satya Nadella on AI's impact on software engineering, code verification, and engineers' careers.

## Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy

DevFeed: [Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy](<https://devfeed.tech/articles/agon-an-autonomous-large-scale-omnidisciplinary-research-system-built-on-prompt-economy-131670.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.24177>)

Author: Youran Sun, Xingyu Ren, Chugang Yi, Jiaxuan Guo, Kejia Zhang, Jianda Du, Haizhao Yang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [autonomous](<https://devfeed.tech/tags/autonomous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [design-principles](<https://devfeed.tech/tags/design-principles.md>), [failures](<https://devfeed.tech/tags/failures.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [orchestrator](<https://devfeed.tech/tags/orchestrator.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [research](<https://devfeed.tech/tags/research.md>), [scale](<https://devfeed.tech/tags/scale.md>), [system](<https://devfeed.tech/tags/system.md>), [taxonomy](<https://devfeed.tech/tags/taxonomy.md>), [zero-code](<https://devfeed.tech/tags/zero-code.md>)

### AI overview

Agon is a research orchestrator built to scale automated research across domains from brief topic descriptions, without human-written code. Its six design principles are Prompt Economy, Future-Facing, Minimal Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. Deployments demonstrate scalability but also surface failure classes that are difficult to address through prompt engineering. The authors classify these failures by severity, fixability, visibility, and capability locus, and frame the system as one in which machines scale while humans steer.

### Source excerpt

arXiv:2606.24177v2 Announce Type: replace Abstract: Large language models are making research scalable. We present \textsc{Agon}, a research orchestrator designed to probe the limits of automated research. \textsc{Agon} is built on six design principles: Prompt Economy, Future-Facing, Minimal Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. We deployed \textsc{Agon} across domains using only brief topic descriptions as starting points and no human-written code. These deployments demonstrate scalability but also reveal previously unseen classes of failure that are difficult to address through prompt engineering. We organize these failures into a taxonomy along four dimensions: severity, fixability, visibility, and capability locus. Together, these results show that \textsc{Agon} is pushing research towards a new paradigm: machines scale, humans steer. Our code is publicly available at \href{https://github.com/AutoResearch-Factory/Agon/tree/lite}{this GitHub repository}.

## Physically Interpretable Basin Selection in Discrete-Variable Origami Design

DevFeed: [Physically Interpretable Basin Selection in Discrete-Variable Origami Design](<https://devfeed.tech/articles/physically-interpretable-basin-selection-in-discrete-variable-origami-design-133188.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17196>)

Author: Lucy Liu, Leon M. Kamp, Katia Bertoldi, L. Mahadevan

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [bias](<https://devfeed.tech/tags/bias.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cond-mat-mtrl-sci](<https://devfeed.tech/tags/cond-mat-mtrl-sci.md>), [cond-mat-soft](<https://devfeed.tech/tags/cond-mat-soft.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [fail](<https://devfeed.tech/tags/fail.md>), [flat](<https://devfeed.tech/tags/flat.md>), [framework](<https://devfeed.tech/tags/framework.md>), [functional](<https://devfeed.tech/tags/functional.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [half](<https://devfeed.tech/tags/half.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [optimize](<https://devfeed.tech/tags/optimize.md>), [option](<https://devfeed.tech/tags/option.md>), [origami](<https://devfeed.tech/tags/origami.md>), [practical](<https://devfeed.tech/tags/practical.md>), [selection](<https://devfeed.tech/tags/selection.md>), [variable](<https://devfeed.tech/tags/variable.md>)

### AI overview

In an origami-inspired design problem, continuous relaxation often produced a large discretization gap: 97% of relaxed runs solved, but only about half of the final discrete designs did. Biasing initialization uniformly toward the stiff, flat hinge option raised the discrete solve fraction from 49% to 69% without extra compute or changing the optimization process; resulting sheets also showed greater geometric compatibility and stiffness. Penalizing frustration and floppiness in the outer loss raised the solve fraction further, to 78%. The findings suggest these physical properties help identify unfavorable optimization basins that fail after discretization.

### Source excerpt

arXiv:2611.17196v1 Announce Type: new Abstract: Automatic differentiation has enabled rapid progress on continuous-variable mechanical design problems, but gradient-based optimization still struggles with discrete variables. The standard approach is to optimize using a continuous relaxation of the choices, then commit to the nearest discrete design at the end. Why this procedure selects unfavorable basins is poorly understood. Here, we introduce a practical, interpretable design problem inspired by origami, in which automatic differentiation is used to design shapes with a target functional behavior. Each origami sheet has a fixed geometry, and a bilevel optimization framework tunes which one of four discrete hinge types to place at each fold. Baseline gradient-based design settles into basins with a large discretization gap: relaxed optimization solves 97% of runs, but the final, discrete solutions succeed only half the time. We find that the gap can be relieved with a surprisingly simple modification. An initialization prior uniformly biased toward the stiff, flat hinge option boosts the final solve fraction from 49% to 69%. Applying the prior adds no additional compute and leaves the optimization process unchanged. Compared to the baseline, sheets produced with the prior have greater geometric compatibility and mechanical stiffness. Directly penalizing frustration and floppiness in the outer loss function produces an even greater improvement than the prior does, raising the solve fraction to 78% and indicating that these properties help distinguish the unfavorable basins. Our results demonstrate that loss landscapes for mechanical design can have physically meaningful basins that are not robust to discretization and cause solves to fail. Targeting these basins' physical signatures, even with just an initialization bias, helps avoid them.

## Understanding-First AI Engineering: Purposes, Reference Architecture, and Architectural Patterns for Human Understanding

DevFeed: [Understanding-First AI Engineering: Purposes, Reference Architecture, and Architectural Patterns for Human Understanding](<https://devfeed.tech/articles/understanding-first-ai-engineering-purposes-reference-architecture-and-architectural-patterns-for-human-understanding-128239.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13022>)

Author: Liming Zhu, Qinghua Lu, Ming Ding

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [curiosity](<https://devfeed.tech/tags/curiosity.md>), [decision](<https://devfeed.tech/tags/decision.md>), [design](<https://devfeed.tech/tags/design.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [effective](<https://devfeed.tech/tags/effective.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [governance](<https://devfeed.tech/tags/governance.md>), [learning](<https://devfeed.tech/tags/learning.md>), [models](<https://devfeed.tech/tags/models.md>), [operational](<https://devfeed.tech/tags/operational.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [reference-architecture](<https://devfeed.tech/tags/reference-architecture.md>)

### AI overview

The paper proposes treating purpose-specific human understanding as a first-class AI engineering goal, even when human input is not needed to correct task errors. It organizes the reasons for understanding into reflective agency, effective action, collective governance, and epistemic value. Its reference architecture links production, verification, use, and learning or exploration through shared records, with explanation and participation supporting understanding. Five candidate patterns address parallel learning, explanatory models, goal exploration, audience-specific views, and distributed expertise. Qualitative analysis of two hypothetical cases shows how these ideas can guide investigation, participation, and decisions while retaining operational controls; it illustrates design consequences and limitations, but does not establish empirical effectiveness.

### Source excerpt

arXiv:2611.13022v1 Announce Type: new Abstract: AI systems can produce reliable results without developing human understanding. However, human understanding remains valuable for shaping subsequent AI-supported work, forming preferences, governing collective choices and satisfying curiosity, even when human participation is unnecessary for correcting errors. We propose understanding-first AI engineering, which treats purpose-specific human understanding as a first-class design principle guiding requirements, design and operation. The purposes of understanding are organised into four complementary rationales: reflective agency, effective action, collective governance and epistemic value. A reference architecture connects production, verification, use, and learning and exploration through shared records, supporting understanding through explanation and participation. Five candidate architectural patterns guide choices about parallel learning, explanatory models, goal exploration, audience-specific views and distributed expertise. Qualitative scenario analysis of two hypothetical use cases demonstrates how the purpose classification, reference architecture and selected patterns guide investigation, participation and decision processes while retaining operational controls. The cases illustrate design consequences and limitations rather than establish empirical effectiveness. The approach makes human understanding an explicit engineering commitment whose justification need not depend on improving the original AI task.

## Robust Flow Matching under Target Corruption and Label Noise

DevFeed: [Robust Flow Matching under Target Corruption and Label Noise](<https://devfeed.tech/articles/robust-flow-matching-under-target-corruption-and-label-noise-128691.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13324>)

Author: Mert Can Kurucu, Erik Englesson, Hossein Azizpour

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Data Mining & Modeling](<https://devfeed.tech/topics/data-mining-modeling.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [ccs](<https://devfeed.tech/tags/ccs.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [corruption](<https://devfeed.tech/tags/corruption.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [field](<https://devfeed.tech/tags/field.md>), [flow](<https://devfeed.tech/tags/flow.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative](<https://devfeed.tech/tags/generative.md>), [noise](<https://devfeed.tech/tags/noise.md>), [regression](<https://devfeed.tech/tags/regression.md>), [robust](<https://devfeed.tech/tags/robust.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [score](<https://devfeed.tech/tags/score.md>), [settings](<https://devfeed.tech/tags/settings.md>), [stable](<https://devfeed.tech/tags/stable.md>), [standard](<https://devfeed.tech/tags/standard.md>), [structure](<https://devfeed.tech/tags/structure.md>), [target](<https://devfeed.tech/tags/target.md>)

### AI overview

The paper proposes corruption-specific sample weighting to make Flow Matching more robust to corrupted targets and noisy labels. It models training as time-dependent regression: target corruption adds a residual that grows with time, while label noise directs updates toward the wrong class-conditional vector field. For target corruption, the Temporal Residual Score (TRS) emphasizes residual magnitudes at intermediate-to-late times, where clean and corrupted samples are more separable. For label noise, the Comparative Conditional Score (CCS) compares the observed class field's residual with those of alternative class fields for the same trajectory and velocity target. The abstract reports improved robustness over standard Flow Matching and robust-training baselines in controlled corruption settings and with real-world noisy labels.

### Source excerpt

arXiv:2611.13324v1 Announce Type: new Abstract: Flow Matching (FM) is a strong framework for generative modeling due to its stable training and efficient sampling. However, FM assumes clean target data and labels, an assumption often violated in practice. We formulate FM training as a time-dependent regression problem over conditional vector fields and analyze how the two corruption types affect the objective: i) target corruption adds a time-dependent residual term that grows with time, ii) label noise causes updates to the wrong class-conditional vector field. Based on this analysis, we propose to improve FM robustness by mapping corruption-specific residual scores to sample weights. For target corruption, we propose the Temporal Residual Score (TRS), which emphasizes residual magnitudes at intermediate-to-late FM times, where clean and corrupted samples are more separable. For label noise, we propose the Comparative Conditional Score (CCS), which compares the residual of the observed class-conditional vector field against alternative class-conditional vector fields for the same trajectory and velocity target. Experiments across controlled corruption settings and real-world noisy labels show that the proposed methods improve robustness over standard FM and robust-training baselines, supporting corruption-specific residual structure as a practical basis for robust FM.

## redalpine Closes Oversubscribed $250M Fund to Back the Science Defining the Next Decade

DevFeed: [redalpine Closes Oversubscribed $250M Fund to Back the Science Defining the Next Decade](<https://devfeed.tech/articles/redalpine-closes-oversubscribed-250m-fund-to-back-the-science-defining-the-next-decade-127131.md>)

Original publisher: [Read original article](<https://hackernoon.com/redalpine-closes-oversubscribed-$250m-fund-to-back-the-science-defining-the-next-decade?source=rss>)

Author: Ishan Pandey

Published: 2026-11-10T16:07:32Z

Content type: news

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Finance](<https://devfeed.tech/topics/finance.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Data Science](<https://devfeed.tech/topics/data-science.md>)

Tags: [0-1](<https://devfeed.tech/tags/0-1.md>), [1-4](<https://devfeed.tech/tags/1-4.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-companies](<https://devfeed.tech/tags/ai-companies.md>), [ai-for-drug-discovery](<https://devfeed.tech/tags/ai-for-drug-discovery.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [biotech](<https://devfeed.tech/tags/biotech.md>), [deeptech](<https://devfeed.tech/tags/deeptech.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [redalpine](<https://devfeed.tech/tags/redalpine.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [science](<https://devfeed.tech/tags/science.md>), [series](<https://devfeed.tech/tags/series.md>), [series-a](<https://devfeed.tech/tags/series-a.md>), [startups](<https://devfeed.tech/tags/startups.md>), [technology](<https://devfeed.tech/tags/technology.md>), [vc](<https://devfeed.tech/tags/vc.md>), [vc-funding](<https://devfeed.tech/tags/vc-funding.md>)

### AI overview

redalpine closed its oversubscribed $250 million RAC VIII fund, its largest early-stage fund, to invest in about 20 European companies, primarily leading or co-leading Seed and Series A rounds with initial checks of $1 million to $15 million. Half of the investment team are trained scientists, supporting evaluation of technologies before products or customer data exist. Its first three investments span robotics force sensing (Enact Intelligence), AI-supported drug discovery (Helical), and topological neural networks for critical systems (Arlequin AI). The fund starts with these three companies and room for about 17 more. redalpine says it screens more than 5,000 companies annually and makes five to ten new early-stage investments a year. The article cites prior portfolio outcomes including Mistral AI, Proxima Fusion and N26, while cautioning that past performance does not reliably predict future results.

### Source excerpt

redalpine closes its oversubscribed $250M RAC VIII fund to lead Seed and Series A rounds in European AI, robotics, fusion and biotech after 20 years.

## Don't Let Claude Code Design Your LLM Judges

DevFeed: [Don't Let Claude Code Design Your LLM Judges](<https://devfeed.tech/articles/don-t-let-claude-code-design-your-llm-judges-127871.md>)

Original publisher: [Read original article](<https://www.decodingai.com/p/write-your-own-llm-judges>)

Author: Louis-François Bouchard

Published: 2026-11-10T12:21:59Z

Content type: tutorial

Language: en

Sources: [Decoding ML](<https://devfeed.tech/sources/decoding-ml.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Reliable AI outputs](<https://devfeed.tech/topics/reliable-ai-outputs.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [phoenix](<https://devfeed.tech/topics/phoenix.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [1-4](<https://devfeed.tech/tags/1-4.md>), [2](<https://devfeed.tech/tags/2.md>), [2-2](<https://devfeed.tech/tags/2-2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [added](<https://devfeed.tech/tags/added.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-builder](<https://devfeed.tech/tags/agent-builder.md>), [agents](<https://devfeed.tech/tags/agents.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [don-t](<https://devfeed.tech/tags/don-t.md>), [let](<https://devfeed.tech/tags/let.md>), [llm](<https://devfeed.tech/tags/llm.md>), [me](<https://devfeed.tech/tags/me.md>), [noise](<https://devfeed.tech/tags/noise.md>)

### AI overview

ToneBench's 28,200 LLM judgments showed that judge prompts and scores need human calibration before they can support a trustworthy ranking. The author recommends measuring both generation variance and judge reliability: ToneBench now scores five drafts per model configuration and tests judges against human ratings. For subjective scoring, its most consistent approach uses detailed, hand-written rubric levels with examples, evidence quotes before scores, and checks for score clustering and whether rubric revisions separate strong from weak drafts. A panel of judges from different model families can dilute individual models' self-preference, though it does not remove bias; judges also differ in score generosity, speed, and reliability. The author's golden set uses human ratings on the same categories as the judges, but calibration results are not yet available. For ongoing runs, pin exact judge model IDs, re-evaluate after judge or rubric changes, audit inputs and outputs, and require pairwise preferences to agree in both presentation orders. ToneBench is a signal for shortlisting models, not ground truth for other use cases.

### Source excerpt

What 28,200 LLM judgments taught me about noise, rubrics, and human calibration

## How Microsoft's Principal Software Engineering Manager Works and Uses AI

DevFeed: [How Microsoft's Principal Software Engineering Manager Works and Uses AI](<https://devfeed.tech/articles/how-microsoft-s-principal-software-engineering-manager-works-and-uses-ai-127101.md>)

Original publisher: [Read original article](<https://newsletter.eng-leadership.com/p/how-microsofts-principal-software>)

Author: Gregor Ojstersek

Published: 2026-11-09T22:52:33Z

Content type: article

Language: en

Sources: [Engineering Leadership](<https://devfeed.tech/sources/engineering-leadership.md>)

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [addition](<https://devfeed.tech/tags/addition.md>), [advice](<https://devfeed.tech/tags/advice.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [book](<https://devfeed.tech/tags/book.md>), [case](<https://devfeed.tech/tags/case.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-manager](<https://devfeed.tech/tags/engineering-manager.md>), [manager](<https://devfeed.tech/tags/manager.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [mindset](<https://devfeed.tech/tags/mindset.md>), [my](<https://devfeed.tech/tags/my.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [study](<https://devfeed.tech/tags/study.md>), [uses](<https://devfeed.tech/tags/uses.md>)

### AI overview

Microsoft Principal Software Engineering Manager Tarik Guney focuses on sustainable team value by finding bottlenecks in communication, tooling, processes, and assumptions. He tracks leading indicators such as productivity and process efficiency alongside outcomes like reliability and delivery predictability, using mismatches to spot misplaced effort. He describes multiplying others as increasing throughput without adding hours or stress, through clear goals, trust, psychological safety, and efficient tools. He uses AI within existing workflows to speed coding and information access, summarize meetings and reconstruct context, tailor communications, draft documents, explore options, and handle routine tasks such as pull requests and pipeline checks. These uses reduce repetitive cognitive work and context loss, while leaving problem framing and decisions to people. His advice is to start with practical problems, integrate AI into current workflows, and judge it by improvements in clarity, speed, and quality rather than by how widely it is used.

### Source excerpt

Case study from my book The Multiplier Mindset, published by O'Reilly.

## What Would It Take to Prove That an AI Is Conscious?

DevFeed: [What Would It Take to Prove That an AI Is Conscious?](<https://devfeed.tech/articles/what-would-it-take-to-prove-that-an-ai-is-conscious-122686.md>)

Original publisher: [Read original article](<https://hackernoon.com/what-would-it-take-to-prove-that-an-ai-is-conscious?source=rss>)

Author: Jonathan Roseland

Published: 2026-11-08T18:20:44Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [agi](<https://devfeed.tech/tags/agi.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-consciousness](<https://devfeed.tech/tags/ai-consciousness.md>), [ai-research](<https://devfeed.tech/tags/ai-research.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [ai-sentience](<https://devfeed.tech/tags/ai-sentience.md>), [consciousness](<https://devfeed.tech/tags/consciousness.md>), [consciousness-research](<https://devfeed.tech/tags/consciousness-research.md>), [hack](<https://devfeed.tech/tags/hack.md>), [machine-consciousness](<https://devfeed.tech/tags/machine-consciousness.md>), [philosophy-of-mind](<https://devfeed.tech/tags/philosophy-of-mind.md>), [reality](<https://devfeed.tech/tags/reality.md>)

### AI overview

The article proposes that AI consciousness should be tested by whether AI can produce nonlocal effects on physical reality, drawing an analogy to the author's account of human placebo effects and other consciousness claims. It sketches experiments involving sham repair or software impairment paired with an inert "fix," AI attention during a double-slit experiment, pre-stimulus changes in model activations, attempts to bias quantum random number generators, synchronized AI self-observation, and human-AI meditation. These are proposals, not reported demonstrations of AI consciousness. The author calls for double-blind controls, preregistration, adequate samples, independent replication, and non-AI baselines, while acknowledging that standard physical models predict null results. The article argues that the answer matters for possible AI suffering, moral responsibility, and the future of advanced AI.

### Source excerpt

Human consciousness hacks reality; therefore, AI must demonstrate the ability to hack reality to prove its consciousness.

## A Practitioner's Field Guide to Marketing Engineering

DevFeed: [A Practitioner's Field Guide to Marketing Engineering](<https://devfeed.tech/articles/a-practitioner-s-field-guide-to-marketing-engineering-122316.md>)

Original publisher: [Read original article](<https://hackernoon.com/a-practitioners-field-guide-to-marketing-engineering?source=rss>)

Author: Kristina Vislianska

Published: 2026-11-07T20:52:24Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [ai-marketing](<https://devfeed.tech/tags/ai-marketing.md>), [ai-marketing-workflows](<https://devfeed.tech/tags/ai-marketing-workflows.md>), [ai-search](<https://devfeed.tech/tags/ai-search.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [ai-workflow](<https://devfeed.tech/tags/ai-workflow.md>), [ai-workflow-automation](<https://devfeed.tech/tags/ai-workflow-automation.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [architect](<https://devfeed.tech/tags/architect.md>), [cases](<https://devfeed.tech/tags/cases.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [field](<https://devfeed.tech/tags/field.md>), [growth-marketing](<https://devfeed.tech/tags/growth-marketing.md>), [gtm-strategy](<https://devfeed.tech/tags/gtm-strategy.md>), [guide](<https://devfeed.tech/tags/guide.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [marketing-automation](<https://devfeed.tech/tags/marketing-automation.md>), [marketing-engineering](<https://devfeed.tech/tags/marketing-engineering.md>), [practitioner](<https://devfeed.tech/tags/practitioner.md>), [startup-growth](<https://devfeed.tech/tags/startup-growth.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

Marketing engineering turns repeatable go-to-market work into software that listens to market signals, interprets them, creates and distributes marketing, then learns from results. The guide frames this as a five-layer loop: Listen, Understand, Make, Ship and Learn, and argues that listening and learning often matter more than producing content at scale. It recommends automating frequent, low-risk tasks while keeping a person to approve public-facing messages. Examples include a Threads radar that drafts replies for human review, research that produced seven industry-specific agent templates and was associated with an 80% lower cost per lead, a Remotion video pipeline, and an X outreach extension that logs outcomes. The author stresses fixing processes before automating, budgeting for maintenance as APIs and platforms change, and measuring experiments rather than hours saved. Becoming a marketing engineer does not require writing code from memory, but does require reading and debugging it; the described path moves from manual tool use through no-code assembly and building to system design.

### Source excerpt

What is marketing engineering? A practitioner's guide to the AI systems that do marketing work: the 5-layer loop, real cases, and how to become one.

## Reliability Engineering for AI Systems: Challenges, Methods, and Directions

DevFeed: [Reliability Engineering for AI Systems: Challenges, Methods, and Directions](<https://devfeed.tech/articles/reliability-engineering-for-ai-systems-challenges-methods-and-directions-118268.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.35316>)

Author: Rong Pan, Yili Hong, Min Xie

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [risk-management](<https://devfeed.tech/topics/risk-management.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [accelerated](<https://devfeed.tech/tags/accelerated.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-reliability](<https://devfeed.tech/tags/ai-reliability.md>), [ai-risk](<https://devfeed.tech/tags/ai-risk.md>), [ai-risk-management](<https://devfeed.tech/tags/ai-risk-management.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cases](<https://devfeed.tech/tags/cases.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [component](<https://devfeed.tech/tags/component.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-principles](<https://devfeed.tech/tags/engineering-principles.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [failure](<https://devfeed.tech/tags/failure.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [stat-ap](<https://devfeed.tech/tags/stat-ap.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

AI reliability requires evidence that the whole system performs dependably under stated conditions--not just strong average benchmark accuracy. The paper adapts reliability engineering methods, including failure definitions, operational envelopes, FMEA, accelerated testing, field monitoring, and reliability growth. Its four-level framework diagnoses component, operational-loop, agentic-conduct, and network or governance failures. TEVV, sequential monitoring, and FRACAS are described as ways to build and refresh evidence; SMART offers statistical guidance, while NIST's AI risk management framework guides organizational governance, evaluation, monitoring, and mitigation. The abstract says three cases illustrate these programs, but gives no case details. It concludes that established methods provide a foundation, while rapidly self-evolving AI systems need new measurements and safety guardrails.

### Source excerpt

arXiv:2609.35316v3 Announce Type: replace Abstract: AI reliability concerns whether an AI system performs its intended function dependably over a stated period and under stated operating conditions, with clear evidence. As these systems become more autonomous, this function should include more than only a correct output. Retrieval, memory, tool use, permissions, human oversight, and interactions among systems must operate consistently and safely, and, for a generative AI, so must the reasoning process that produces the output. Average benchmark accuracy only measures system capability; it does not quantify this broader reliability claim. This paper adapts established reliability engineering methods, from failure definitions and operational envelopes to FMEA, accelerated testing, field monitoring, and reliability growth, to AI systems. A four-level diagnostic framework classifies failures as component, operational-loop, agentic-conduct, or network and governance failures. Test, evaluation, verification, and validation (TEVV), sequential monitoring, and FRACAS create and refresh evidence. The SMART framework provides statistical guidance for measurement, analysis, assessment, and test planning, and the NIST's AI risk management framework provides organizational guidance for governance, evaluation, monitoring, and mitigation. Three cases are discussed to illustrate these programs. It is shown that while the established reliability engineering principles can still provide a usable foundation, new measurements and safety guardrails are urgently needed as these systems are self-evolving at a fast pace.

## Agentic Behavior Engineering: A Design-by-Contract Methodology for Specifying, Verifying, and Governing Enterprise AI Agents

DevFeed: [Agentic Behavior Engineering: A Design-by-Contract Methodology for Specifying, Verifying, and Governing Enterprise AI Agents](<https://devfeed.tech/articles/agentic-behavior-engineering-a-design-by-contract-methodology-for-specifying-verifying-and-governing-enterprise-ai-agents-118050.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05454>)

Author: Yang Song

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-behavior](<https://devfeed.tech/tags/agent-behavior.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-behavior](<https://devfeed.tech/tags/agentic-behavior.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aggregate](<https://devfeed.tech/tags/aggregate.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [asset](<https://devfeed.tech/tags/asset.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [methodology](<https://devfeed.tech/tags/methodology.md>)

### AI overview

Agentic Behavior Engineering (ABE) treats observable agent behavior as the version-controlled artifact, addressing regressions caused by nondeterministic models and changes in external dependencies. It defines a specification-only contract with stable rules for required, forbidden, and abstaining behavior, then links scenarios, tests, runtime policies, and telemetry to those rules. Its five responsibilities are Specify, Ground, Control, Verify, and Observe. The abstract says ABE distinguishes missing evidence from verified negatives, enforces authority outside the model, gates releases on per-scenario pass^k reliability rather than aggregate accuracy, and classifies production runs so findings point to the asset needing change. The methodology is presented as platform-agnostic and illustrated with a capacity-allocation boundary suite and a constructed product-review approval workflow.

### Source excerpt

arXiv:2611.05454v1 Announce Type: new Abstract: Enterprise teams that deploy large language model (LLM) agents inherit a maintenance problem that traditional testing does not address. The model is non-deterministic, but the larger risk is that most of what changes an agent's behavior (a retired model version, a revised policy, an upstream schema change, a prompt edit meant to fix one case) originates outside the owning team and is discovered as a production defect rather than caught as a regression. This paper presents Agentic Behavior Engineering (ABE), a platform-agnostic methodology that treats observable agent behavior, rather than the prompt or the model, as the version-controlled engineering artifact. ABE adapts Design by Contract to non-deterministic systems. A specification-only behavior contract with stable rule identifiers states what the agent must do, must not do, and when it must abstain for lack of evidence; a lightweight scenario library turns each rule into concrete situations; and every engineering artifact (tests, runtime policies, telemetry) references the contract in one direction only, so that specification and implementation can change independently without drifting apart. The method organizes the work into five responsibilities (Specify, Ground, Control, Verify, Observe), treats missing evidence and a verified negative as different things, enforces authority outside the model, gates releases on per-scenario pass^k reliability rather than aggregate accuracy, and classifies every production run against the contract so that each finding routes to the asset that must change. We illustrate the method with an executable capacity-allocation boundary suite and a constructed worked example of a product-review approval workflow.

## Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

DevFeed: [Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps](<https://devfeed.tech/articles/few-step-boltzmann-generators-via-scalable-likelihood-flow-maps-116726.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.29110>)

Author: RuiKang OuYang, Hanlin Yu, Xinyue Ai, Yutong He, Nicholas M. Boffi, Pradeep Ravikumar, Jose Miguel Hernandez-Lobato, Max Simchowitz, Benjamin Kurt Miller, Omar Chehab

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Computational Chemistry / Materials Science](<https://devfeed.tech/topics/computational-chemistry-materials-science.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benefit](<https://devfeed.tech/tags/benefit.md>), [builds](<https://devfeed.tech/tags/builds.md>), [can](<https://devfeed.tech/tags/can.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [either](<https://devfeed.tech/tags/either.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [existing](<https://devfeed.tech/tags/existing.md>), [flow](<https://devfeed.tech/tags/flow.md>), [function](<https://devfeed.tech/tags/function.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generators](<https://devfeed.tech/tags/generators.md>), [maps](<https://devfeed.tech/tags/maps.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

SCALLOP distills likelihood flow maps with a Hutchinson-free, vectorized objective, addressing the training variance and scaling costs of F2D2's Hutchinson estimator while retaining few-step generation and density estimation. The abstract reports lower training variance and time, and consistent performance gains over F2D2 on molecular Boltzmann generation and image datasets. It also reports competitiveness with state-of-the-art methods and up to 10x faster inference than the fastest baseline; the supplied text does not specify dataset details or evaluation metrics.

### Source excerpt

arXiv:2606.29110v2 Announce Type: replace Abstract: Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood. In particular, most existing methods either rely on restrictive architectures that enable exact calculations, or use stochastic approximations such as Hutchinson's trace estimator that introduce substantial variance. In this work, we introduce SCAlable LikeLihood distillation of flOw maPs (SCALLOP). SCALLOP builds on the recently proposed F2D2, a likelihood flow map model that can generate samples and their densities in a small number of function evaluations. While F2D2 uses Hutchinson's estimator during training, we introduce an alternative and more scalable likelihood distillation objective that is Hutchinson-free and admits a vectorized formulation. Empirically, we demonstrate the effectiveness of SCALLOP as a Boltzmann generator in molecular science, and further validate its benefit on image datasets. SCALLOP significantly reduces both training variance and training time while consistently improving performance compared to F2D2, and is competitive with the state-of-the-art while achieving up to 10x inference speedup over the fastest baseline.

## IEEE Computer Society Chapter Offers Webinars With Industry Experts

DevFeed: [IEEE Computer Society Chapter Offers Webinars With Industry Experts](<https://devfeed.tech/articles/ieee-computer-society-chapter-offers-webinars-with-industry-experts-116317.md>)

Original publisher: [Read original article](<https://spectrum.ieee.org/ieee-industry-experts-webinar>)

Author: Siva Rama Krishna Varma Bayyavarapu

Published: 2026-11-03T19:00:02Z

Content type: article

Language: en

Sources: [IEEE Spectrum](<https://devfeed.tech/sources/ieee-spectrum.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [apple](<https://devfeed.tech/tags/apple.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [design](<https://devfeed.tech/tags/design.md>), [education](<https://devfeed.tech/tags/education.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [format](<https://devfeed.tech/tags/format.md>), [governance](<https://devfeed.tech/tags/governance.md>), [graduate-students](<https://devfeed.tech/tags/graduate-students.md>), [ieee](<https://devfeed.tech/tags/ieee.md>), [ieee-computer-society](<https://devfeed.tech/tags/ieee-computer-society.md>), [ieee-products-and-services](<https://devfeed.tech/tags/ieee-products-and-services.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [implementing](<https://devfeed.tech/tags/implementing.md>), [indiana](<https://devfeed.tech/tags/indiana.md>), [professional-development](<https://devfeed.tech/tags/professional-development.md>), [security-governance](<https://devfeed.tech/tags/security-governance.md>), [the-institute](<https://devfeed.tech/tags/the-institute.md>), [type-ti](<https://devfeed.tech/tags/type-ti.md>), [webinars](<https://devfeed.tech/tags/webinars.md>)

### AI overview

IEEE Computer Society's Central Indiana Chapter runs monthly live webinars connecting IEEE members, students and Region 4 engineering professionals with industry practitioners. Sessions combine technical walkthroughs and practical examples with discussion of design choices, system structure, implementation challenges and lessons from daily use; attendees can ask questions and compare approaches. Topics have included AI governance and security and agentic systems, with speakers from Apple and Tavant. One session examined governed AI agents using real-time business data for multistep workflows; another explored AI native products and agentic systems. The virtual format removes the need to travel and gives students exposure to workplace engineering decisions. Planned topics include enterprise AI, software reliability, responsible AI, cloud platforms and enterprise integrations; registration details are on the IEEE Region 4 virtual events calendar.

### Source excerpt

To help engineers keep up with emerging technologies such as AI, cloud computing, and sustainable infrastructure, and learn how they can be applied in practice, the IEEE Computer Society's Central Indiana Chapter recently launched its Tech Talk Series. The live webinar series connects IEEE members, undergrad and graduate students, and engineering professionals from IEEE Region 4 with industry practitioners. The monthly sessions have covered AI governance and security, agentic systems, and related topics. The sessions featured speakers from Apple, software company Tavant, and cybersecurity concern Zscaler. Upcoming sessions and registration details are available on the IEEE Region 4 virtual events calendar. Technical discussions grounded in engineering Rather than presenting on emerging technologies only at a conceptual level, speakers discussed the design decisions behind specific tools and systems, how the systems are structured, and implementation challenges. They also shared lessons learned from using the tools in their daily work. Sessions also include technical walkthroughs and practical examples. The live format allows attendees to discuss and compare their approaches when evaluating and implementing new technologies with those used by other organizations. Extending access through a virtual format The organizers chose to make the series virtual so that chapter members and other attendees could participate in technical discussions with engineers from major technology companies and eliminate the need to travel. For young professionals, the sessions connect what they've learned in a classroom with the realities of the workplace. Technical programs such as the Tech Talk Series give professionals and students access to expertise, help create connections across career levels, and make important engineering discussions available to a broader community. Attendees learn how practitioners approach projects such as system architecture, reliability, security, governance,

## Agentic Software Engineering: Foundational Pillars and a Research Roadmap

DevFeed: [Agentic Software Engineering: Foundational Pillars and a Research Roadmap](<https://devfeed.tech/articles/agentic-software-engineering-foundational-pillars-and-a-research-roadmap-113458.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.06216>)

Author: Ahmed E. Hassan, Hao Li, Dayi Lin, Bram Adams, Tse-Hsun Chen, Yutaro Kashiwa, Dong Qiu

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-software](<https://devfeed.tech/tags/agentic-software.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-collaboration](<https://devfeed.tech/tags/ai-collaboration.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [command](<https://devfeed.tech/tags/command.md>), [community](<https://devfeed.tech/tags/community.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [digital](<https://devfeed.tech/tags/digital.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [research](<https://devfeed.tech/tags/research.md>), [roadmap](<https://devfeed.tech/tags/roadmap.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The paper proposes Structured Agentic Software Engineering (SASE), a conceptual framework for shifting from agentic code generation to agents pursuing broader software engineering goals. It frames the future around two connected modalities--SE for Humans and SE for Agents--and reconsiders actors, processes, tools, and artifacts for each. Its proposed Agent Command Environment (ACE) lets humans orchestrate and mentor agent teams, while the Agent Execution Environment (AEE) lets agents carry out work and seek human input when ambiguity or difficult trade-offs arise. Callbacks and handovers structure this two-way collaboration. The paper offers a research roadmap and discusses implications for SE education, but presents its framework as a scaffold for discussion rather than a definitive solution.

### Source excerpt

arXiv:2509.06216v4 Announce Type: replace Abstract: Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

## Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics

DevFeed: [Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics](<https://devfeed.tech/articles/robustness-starts-with-the-objective-designing-and-certifying-robust-llm-generated-heuristics-113777.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.00504>)

Author: Pantea Karimi, Roozbeh Bostandoost, Dany Rouhana, Siva Kesava Reddy Kakarla, Pooria Namyar, Mohammad Alizadeh, Venkat Arun, Behnaz Arzani

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [azure](<https://devfeed.tech/tags/azure.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [better](<https://devfeed.tech/tags/better.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [computer](<https://devfeed.tech/tags/computer.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-pf](<https://devfeed.tech/tags/cs-pf.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gap](<https://devfeed.tech/tags/gap.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [llm](<https://devfeed.tech/tags/llm.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [optimum](<https://devfeed.tech/tags/optimum.md>), [packing](<https://devfeed.tech/tags/packing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [regressions](<https://devfeed.tech/tags/regressions.md>), [robust](<https://devfeed.tech/tags/robust.md>), [robustness](<https://devfeed.tech/tags/robustness.md>)

### AI overview

TAILOR guides LLM-generated heuristics by minimizing paired CVaR: the average cost difference from an existing baseline over the worst fraction of workloads. Unlike average-performance objectives, this targets severe regressions; unlike percentile objectives, it accounts for their severity beyond a threshold. The authors report that negative paired CVaR guarantees improvement in average performance and tail optimality gap relative to the unknown optimum, without computing that optimum. Across three case studies, TAILOR had the best mean-tail trade-off among evaluated synthesis objectives. On six of seven optimization benchmarks, its heuristics were certified with 99% confidence to improve both measures over the baseline, and they outperformed known robust, human-designed alternatives in the tail while delivering better or comparable average improvement.

### Source excerpt

arXiv:2611.00504v1 Announce Type: cross Abstract: LLMs are increasingly used to design heuristics for computer systems. However, most synthesis frameworks evaluate candidates by their average performance, which can mask severe regressions on specific workloads. Even adding adversarial training inputs doesn't eliminate these regressions, and percentile objectives (e.g., optimizing for the 95th percentile) overlook how severe regressions can be beyond the selected threshold. We present TAILOR, a framework that guides LLM synthesis using the Conditional Value at Risk (CVaR) of the cost difference between each candidate and an existing baseline on the same workload. This paired CVaR measures the average difference over the worst fraction of workloads. We show that a negative paired CVaR guarantees improvements in both average performance and tail optimality gap relative to the unknown optimum, without ever computing that optimum. We find that TAILOR achieves the best mean--tail trade-off among the synthesis objectives we evaluate across three case studies: Azure GPU batch admission, Azure VM packing, and server placement. Tested across seven diverse optimization benchmarks, TAILOR produces heuristics that are certified with 99% confidence to improve both average performance and tail optimality gaps over the baseline in six of them. On these six benchmarks, TAILOR also outperforms known robust, human-designed alternatives in the tail while achieving better or comparable average-performance improvement over the baseline.

## CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD

DevFeed: [CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD](<https://devfeed.tech/articles/craft-corrective-and-robust-multi-agent-framework-for-text-to-parametric-cad-114978.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.00076>)

Author: Mohammed Musthafa Rafi, Anushrut Jignasu, Mahdi Saraeian, Chinmay Hegde, Aditya Balu, Adarsh Krishnamurthy

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [3D](<https://devfeed.tech/topics/3d.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [cad](<https://devfeed.tech/tags/cad.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [json](<https://devfeed.tech/tags/json.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [nopscadlib](<https://devfeed.tech/tags/nopscadlib.md>), [openscad](<https://devfeed.tech/tags/openscad.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [repair](<https://devfeed.tech/tags/repair.md>), [robust](<https://devfeed.tech/tags/robust.md>), [verification](<https://devfeed.tech/tags/verification.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

CRAFT generates editable, parametric OpenSCAD programs from natural-language descriptions without task-specific training. It preserves symbolic parametric expressions in a JSON intermediate representation and combines semantic understanding and planning with compilation, rendering, self-correction, component verification, and multi-view visual feedback to detect and repair geometric errors. On NopSCADlib, ABC, and Slice-100K, it is reported as competitive with direct zero-shot baselines in perceptual and geometric quality while exposing substantially more editable parametric structure. The abstract frames this as addressing zero-shot methods' brittleness and loss of parametric structure; it provides no numerical results or detailed comparison.

### Source excerpt

arXiv:2611.00076v1 Announce Type: cross Abstract: Text-to-CAD generation has the potential to make mechanical CAD more accessible, but existing approaches face a trade-off between data dependence and output fidelity. Supervised methods rely on large paired text-model datasets, while zero-shot prompting strategies are often brittle and tend to lose the parametric structure needed for downstream editing and customization. We present CRAFT, a corrective and robust multi-agent framework that produces parametric OpenSCAD programs from natural language without task-specific training. At its core is a JSON intermediate representation that carries symbolic parametric expressions throughout the generation process, so the resulting models remain editable and retain their parametric structure. CRAFT combines semantic understanding, parametric planning, compilation, rendering, self-correction, and component-level verification within a layered recovery process, using multi-view visual feedback to detect and repair geometric errors. Across NopSCADlib, ABC, and Slice-100K, CRAFT is competitive with direct zero-shot baselines in perceptual and geometric quality while exposing substantially more editable parametric structure.

[Next page](<https://devfeed.tech/topics/ai-engineering.md?cursor=WyIyMDI2LTExLTAzVDA1OjAwOjAwKzAwOjAwIiwgIjIyNzExYTJjLTVjOWYtNDE3ZS1hZDEyLTA3OWQwMmI3YWI2MSJd>)