# Code generation

Compiler process that translates an intermediate representation into target machine code, assembly, or other target code.

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

## CrypTorch: Unified PyTorch-based Auto-tuning Compiler for Private Machine Learning Inference

DevFeed: [CrypTorch: Unified PyTorch-based Auto-tuning Compiler for Private Machine Learning Inference](<https://devfeed.tech/articles/cryptorch-unified-pytorch-based-auto-tuning-compiler-for-private-machine-learning-inference-139225.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2511.19711>)

Author: Jinyu Liu, Gang Tan, Kiwan Maeng

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

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [FHE](<https://devfeed.tech/topics/fhe.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>)

Tags: [compiler](<https://devfeed.tech/tags/compiler.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [fhe](<https://devfeed.tech/tags/fhe.md>), [inference](<https://devfeed.tech/tags/inference.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mpc](<https://devfeed.tech/tags/mpc.md>), [performance](<https://devfeed.tech/tags/performance.md>), [private](<https://devfeed.tech/tags/private.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [share](<https://devfeed.tech/tags/share.md>)

### AI overview

CrypTorch addresses the cost and accuracy limits of globally fixed operator approximations in MPC-based machine learning. Its compiler estimates costs from the target MPC backend and quality through proxy PyTorch execution, then auto-selects approximations to maximize performance under a quality constraint. The abstract reports 1.14-1.60x performance improvement across multiple MPC backends with no accuracy loss, or 1.17-1.92x with less than 3% accuracy degradation. Its shared compiler design supports multiple backends, and its auto-tuner also reduces bootstrapping operations by 1.31-1.65x on a related FHE backend.

### Source excerpt

arXiv:2511.19711v3 Announce Type: replace Abstract: MPC-based ML uses secure multi-party computation (MPC) to execute machine learning (ML) workloads across multiple parties without requiring any party to reveal its private data or model parameters. Our characterization study finds that the performance of state-of-the-art MPC frameworks is often dominated by operator-approximation strategies, where ML operators not natively supported by MPC are replaced with iterative methods or polynomials. These approximations are typically chosen heuristically by each framework and applied globally. As a result, they can be unnecessarily expensive in some cases, yet insufficiently accurate in others. We find that the best approximation choice depends on the context, target framework, and application, making a single globally fixed approximation fundamentally suboptimal. To address this problem, we design CrypTorch, a multi-stage compiler for MPC-based ML that supports multiple MPC frameworks as backends. At the core of CrypTorch is its auto-tuning stage, which extracts cost estimates from the target MPC backend and quality estimates from a proxy PyTorch execution, and uses them to automatically select a set of approximations that maximizes performance while satisfying the given quality constraint. We show that CrypTorch's auto-tuner improves performance across multiple MPC backends by 1.14--1.60x without degrading accuracy, and by 1.17--1.92x with less than 3% accuracy degradation. CrypTorch's unified design also improves programmability and usability by allowing multiple backends to share other common compiler functionality and optimizations. We further show that the auto-tuner extends to a related fully homomorphic encryption (FHE) backend, reducing the number of bootstrapping operations by 1.31--1.65x.

## LLVM's Old AMD R600 Compiler Backend Slated For Removal

DevFeed: [LLVM's Old AMD R600 Compiler Backend Slated For Removal](<https://devfeed.tech/articles/llvm-s-old-amd-r600-compiler-backend-slated-for-removal-135358.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/LLVM-R600-Backend-To-Retire>)

Author: Michael Larabel

Published: 2026-11-16T13:04:01Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [deprecated](<https://devfeed.tech/topics/deprecated.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [backend](<https://devfeed.tech/tags/backend.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [legacy](<https://devfeed.tech/tags/legacy.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [mesa](<https://devfeed.tech/tags/mesa.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [radeon](<https://devfeed.tech/tags/radeon.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

AMD has proposed removing LLVM's R600 back-end, which supports Radeon HD 2000-6000 GPUs. Its former Mesa R600 Gallium3D and Clover OpenCL uses have ended: Mesa's R600g driver moved to NIR, and Clover was replaced by Rusticl. With no known users or maintainers, the legacy code and lit tests add upkeep and complicate changes to the modern AMDGPU back-end. The RFC covers R600/TeraScale hardware only; GCN and newer GPUs using AMDGPU are unaffected. The excerpt says no concerns had been raised at the time.

### Source excerpt

The old ATI/AMD Radeon R600 back-end within the LLVM compiler codebase will likely be removed given it's become a legacy burden and doesn't have any current use by the modern Mesa driver stack...

## FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly

DevFeed: [FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly](<https://devfeed.tech/articles/forge-fault-oriented-rework-code-generation-for-executable-interlocking-assembly-115325.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02536>)

Author: Fuqiang Wang, Jiahao Fu, Ren Hefeng, Yining Qian, Chuanting Zhang, Cheng Tan, Yuwen Liu, Jingxuan Wei

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

Content type: article

Language: en

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

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [tgi](<https://devfeed.tech/topics/tgi.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [actions](<https://devfeed.tech/tags/actions.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [assembly](<https://devfeed.tech/tags/assembly.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [essential](<https://devfeed.tech/tags/essential.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [forge](<https://devfeed.tech/tags/forge.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [rework](<https://devfeed.tech/tags/rework.md>)

### AI overview

FORGE addresses the gap between identifying an assembly fault and generating executable rework that restores the intended configuration. Its FORGE-Bench benchmark contains 4,000 tasks across 26 interlocking assemblies, with five assemblies held out to evaluate generalization to unseen structures. The framework separates rework into two stages: Rework Structuring captures recovery dependencies caused by faults, and Action Grounding maps them to state-conditioned executable actions. The reported experiments find that locally plausible repair code can still fail, and that linking structural recovery reasoning to executable actions is important for verified restoration.

### Source excerpt

arXiv:2611.02536v1 Announce Type: new Abstract: Large language models have demonstrated strong capabilities in structured reasoning and code generation, yet identifying an assembly fault does not guarantee the ability to generate executable rework programs. In interlocking assemblies, a locally plausible repair program may violate blocking dependencies, omit required recovery operations, or terminate in an incorrect configuration. We identify this challenge as fault-conditioned executable rework generation, where models must jointly reason about structural failures and generate programs that restore constrained assembly states. To benchmark this capability, we introduce FORGE-Bench, containing 4,000 tasks across 26 interlocking assemblies with five assemblies held out for evaluating generalization to unseen structures. We further propose FORGE (Fault-Oriented Rework Code Generation for Executable Interlocking Assembly), a structured state-to-program framework that decomposes rework generation into Rework Structuring and Action Grounding. Rework Structuring captures fault-induced recovery dependencies, while Action Grounding maps these dependencies into state-conditioned executable actions. Experiments show that locally reasonable repair code is insufficient for reliable assembly recovery, and that connecting structural recovery reasoning with executable action realization is essential for verified target restoration.

## Isomorphism Is Not Enough: An Agentic Audit of Verified Code Generation in Lean

DevFeed: [Isomorphism Is Not Enough: An Agentic Audit of Verified Code Generation in Lean](<https://devfeed.tech/articles/isomorphism-is-not-enough-an-agentic-audit-of-verified-code-generation-in-lean-113467.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.23772>)

Author: Alessandro Sosso, Akhil Arora, Bas Spitters

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

Content type: news

Language: en

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

Topics: [Lean](<https://devfeed.tech/topics/lean.md>), [Formal verification](<https://devfeed.tech/topics/formal-verification.md>), [audit](<https://devfeed.tech/topics/audit.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [audit](<https://devfeed.tech/tags/audit.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [lean](<https://devfeed.tech/tags/lean.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

An audit of CLEVER, a Lean 4 benchmark for verifiable code generation, found arguably erroneous reference specifications in 80 of 161 entries and showed that isomorphism-based scoring can fail when two defensible formalizations differ. Across three agentic stacks based on Claude Opus 4.6, GPT-5.4, and Kimi K2.5, the work reports up to 98.8% arguably valid specification generation, 92.3% implementation certification against sound specifications, and 96.2% end-to-end success on entries with sound premises. The authors suggest CLEVER may no longer sufficiently challenge modern agentic provers and offer the error analysis as a benchmark repair list and checklist for future benchmark design.

### Source excerpt

arXiv:2605.23772v2 Announce Type: replace-cross Abstract: Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification and how reliably existing benchmarks can measure them, we audit CLEVER, a Lean 4 benchmark for verifiable code generation, using three independent agentic stacks based on Claude Opus 4.6, GPT-5.4, and Kimi K2.5. Our audit finds arguably erroneous reference specifications in 80 of 161 entries, each accepted by the benchmark's authors, distills a taxonomy of benchmark errors, and exposes structural limitations of isomorphism-based scoring, whose signal breaks down when generated and reference specifications formalize different yet defensible readings. In the process, the stacks generate arguably valid specifications for up to 98.8% of entries, certify implementations against sound reference specifications for up to 92.3%, and reach up to 96.2% end-to-end success over entries with sound premises, suggesting that CLEVER no longer stresses modern agentic provers as much as its design intended. Looking ahead, we translate our findings into recommendations for future work, with our error analysis doubling as a repair list for CLEVER and a heuristic checklist for the next generation of benchmarks.

## Gleam doesn't compile to Erlang source anymore

DevFeed: [Gleam doesn't compile to Erlang source anymore](<https://devfeed.tech/articles/gleam-doesn-t-compile-to-erlang-source-anymore-64919.md>)

Original publisher: [Read original article](<https://gleam.run/news/gleam-doesnt-compile-to-erlang-source-anymore>)

Author: Louis Pilfold

Published: 2026-10-05T00:00:00Z

Content type: release

Language: en

Sources: [Gleam](<https://devfeed.tech/sources/gleam.md>)

Topics: [Compiler](<https://devfeed.tech/topics/compiler.md>), [Erlang](<https://devfeed.tech/topics/erlang.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>)

Tags: [beam](<https://devfeed.tech/tags/beam.md>), [build-times](<https://devfeed.tech/tags/build-times.md>), [code-generator](<https://devfeed.tech/tags/code-generator.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [debuggers](<https://devfeed.tech/tags/debuggers.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [erlang](<https://devfeed.tech/tags/erlang.md>), [gleam](<https://devfeed.tech/tags/gleam.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [performance](<https://devfeed.tech/tags/performance.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [source-code](<https://devfeed.tech/tags/source-code.md>), [syntax](<https://devfeed.tech/tags/syntax.md>), [type-safe](<https://devfeed.tech/tags/type-safe.md>), [virtual-machine](<https://devfeed.tech/tags/virtual-machine.md>)

### AI overview

Gleam v1.19.0 rewrites its Erlang code generator to emit Erlang abstract forms, which the Erlang compiler can load directly, skipping its tokenizer and parser. The article reports faster Erlang builds and runtime location metadata that points accurately to Gleam source, improving crash reports and stack traces; debugger support such as edb is described as a possibility, not completed work. It favors abstract forms over direct BEAM bytecode because bytecode changes across VM releases, and reproducing Erlang compiler optimizations would take substantial ongoing effort. The release also flattens generated JavaScript for pattern matches, improves short-list construction while retaining array conversion for longer lists, preserves TypeScript generic types through overloads, adds build-tool support including generated `.app` files and a `--no-dev` flag, and adds language-server label operations, browser formatting capability, and more targeted errors. Its compilation benchmark compares a small synthetic workload and is explicitly limited; it cannot establish performance across real projects.

### Source excerpt

Gleam is a type-safe and scalable language for the Erlang virtual machine and JavaScript runtimes. Today Gleam v1.19.0 has been published, so let's go over what's new. A new compilation target Over the last few months Giacomo Cavalieri has entirely rewritten Gleam's Erlang code generator that has an entirely different design, and most notably, outputs a different format. Previously Gleam generated Erlang source code, now it generates Erlang abstract forms. "Erlang abstract forms" is an intermediate representation used by the Erlang compiler. It is a metadata-annotated tree that represents Erlang syntax, and it is normally produced by running Erlang's tokeniser and parser. It has a binary encoding using Erlang's external term format, and with this binary format we can load our generated code directly, skipping the front-half of the Erlang compiler. This new Erlang code generator brings several benefits: The performance of the compiler has been improved, significantly reducing the build times for Gleam projects running on Erlang. The location metadata available to the runtime is now accurate to original Gleam source code, rather than to the Erlang source code the compiler would generate. This means, for example, the line numbers in BEAM crash reports and stacktraces are perfectly accurate, while previously they could be inaccurate, only pointing to the nearest function. This metadata could also enable full support for Gleam in debuggers such as edb, though we have not done any work on this ourselves. The code-quality of the Gleam compiler has been improved. The Erlang code generator was one of the oldest and most stable parts of the Gleam codebase, so while it wasn't causing us any problems it wasn't conforming to the standards and conventions we have today. This new replacement is excellent, and arguably raising the bar for the compiler as whole. We never have to hear someone use the word "transpiler" as a pejorative ever again.1 Ok, so how fast is it? I'm going to s

## AI in Chip Design: From Code Generation to EDA Orchestration (University of Edinburgh)

DevFeed: [AI in Chip Design: From Code Generation to EDA Orchestration (University of Edinburgh)](<https://devfeed.tech/articles/ai-in-chip-design-from-code-generation-to-eda-orchestration-university-of-edinburgh-55469.md>)

Original publisher: [Read original article](<https://semiengineering.com/ai-in-chip-design-from-code-generation-to-eda-orchestration-university-of-edinburgh/>)

Author: Technical Paper Link

Published: 2026-09-19T18:30:22Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-ml-dl](<https://devfeed.tech/tags/ai-ml-dl.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [chip](<https://devfeed.tech/tags/chip.md>), [chip-design](<https://devfeed.tech/tags/chip-design.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [design-automation](<https://devfeed.tech/tags/design-automation.md>), [design-verification](<https://devfeed.tech/tags/design-verification.md>), [eda](<https://devfeed.tech/tags/eda.md>), [eda-orchestration](<https://devfeed.tech/tags/eda-orchestration.md>), [electronic-design-automation](<https://devfeed.tech/tags/electronic-design-automation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hardware-design](<https://devfeed.tech/tags/hardware-design.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [rtl-generation](<https://devfeed.tech/tags/rtl-generation.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [technical-papers](<https://devfeed.tech/tags/technical-papers.md>), [university](<https://devfeed.tech/tags/university.md>), [university-of-edinburgh](<https://devfeed.tech/tags/university-of-edinburgh.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Researchers at the University of Edinburgh examine how large language models could support digital electronic design automation, comparing generator, agent, and orchestrator roles. The perspective highlights challenges including plausible but physically incorrect code, fragmented tools, and loss of design context, and proposes physics-aware orchestration for more reliable hardware design.

### Source excerpt

Researchers at the University of Edinburgh published a technical perspective titled "LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration." Abstract Excerpt: "In this Perspective, we instead define three hierarchical roles that reveal how capability accumulates: a Generator that produces design artifacts in a single pass, an Agent that refines outputs... " read more The post AI in Chip Design: From Code Generation to EDA Orchestration (University of Edinburgh) appeared first on Semiconductor Engineering.

## Rust is Now a 'Tier One' Language at Microsoft

DevFeed: [Rust is Now a 'Tier One' Language at Microsoft](<https://devfeed.tech/articles/rust-is-now-a-tier-one-language-at-microsoft-55106.md>)

Original publisher: [Read original article](<https://developers.slashdot.org/story/26/09/13/2144215/rust-is-now-a-tier-one-language-at-microsoft>)

Author: EditorDavid

Published: 2026-09-18T14:34:00Z

Content type: news

Language: en

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

Topics: [Rust](<https://devfeed.tech/topics/rust.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [c-sharp](<https://devfeed.tech/tags/c-sharp.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [developers](<https://devfeed.tech/tags/developers.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [rust](<https://devfeed.tech/tags/rust.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

Microsoft has designated Rust a Tier One language for internal development, placing it alongside C++, C# and TypeScript with strong tooling and process support across the software development lifecycle. Rust is already used in more than 100 Microsoft repositories and in services including Microsoft 365 and Copilot-related technology.

### Source excerpt

The Register reports: When Microsoft's developers and engineers sit down to code, they can now choose to work in Rust, which Redmond has added to its list of canonical languages. "Rust now is a Tier One language at Microsoft, and that just means that it sits among C++, C# and TypeScript as the best supported languages for internal development in the company," explained Victor Ciura, Microsoft principal engineer for the Rust tooling team, during a keynote talk today at this year's annual RustConf, being held this week in Montréal. Ciura said Microsoft has "paved a path" of tools and processes that support local Rust development across the entire software development lifecycle. Rust is no stranger at Microsoft and is already present in over 100 Microsoft project repositories. The company has built Oxidizer, a set of crates to build scalable services in Rust, which have been used to build and refine the Microsoft 365 core services such as Outlook, Word, Excel, OneDrive, and SharePoint. The Copilot tech stack also owes quite a bit to Rust... [C]ompany engineers built rustc_codegen_utc, a custom Rust compiler code-generation backend that wires the rustc compiler directly into the Microsoft Visual C++ internal toolchain for Windows... "The result is a unified code generation platform for Rust and C++ on Windows" [Ciura wrote in a blog post, noting that more than 100 Microsoft project repositories now build with rustc_codegen_utc.] Still, Redmond running towards Rust is a welcome development. In his 2025 RustConf keynote, Microsoft Azure CTO Mark Russinovich noted that ~70 percent of Windows CVEs are memory issues. "One of the things that I realized a long time ago is that no matter how much we really want to make C and C++ better, we can't make it as good as what Rust starts with," he said. Read more of this story at Slashdot.

## Why client SDK generation belongs in the open

DevFeed: [Why client SDK generation belongs in the open](<https://devfeed.tech/articles/why-client-sdk-generation-belongs-in-the-open-42092.md>)

Original publisher: [Read original article](<https://developers.googleblog.com/why-client-sdk-generation-belongs-in-the-open/>)

Author: Amir Hardon; Philipp Schmid

Published: 2026-09-18T01:27:10.987787Z

Content type: release

Language: en

Sources: [Google Developers Blog](<https://devfeed.tech/sources/google-developers-blog.md>)

Topics: [Code generation](<https://devfeed.tech/topics/code-generation.md>), [SDK](<https://devfeed.tech/topics/sdk.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openapi](<https://devfeed.tech/tags/openapi.md>), [sdk-generation](<https://devfeed.tech/tags/sdk-generation.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

### AI overview

Google and Speakeasy are open-sourcing an OpenAPI code generation suite under the AGPLv3 license after the shutdown of Google's previous proprietary SDK provider. The suite generates deterministic, multi-language client libraries and supports strict typing, streaming, agent-native CLIs, and documentation MCP servers.

### Source excerpt

Google has partnered with Speakeasy to open-source their OpenAPI code generation suite under the AGPLv3 license, a strategic move prompted by the sudden shutdown of Google's previous proprietary SDK provider. The newly open-sourced suite equips developers with deterministic, multi-language SDK generators that natively support strict typing and SSE streaming, alongside tools for compiling agent-native CLIs and documentation MCP servers. Engineering teams can now safely integrate this robust tooling directly into their CI pipelines to automatically generate reliable client libraries for their own APIs, all while retaining complete licensing control over the output code.

## What's New in Apollo Client 4.3

DevFeed: [What's New in Apollo Client 4.3](<https://devfeed.tech/articles/what-s-new-in-apollo-client-4-3-32028.md>)

Original publisher: [Read original article](<https://www.apollographql.com/blog/whats-new-in-apollo-client-4-3>)

Author: Jerel Miller

Published: 2026-09-15T12:01:05Z

Content type: release

Language: en

Sources: [Apollo Blog](<https://devfeed.tech/sources/apollo-blog.md>)

Topics: [apollo-client](<https://devfeed.tech/topics/apollo-client.md>), [GraphQL](<https://devfeed.tech/topics/graphql.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>)

Tags: [apollo-client](<https://devfeed.tech/tags/apollo-client.md>), [cache](<https://devfeed.tech/tags/cache.md>), [codegen](<https://devfeed.tech/tags/codegen.md>), [graphql](<https://devfeed.tech/tags/graphql.md>), [native](<https://devfeed.tech/tags/native.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

Apollo Client 4.3 adds native custom scalar support, type-safe cache access, and improved TypeScript handling for incremental GraphQL data. The release also updates generated types and data-state narrowing for deferred fields.

### Source excerpt

Apollo Client 4.3 is here: native custom scalar support, type-safe cache access, and more consistent @defer and @stream behavior. See what's new and upgrade today.

## Generate standalone types with Smithy

DevFeed: [Generate standalone types with Smithy](<https://devfeed.tech/articles/generate-standalone-types-with-smithy-50113.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/developer/generate-standalone-types-with-smithy/>)

Author: Jordon Phillips

Published: 2026-09-08T16:03:12Z

Content type: tutorial

Language: en

Sources: [AWS Developer Tools Blog](<https://devfeed.tech/sources/aws-developer-tools-blog.md>)

Topics: [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [interface](<https://devfeed.tech/topics/interface.md>), [service](<https://devfeed.tech/topics/service.md>)

Tags: [announcements](<https://devfeed.tech/tags/announcements.md>), [aws-sdk](<https://devfeed.tech/tags/aws-sdk.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [generate](<https://devfeed.tech/tags/generate.md>), [serialization](<https://devfeed.tech/tags/serialization.md>), [services](<https://devfeed.tech/tags/services.md>), [smithy](<https://devfeed.tech/tags/smithy.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

This tutorial explains how Smithy shape closures can generate standalone types for event payloads, allowing services and subscribers to share generated definitions and serialization instead of maintaining separate copies. It notes support in smithy-java and smithy-typescript.

### Source excerpt

Without generated standalone types, a service that publishes events ends up with the payload defined manually in several places. The service has its own definition, and every consumer has their own definition. This is tedious, error-prone busywork for consumers. And as the service evolves, changes to events can expose bugs. A missing field or changed [...]

## Introducing CUDA Rust: Two Tracks for Writing GPU Kernels

DevFeed: [Introducing CUDA Rust: Two Tracks for Writing GPU Kernels](<https://devfeed.tech/articles/introducing-cuda-rust-two-tracks-for-writing-gpu-kernels-6871.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/introducing-cuda-rust-two-tracks-for-writing-gpu-kernels/>)

Author: Elizabeth Goodman

Published: 2026-09-08T12:00:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [GPU](<https://devfeed.tech/topics/gpu.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [toolchain](<https://devfeed.tech/topics/toolchain.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [cuda-tile](<https://devfeed.tech/tags/cuda-tile.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [dynamo](<https://devfeed.tech/tags/dynamo.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [nemo-retriever](<https://devfeed.tech/tags/nemo-retriever.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [programming-languages-compilers](<https://devfeed.tech/tags/programming-languages-compilers.md>), [rust](<https://devfeed.tech/tags/rust.md>), [toolchains](<https://devfeed.tech/tags/toolchains.md>)

### AI overview

NVIDIA introduces CUDA Rust for writing GPU kernels natively in Rust and compiling them to PTX. The article explains the SIMT and Tile programming tracks, recommends Tile as the default, and describes cuda-oxide's Rust-based code-generation path.

### Source excerpt

In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and...

## Shift-Left Defensibility: Architecting Immutable Software Moats

DevFeed: [Shift-Left Defensibility: Architecting Immutable Software Moats](<https://devfeed.tech/articles/shift-left-defensibility-architecting-immutable-software-moats-50881.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/shift-left-defensibility-architecting-immutable-software-moats/>)

Author: رامي الغدران

Published: 2026-09-06T17:50:40Z

Content type: article

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [Software](<https://devfeed.tech/topics/software.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Back end](<https://devfeed.tech/topics/backend.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Database](<https://devfeed.tech/topics/database.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [backend](<https://devfeed.tech/tags/backend.md>), [boilerplate](<https://devfeed.tech/tags/boilerplate.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [llm](<https://devfeed.tech/tags/llm.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

This technical article argues that code volume and predictable application components are becoming commoditized by code-generation tools and LLM agents. It proposes building durable software advantages from immutable workflow context, including human-validated telemetry and a TypeScript backend that captures contextual overrides and edge-case decisions.

### Source excerpt

null Continue reading Shift-Left Defensibility: Architecting Immutable Software Moats on SitePoint.

## The AI Equalizer: How Generative AI is Leveling Modern Digital Moats

DevFeed: [The AI Equalizer: How Generative AI is Leveling Modern Digital Moats](<https://devfeed.tech/articles/the-ai-equalizer-how-generative-ai-is-leveling-modern-digital-moats-50885.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/the-ai-equalizer-how-generative-ai-is-leveling-modern-digital-moats/>)

Author: رامي الغدران

Published: 2026-09-06T16:05:11Z

Content type: opinion

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [migration](<https://devfeed.tech/topics/migration.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Vibe coding](<https://devfeed.tech/topics/vibe-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [migration](<https://devfeed.tech/tags/migration.md>)

### AI overview

This opinion argues that generative AI and large language models are weakening traditional software and technology business moats. It describes AI-assisted scaffolding, code generation, automated legacy migration, and rapid replication as reducing the defensibility of feature breadth and implementation speed, and asks what may constitute a stronger digital moat.

### Source excerpt

null Continue reading The AI Equalizer: How Generative AI is Leveling Modern Digital Moats on SitePoint.

## Test what you ship: MSTest and Native AOT

DevFeed: [Test what you ship: MSTest and Native AOT](<https://devfeed.tech/articles/test-what-you-ship-mstest-and-native-aot-2952.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/dotnet/mstest-source-generation/>)

Author: Amaury Levé

Published: 2026-09-03T18:00:00Z

Content type: article

Language: en

Sources: [.NET Blog](<https://devfeed.tech/sources/net-blog.md>)

Topics: [native aot](<https://devfeed.tech/topics/native-aot.md>), [trimming](<https://devfeed.tech/topics/trimming.md>), [.NET](<https://devfeed.tech/topics/net.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>)

Tags: [deployment](<https://devfeed.tech/tags/deployment.md>), [generation](<https://devfeed.tech/tags/generation.md>), [mstest](<https://devfeed.tech/tags/mstest.md>), [native-aot](<https://devfeed.tech/tags/native-aot.md>), [net](<https://devfeed.tech/tags/net.md>), [source-generators](<https://devfeed.tech/tags/source-generators.md>), [testing](<https://devfeed.tech/tags/testing.md>), [trimming](<https://devfeed.tech/tags/trimming.md>)

### AI overview

MSTest 4.4 uses source generation to let test projects run as Native AOT executables, helping teams test under the same trimming and deployment constraints as their applications. The article explains that this can reveal application issues such as reflection-dependent serialization that managed test runs may miss.

### Source excerpt

MSTest source generation lets test projects use the same Native AOT and trimming deployment model as the applications they validate, while reducing reflection on the test execution path. The post Test what you ship: MSTest and Native AOT appeared first on .NET Blog.

## Why AI-Generated Code Is Easy but Engineering Trust Is Hard

DevFeed: [Why AI-Generated Code Is Easy but Engineering Trust Is Hard](<https://devfeed.tech/articles/why-ai-generated-code-is-easy-but-engineering-trust-is-hard-52426.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/why-ai-generated-code-is-easy-but-engineering-trust-is-hard/>)

Author: Scott Nyberg

Published: 2026-08-20T21:56:01Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [test](<https://devfeed.tech/topics/test.md>), [Boilerplate](<https://devfeed.tech/topics/boilerplate.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agent](<https://devfeed.tech/tags/ai-coding-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [plan](<https://devfeed.tech/tags/plan.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [technical-debt](<https://devfeed.tech/tags/technical-debt.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

An engineering article examines why AI-generated code can pass builds, tests, and code review while still implementing an ambiguous requirement incorrectly. It argues that engineering trust must be established earlier by making assumptions, success measures, unresolved questions, and failure conditions explicit in a specification before implementation begins.

### Source excerpt

Imagine an AI coding agent generating a large pull request filled with AI-generated code. Everything looks exactly as it should: Later, your team discovers the agent quietly misinterpreted an ambiguous requirement near the beginning of the implementation. Every decision that followed was internally consistent. The tests validated the implementation. The reviewer approved the diff. The [...] The post Why AI-Generated Code Is Easy but Engineering Trust Is Hard appeared first on Salesforce Engineering Blog.

## MSVC Build Tools Preview updates - August 2026

DevFeed: [MSVC Build Tools Preview updates - August 2026](<https://devfeed.tech/articles/msvc-build-tools-preview-updates-august-2026-2958.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/cppblog/msvc-build-tools-preview-updates-august-2026/>)

Author: Eric Brumer

Published: 2026-08-13T15:01:10Z

Content type: article

Language: en

Sources: [C++ Team Blog](<https://devfeed.tech/sources/c-team-blog.md>)

Topics: [MSVC](<https://devfeed.tech/topics/msvc.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [toolchain](<https://devfeed.tech/topics/toolchain.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Visual Studio](<https://devfeed.tech/topics/visual-studio.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [diagnostics](<https://devfeed.tech/tags/diagnostics.md>), [features](<https://devfeed.tech/tags/features.md>), [ide](<https://devfeed.tech/tags/ide.md>), [msvc](<https://devfeed.tech/tags/msvc.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [release](<https://devfeed.tech/tags/release.md>), [tools](<https://devfeed.tech/tags/tools.md>), [updates](<https://devfeed.tech/tags/updates.md>), [visual-studio](<https://devfeed.tech/tags/visual-studio.md>), [visual-studio-2026](<https://devfeed.tech/tags/visual-studio-2026.md>)

### AI overview

The article summarizes August 2026 updates to the MSVC Build Tools Preview, targeting the v14.52 release. It covers compiler conformance, diagnostics, C++ modules, code generation, optimization, and ARM64 improvements.

### Source excerpt

Try the latest updates to MSVC Build Tools Preview The post MSVC Build Tools Preview updates - August 2026 appeared first on C++ Team Blog.

## Practical AI in Platform Engineering: lessons from Port's latest meetup

DevFeed: [Practical AI in Platform Engineering: lessons from Port's latest meetup](<https://devfeed.tech/articles/practical-ai-in-platform-engineering-lessons-from-port-s-latest-meetup-12291.md>)

Original publisher: [Read original article](<https://www.port.io/blog/practical-ai-in-platform-engineering-lessons-from-ports-latest-meetup>)

Author: Matar Peles

Published: 2026-08-10T11:42:45Z

Content type: article

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [sdlc](<https://devfeed.tech/topics/sdlc.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Incident response](<https://devfeed.tech/topics/incident-response.md>), [Infrastructure as code](<https://devfeed.tech/topics/infrastructure-as-code.md>), [Security](<https://devfeed.tech/topics/security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [iac](<https://devfeed.tech/tags/iac.md>), [ide](<https://devfeed.tech/tags/ide.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [platform-engineering](<https://devfeed.tech/tags/platform-engineering.md>), [review](<https://devfeed.tech/tags/review.md>), [sdlc](<https://devfeed.tech/tags/sdlc.md>), [security](<https://devfeed.tech/tags/security.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

Port's Tel Aviv meetup examined how engineering organizations are adopting AI in platform engineering. Speakers discussed agentic workflows for bug triage, platform requests, and the SDLC, while an anonymous survey measured AI maturity, production deployments, evaluation practices, human oversight, and concerns about autonomy. Most teams reported having a few SDLC agents but not scaling them broadly; code review and code generation were the most common production uses, while operational applications such as infrastructure, security, and incident response lagged behind.

### Source excerpt

We hosted a meetup with engineering leaders working on AI inside their orgs and ran an anonymous survey. Here's what came out of it.

## Keleusma Research Spike: Blocking Frequency as the Ordering Principle for Instruction-Set Coverage

DevFeed: [Keleusma Research Spike: Blocking Frequency as the Ordering Principle for Instruction-Set Coverage](<https://devfeed.tech/articles/keleusma-research-spike-blocking-frequency-as-the-ordering-principle-for-instruction-set-coverage-39752.md>)

Original publisher: [Read original article](<https://sgeos.github.io/engineering/compilers/verification/2026/08/06/native_lowering_coverage.html>)

Author: Brendan Sechter

Published: 2026-08-06T09:00:00Z

Content type: article

Language: en

Sources: [Brendan A R Sechter's Development Blog](<https://devfeed.tech/sources/brendan-a-r-sechter-s-development-blog.md>)

Topics: [Compiler](<https://devfeed.tech/topics/compiler.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [article](<https://devfeed.tech/tags/article.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [compilers](<https://devfeed.tech/tags/compilers.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [ordering](<https://devfeed.tech/tags/ordering.md>), [research](<https://devfeed.tech/tags/research.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

This case study examines how blocking frequency can guide the order of instruction implementation in Keleusma's compiler backend. It contrasts instruction-level coverage with whole-program compilability and describes a small measurement tool that exposed a flawed implementation plan.

### Source excerpt

A compiler was 87 percent finished. It could not compile two thirds of the programs it was for. Both numbers are correct. The first counts individual instructions the compiler knew how to translate. The second counts whole programs that would actually go through. The gap between them is what this article is about, and the reason it exists is simple enough to state in one sentence. A program needs every instruction it uses, not most of them. One missing instruction out of a hundred stops the whole thing, exactly as one missing link stops a chain. That gap then destroyed a carefully reasoned plan. One working session before the measurement was taken, the author of this article had formally recommended what the next piece of work should be. The reasoning had no invalid step in it. The measurement showed the recommendation to be worth nothing at all, because the thing it would have unblocked does not occur even once in any program the compiler is meant to serve. The instrument that established this took about twenty minutes to build and two seconds to run. The article reports that, and then reports four errors made while writing it, all four of which ran in the direction of a more striking result, and one of which was committed inside the paragraph warning against the other three. What this is a case study of The setting is compiler engineering, and a reader who has never written a compiler can follow the argument, because the shape of the problem is not specific to compilers. The concrete project is Keleusma, whose compiler until now has emitted bytecode for a virtual machine, as described in the self-hosting strategy and its getting-started article. Native code generation is the step after that one, and it is where the ordering question first became expensive enough to measure. The lineage of the design sits in the stream-based compilers series and in the self-hosted silicon compiler. None of that background is needed to follow what follows, and the measurement stands

## KotlinLLM is Going Open Source

DevFeed: [KotlinLLM is Going Open Source](<https://devfeed.tech/articles/kotlinllm-is-going-open-source-8796.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/research/2026/07/kotlinllm-open-source/>)

Author: Anastasia Birillo

Published: 2026-07-28T07:50:41Z

Content type: article

Language: en

Sources: [Kotlin](<https://devfeed.tech/sources/kotlin-a-concise-multiplatform-language-developed-by-jetbrains-the-jetbrains-blog.md>)

Topics: [Kotlin](<https://devfeed.tech/topics/kotlin.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [code-completion](<https://devfeed.tech/tags/code-completion.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [intellij](<https://devfeed.tech/tags/intellij.md>), [intellij-idea](<https://devfeed.tech/tags/intellij-idea.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [kotlinllm](<https://devfeed.tech/tags/kotlinllm.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [research](<https://devfeed.tech/tags/research.md>), [research-prototype](<https://devfeed.tech/tags/research-prototype.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

KotlinLLM is an open-source research prototype and IntelliJ IDEA plugin for Kotlin/JVM projects. It introduces Smart macros whose generated Kotlin source evolves from runtime scenarios, allowing applications to delegate selected logic to an LLM without calling the model on every request or relying on a separate runtime agent.

### Source excerpt

TL;DR KotlinLLM is now public. It's a research prototype for delegating runtime logic to an LLM from Kotlin code. Instead of calling an LLM on every request or running a separate agent, you can write an explicit Kotlin call. Its body is generated Kotlin source code, and that code is updated as your application hits [...]

## Casper: Snap's fleet of friendly AI teammates

DevFeed: [Casper: Snap's fleet of friendly AI teammates](<https://devfeed.tech/articles/casper-snap-s-fleet-of-friendly-ai-teammates-56677.md>)

Original publisher: [Read original article](<https://eng.snap.com/casper>)

Published: 2026-07-28T07:00:00Z

Content type: article

Language: en

Sources: [Snap](<https://devfeed.tech/sources/snap.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [development](<https://devfeed.tech/tags/development.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [identity-security](<https://devfeed.tech/tags/identity-security.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>)

### AI overview

Snap describes Casper, a fleet of autonomous AI agents that works through Slack and a web console to perform software engineering tasks, including coding, code review, data queries, project management, and pull request creation. The system keeps engineers involved in judgment decisions while handling repetitive work.

### Source excerpt

Casper: Snap's fleet of friendly AI teammates Software engineering is changing fast. Across the industry, the question is no longer whether AI can write production code, it's how much of the development lifecycle organizations are willing to offload to the agents. At Snap, we continue to increase the amount we count on agents for the work while keeping the human in the loop for judgement decisions.

## NVIDIA Nemotron 3 Ultra Leads Open Models on Accuracy and Efficiency in Agentic RTL Coding

DevFeed: [NVIDIA Nemotron 3 Ultra Leads Open Models on Accuracy and Efficiency in Agentic RTL Coding](<https://devfeed.tech/articles/nvidia-nemotron-3-ultra-leads-open-models-on-accuracy-and-efficiency-in-agentic-rtl-coding-6901.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/nvidia-nemotron-3-ultra-leads-open-models-on-accuracy-and-efficiency-in-agentic-rtl-coding/>)

Author: Nirmal Kumar Juluru

Published: 2026-07-27T00:45:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Programming](<https://devfeed.tech/topics/programming.md>), [Verilog](<https://devfeed.tech/topics/verilog.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [debugging](<https://devfeed.tech/topics/debugging.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [long-context](<https://devfeed.tech/topics/long-context.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [automation](<https://devfeed.tech/tags/automation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [chip-design](<https://devfeed.tech/tags/chip-design.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coding](<https://devfeed.tech/tags/coding.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [featured](<https://devfeed.tech/tags/featured.md>), [hardware-semiconductor](<https://devfeed.tech/tags/hardware-semiconductor.md>), [llms](<https://devfeed.tech/tags/llms.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [models](<https://devfeed.tech/tags/models.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open](<https://devfeed.tech/tags/open.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

NVIDIA's article presents ACE-RTL and Nemotron 3 Ultra as a combined approach to agentic RTL coding. The workflow generates Verilog, runs simulations and other EDA checks, analyzes failures, and iteratively refines designs while maintaining debugging context. The CVDP benchmark evaluates accuracy and efficiency on realistic RTL generation, modification, debugging, and verification tasks.

### Source excerpt

Modern chip design is increasingly limited by engineering time. Register transfer level (RTL) development and verification require specialized hardware...

## Fragments: July 21

DevFeed: [Fragments: July 21](<https://devfeed.tech/articles/fragments-july-21-4432.md>)

Original publisher: [Read original article](<https://martinfowler.com/fragments/2026-07-21.html>)

Author: Martin Fowler (martin@martinfowler.com)

Published: 2026-07-21T13:13:00Z

Content type: article

Language: en

Sources: [Martin Fowler](<https://devfeed.tech/sources/martin-fowler.md>)

Topics: [Vibe coding](<https://devfeed.tech/topics/vibe-coding.md>), [Security](<https://devfeed.tech/topics/security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [data-quality](<https://devfeed.tech/tags/data-quality.md>), [llms](<https://devfeed.tech/tags/llms.md>), [modernization](<https://devfeed.tech/tags/modernization.md>), [security](<https://devfeed.tech/tags/security.md>), [testing](<https://devfeed.tech/tags/testing.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>)

### AI overview

The article discusses findings from a software development retreat, emphasizing that verification has become more important as code generation improves. It examines risks from LLMs and vibe coding, including security concerns, poor contextual fit, weak testing, and inadequate data-quality controls. It argues for feedback sensors, organizational safeguards, and stronger engagement between engineers and executives.

### Source excerpt

With this post, I'll wrap up my notes from the second Future of Software Development Retreat. But before I do, I should note that the full Thoughtworks report on the retreat is now available. They have five headline findings: Code generation is no longer the bottleneck -- verification is. 'Harness engineering' is emerging as a distinct, ownable discipline. Organizations are colliding with a real apprenticeship crisis. The executive/engineer expectation gap is a bigger risk than any technical limitation. Legacy modernization is the clearest, most defensible near-term value pool. ❄ ❄ A session convened around the mismatch of views about using LLMs between engineers using it and the C-suite and boards that were calling for it. The concern is that boards are looking at promised productivity gains, and not concerned enough about the risks, particularly about security. This was illustrated by one tale of a company that used ML-trained software to optimize the replacement of air filters on their field equipment. They were pleased to see that they were able to change the air filters less frequently, saving them $50 million. But the problem was the ML models were trained on equipment used in the desert, while their equipment was used in the arctic. Air filters in the desert deal with dust, but in the arctic the thing to remove is mosquitoes. There's an important difference here, mosquitoes rot, and enough decaying mosquitoes is a serious fire risk. Fires from such dead mosquitoes around infrequently replaced air filters cost the company $100 billion. Now such a tale could told of many situations without AI in the mix. Plenty of human situations have gone wrong when solutions are applied in a new context (which is why context is such a key word among pattern-writers). But the tale does remind us to be wary of an AI's suggestions, and to always think of how to build sensors to provide rapid feedback. Engineers particularly worry about the risks when citizen developers start vib

## Migrating from Apollo Tooling to GraphQL Codegen at Yelp

DevFeed: [Migrating from Apollo Tooling to GraphQL Codegen at Yelp](<https://devfeed.tech/articles/migrating-from-apollo-tooling-to-graphql-codegen-at-yelp-27428.md>)

Original publisher: [Read original article](<https://engineeringblog.yelp.com/2026/07/migrating-to-graphql-codegen.html>)

Author: Igor Kusakov, Software Engineer

Published: 2026-07-16T00:00:00Z

Content type: article

Language: en

Sources: [Yelp](<https://devfeed.tech/sources/yelp.md>)

Topics: [GraphQL](<https://devfeed.tech/topics/graphql.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [migration](<https://devfeed.tech/topics/migration.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [React](<https://devfeed.tech/topics/react.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [monorepo](<https://devfeed.tech/topics/monorepo.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [deprecated](<https://devfeed.tech/tags/deprecated.md>), [graphql](<https://devfeed.tech/tags/graphql.md>), [migrate](<https://devfeed.tech/tags/migrate.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [react](<https://devfeed.tech/tags/react.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

Yelp describes migrating its frontend React monorepo from deprecated Apollo Tooling to GraphQL Codegen for generating TypeScript definitions from GraphQL queries and the server schema.

### Source excerpt

Introduction At Yelp, we rely heavily on GraphQL and Apollo for data loading in our frontend React monorepo. When a developer writes a GraphQL query or mutation inside a React component, the shape of the response is defined by the query itself -- but TypeScript has no way to know what that shape looks like at compile time. That's where code generation (codegen) comes in. We rely on codegen to read our queries and server schema, then produce TypeScript type definitions for every operation's input variables and output data. In our codebase, this looks like: src/components/UserProfile/ ├── UserProfile.tsx <- contains...

## How ParparVM Reached Performance Parity with Warmed Java 25

DevFeed: [How ParparVM Reached Performance Parity with Warmed Java 25](<https://devfeed.tech/articles/how-we-beat-hotspot-performance-by-cheating-but-not-like-that-19212.md>)

Original publisher: [Read original article](<https://www.codenameone.com/blog/beating-hotspot-performance/>)

Author: Shai Almog

Published: 2026-07-10T00:00:00Z

Content type: article

Language: en

Sources: [CodeName One](<https://devfeed.tech/sources/codename-one.md>)

Topics: [Java](<https://devfeed.tech/topics/java.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [C](<https://devfeed.tech/topics/c.md>), [Project Valhalla](<https://devfeed.tech/topics/project-valhalla.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [c](<https://devfeed.tech/tags/c.md>), [java](<https://devfeed.tech/tags/java.md>), [memory](<https://devfeed.tech/tags/memory.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [project-valhalla](<https://devfeed.tech/tags/project-valhalla.md>)

### AI overview

This article explains how ParparVM, an ahead-of-time virtual machine that compiles Java bytecode to C, improved from 4.21x slower than warmed Java 25 to geometric-mean parity across ten benchmarks. It describes changes involving heap layout, code generation, allocation, and collection, with correctness checked against HotSpot.

### Source excerpt

ParparVM went from 4.21x slower than warmed Java 25 to geomean parity, with peak memory below the JVM's. The architecture behind it, in C terms.

[Next page](<https://devfeed.tech/topics/code-generation.md?cursor=WyIyMDI2LTA3LTEwVDAwOjAwOjAwKzAwOjAwIiwgImUwZWFkYTczLTNhNTEtNDU3Mi05NzZkLWI5N2RlMWY2NGM1MSJd>)