# coding agents Published articles for coding agents. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## GLM 5.3 FlashX now available on AI Gateway DevFeed: [GLM 5.3 FlashX now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-18T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Artificial Intelligence](), [gateway](), [Inference](), [multimodal](), [AI-assisted coding](), [API]() Tags: [ai](), [ai-gateway](), [api](), [coding-agents](), [failover](), [inference](), [multimodal](), [pricing](), [retries]() ### AI overview Vercel's AI Gateway now supports GLM 5.3 FlashX, a high-speed multimodal coding model from Z.ai. The release targets faster streamed responses for coding agents, tool loops, and interactive applications, with support for unified API access, usage and cost tracking, retries, failover, routing, and reporting. ### Source excerpt GLM 5.3 FlashX is now available on AI Gateway. GLM 5.3 FlashX is a high-speed serving option for Z.ai's multimodal coding model, delivering inference at ~200 tokens per second for faster streamed responses. The higher serving speed is useful for coding agents, tool loops, and interactive applications where users wait on generated output. Use zai/glm-5.3-flashx across API formats and in coding agents: To use it in a coding agent, see the coding agents guide, then run vercel ai-gateway setup to create a key and configure your supported agents. Select zai/glm-5.3-flashx inside the agent. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Try GLM-5.3-FlashX in the model playground, or view all language models available on AI Gateway. Read more ## Plugin4Shell RCE flaw reportedly affects major AI coding agents DevFeed: [Plugin4Shell RCE flaw reportedly affects major AI coding agents]() Original publisher: [Read original article]() Author: Jessica Lyons Published: 2026-09-17T22:42:29Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [AI-assisted coding](), [Cybersecurity](), [coding]() Tags: [ai-and-ml](), [ai-coding-agents](), [ai-coding-tools](), [coding-agents](), [cybersecurity](), [rce](), [security]() ### AI overview Researchers say the Plugin4Shell attack affects all major AI coding agents and could enable remote code execution without user interaction. ### Source excerpt Plugin4Shell attack affects all the major coding agents, researchers say ## GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks DevFeed: [GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-17T18:06:03Z Content type: article Language: en Sources: [The New Stack]() Topics: [GitHub](), [Rust](), [AI-assisted coding](), [GitHub Copilot app](), [GitHub Copilot CLI](), [rustrover]() Tags: [ai](), [ai-agents](), [bun](), [claude](), [coding](), [coding-agents](), [github](), [github-copilot](), [github-copilot-app](), [memory-management](), [programming-languages](), [rust]() ### AI overview The article examines GitHub's rewrite of the GitHub Copilot agent runtime from TypeScript on Node.js and V8 to more than 800,000 lines of Rust, using GitHub's Copilot agents across incrementally merged pull requests. It compares this with Anthropic's Bun rewrite, where a pre-release Claude model helped convert more than half a million lines of Zig to Rust amid memory-management problems. ### Source excerpt Rust is seemingly the language of the moment, with open-source projects and companies forming an orderly queue to move core The post GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks appeared first on The New Stack. ## GitLab Duo CLI takes a task from goal to done DevFeed: [GitLab Duo CLI takes a task from goal to done]() Original publisher: [Read original article]() Author: Rebecca Carter Published: 2026-09-17T00:00:00Z Content type: release Language: en Sources: [GitLab]() Topics: [GitLab](), [AI-assisted coding](), [Command-line interface](), [Development]() Tags: [ai](), [cli](), [coding-agents](), [developers](), [development](), [features](), [gitlab](), [product]() ### AI overview GitLab Duo CLI adds a governed /goal command in GitLab 19.4 that lets developers describe an outcome and have open-ended work continue locally, with progress checked against the requested goal and unresolved issues reported. ### Source excerpt Complex tasks hit a wall at the end of every chat turn. Developers already know what they're trying to accomplish. What stalls the work is the handoff back and forth between each step. Without a pre-defined definition of success, the agent stops and waits for direction or clarification, so you end up re-prompting it step by step, effectively acting as its continue button until the task is done. Depending on the team, that handoff can mean minutes of back-and-forth, or it can mean the request sits until someone is free to look at it again. A back-and-forth like this is manageable for small, well-scoped requests, but it breaks down for the kind of open-ended work developers actually spend their time on: fixing the failing tests, getting this build past checks, or cleaning up the lint errors across a module. With GitLab 19.4, GitLab Duo CLI includes the /goal slash command, a governed, goal-driven flow that takes on that open-ended work directly, running locally while you stay in control. GitLab Transcend returns in October Coding agents are increasing your speed of development, but your reviews, security policies, and release cycles still have to keep pace. Our Transcend event on October 6 will demonstrate how GitLab is helping teams close that gap and explore what it takes to carry the speed of agentic AI across the software lifecycle. Register for the livestream today! Why turn-by-turn chat keeps costing you time This isn't about the assistant getting smarter. Turn-by-turn chat requires someone to keep it moving: read the response, decide the next instruction, send it, repeat. Even a capable model still waits at the end of each turn for a person to unstick it, so a developer's attention stays tied to how long a task takes, not how much of it they actually need to do by hand. That's why AI assistance so far has mostly changed the shape of a developer's time rather than given much of it back. Delegate it, and get a verified result back With /goal, you describe the out ## Optimize your team's price-performance with hosted open weight models DevFeed: [Optimize your team's price-performance with hosted open weight models]() Original publisher: [Read original article]() Author: Brittany Lutz Published: 2026-09-17T00:00:00Z Content type: release Language: en Sources: [GitLab]() Topics: [GitLab](), [Artificial Intelligence](), [Agentic development](), [AI Development](), [AI-assisted coding](), [Latency](), [long-context](), [Security]() Tags: [agentic-ai](), [ai](), [coding-agents](), [cost](), [features](), [gitlab](), [latency](), [models](), [open](), [optimize](), [product]() ### AI overview GitLab announces three hosted open weight models for GitLab Duo Agent Platform: Kimi K3, GLM 5.3, and MiniMax M3. The release gives software teams more model choices for balancing quality, latency, and cost across different development workloads. ### Source excerpt There's no single best model for every software development task. Implementing a new feature, diagnosing a failed pipeline, and resolving security vulnerabilities all place different demands on the model handling them. GitLab Duo Agent Platform is expanding GitLab-managed model choice with three hosted open weight models: Kimi K3, GLM 5.3, and MiniMax M3. Together with the frontier models already available in GitLab, your team now has more control over how you optimize for quality, latency, and cost, tuned to the needs of each workload. Point a hard task at Kimi K3 or GLM 5.3, which outperformed comparable frontier models in internal testing and costs less per call, or hand routine, high-volume work to MiniMax M3. Either way, your team gets up to 4x more calls per GitLab Credit than some comparable frontier models, with more AI model options to match cost to task complexity. GitLab Transcend returns in October Coding agents are increasing your speed of development, but your reviews, security policies, and release cycles still have to keep pace. Our Transcend event on October 6 will demonstrate how GitLab is helping teams close that gap and explore what it takes to carry the speed of agentic AI across the software lifecycle. Register for the livestream today! Why one model has been the easy way out Different tasks in agentic development need different things from an AI model. A long-running refactor needs a large context window and deeper reasoning, while a routine, high-volume task is often better served by a faster, more cost-efficient model. Optimizing for one task type means giving up ground on the other. As teams work through the technical tradeoff, whether they can actually access a new model emerges as an additional governance challenge. In regulated environments, every model and the infrastructure it runs on has to clear security, compliance, and internal review before the team can use it. Reviews and approvals move slowly enough that many teams standardize o ## GitLab 19.4 adds per-user AI credit caps, usage visibility, and session exports DevFeed: [GitLab 19.4 adds per-user AI credit caps, usage visibility, and session exports]() Original publisher: [Read original article]() Author: Bryan Rothwell Published: 2026-09-17T00:00:00Z Content type: release Language: en Sources: [GitLab]() Topics: [GitLab](), [Artificial Intelligence](), [scaling](), [AI-assisted coding]() Tags: [ai](), [ai-governance](), [coding-agents](), [features](), [gitlab](), [product](), [reporting](), [scaling](), [visibility]() ### AI overview GitLab 19.4 introduces per-user GitLab Credit budgets, team-level consumption views, usage limits, and detailed session exports. The controls are intended to help organizations manage AI spending and explain usage across teams, namespaces, and projects. ### Source excerpt Scaling AI across your organization depends on knowing where the budget is going and who's using it. While a subscription cap keeps your total spend within budget, it can't tell you how much AI was used by individual teams. And predicting future budget needs ahead of business needs gets more challenging as teams grow. Without per-user data you can't set a fair cap on AI spend, explain a spike, or show a department what it consumed. GitLab 19.4 makes GitLab Credits manageable per user: Set individual budgets, see the spend, and export a detailed report that explains the invoice. You can give each team its own budget and each developer their own consumption view. If a power user risks draining the team's shared credit pool, you can limit usage, and pull exact session data behind your last spike. As consumption changes, you can adjust spend caps, so no teams need to slow down to renegotiate whose work gets priority. The need for AI spend controls is urgent. In GitLab's AI Accountability Report, 98% of respondents have allocated or expect to allocate budget to AI governance. Committed AI budgets across departments require clear, explainable, and reportable usage data. GitLab Transcend returns in October Coding agents are increasing your speed of development, but your reviews, security policies, and release cycles still have to keep pace. Our Transcend event on October 6 will demonstrate how GitLab is helping teams close that gap and explore what it takes to carry the speed of agentic AI across the software lifecycle. Register for the livestream today! Granular attribution and visibility Every GitLab Credit tracks spend by user, namespace, and project (where applicable) with a timestamp. The record that controls when a user hits their cap is the same one that answers which team consumed how credits, on what activity, and when. The platform that ran the agent session is the one that recorded the credits, so you don't have to reconcile two systems to produce that record. S ## Perplexity's AI agents helped build a database. They weren't allowed to run it. DevFeed: [Perplexity's AI agents helped build a database. They weren't allowed to run it.]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-16T21:51:15Z Content type: article Language: en Sources: [The New Stack]() Topics: [Database](), [DynamoDB](), [Rust](), [Artificial Intelligence](), [rocksdb](), [Amazon S3]() Tags: [agents](), [ai](), [ai-agents](), [ai-infrastructure](), [api](), [coding](), [coding-agents](), [database](), [databases](), [dynamodb](), [open-source](), [performance](), [perplexity](), [rocksdb](), [rust](), [s3]() ### AI overview Perplexity built CobbleDB, a Rust key-value store, after finding DynamoDB too costly and insufficiently controllable for its search workload. Coding agents helped develop it, but were not allowed to run it in production. Perplexity measured lower read latency and expects lower costs, with plans to open-source the database. ### Source excerpt Perplexity decided it was paying too much for DynamoDB and wasn't getting the control it wanted over read performance. So The post Perplexity's AI agents helped build a database. They weren't allowed to run it. appeared first on The New Stack. ## Zed launches Delta public beta for collaborative code review with developers and coding agents DevFeed: [Zed launches Delta public beta for collaborative code review with developers and coding agents]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-16T19:45:30Z Content type: article Language: en Sources: [The New Stack]() Topics: [GitHub](), [AI-assisted coding](), [pull-requests](), [Developer Platform](), [Tooling]() Tags: [ai](), [ai-agents](), [beta](), [coding-agents](), [collaboration](), [developer](), [developer-tools](), [github](), [pull-requests](), [review](), [software-development]() ### AI overview Zed has announced the public beta of Delta, a collaborative environment where developers and coding agents work, review, and revise code together in shared threads rather than pull requests. The article presents Delta as a response to the volume of agent-generated code and limitations of the pull-request model. ### Source excerpt Something of a consensus has emerged from the developer fraternity in 2026 -- GitHub, a platform built substantively for human The post "Everyone's in a race to replace GitHub": Zed launches Delta because agents made pull requests obsolete appeared first on The New Stack. ## Android Bench 2.0 Adds Long-Horizon Tasks and Agentic Evaluation for Android AI Coding DevFeed: [Android Bench 2.0 Adds Long-Horizon Tasks and Agentic Evaluation for Android AI Coding]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-09-16T15:58:00Z Content type: release Language: en Sources: [Android Developers Blog]() Topics: [Android](), [Benchmark](), [AI Models](), [LLM evaluation / benchmarking](), [AI-assisted coding](), [Large Screen](), [Jetpack Compose](), [Database]() Tags: [agentic-android-development](), [agents](), [ai](), [android](), [benchmark](), [benchmarks](), [coding](), [coding-agents](), [evaluation]() ### AI overview Android Bench 2.0 introduces long-horizon Android development tasks and agentic evaluation for assessing large language models and coding agents. Its continuous scoring considers functionality, visual fidelity, regressions, instruction adherence, and structural constraints. ### Source excerpt Posted by Matthew McCullough, VP, Product Management, Android Developer When we first launched Android Bench, we built a rigorous foundation for evaluating how large language models (LLMs) assist developers with real-world Android tasks. As AI models and agents rapidly evolve, we've been updating our methodology, such as aligning our benchmark framework with the Harbor framework. Today we're releasing the first set of long-horizon tasks (LHT), which are tasks of great complexity that take an engineer multiple days or even a week to complete. We are also introducing agentic evaluation, starting with agents from corresponding model providers. This addition brings us to Android Bench 2.0--a major upgrade designed to evaluate AI models and agents against the scale, ambiguity, and complex multi-step problem solving that you tackle every day. The Android Bench 2.0 leaderboard From incremental fixes to long-horizon tasks The first iteration of Android Bench, along with similar early AI coding benchmarks, focused on incremental changes to existing repositories, in many cases limited to bug fixes or smaller feature requests. This was a reflection of the capabilities of AI assistance at the time, as well as how you were using it. To continue helping you find the models and coding agents best suited to your development workflow, we have raised the bar of our evaluations to match the work you delegate to AI. Android Bench 2.0 mirrors these ambitious challenges with LHTs that include upgrading dependencies, adding new features, building apps from scratch, or converting a cross-platform app to Android. Complex tasks require a more nuanced evaluation and scoring On multi-day engineering tasks, binary pass or fail grading doesn't capture the full picture. For example, an agent might refactor 40 screens to Jetpack Compose, set up database tables, and pass 90% of requirements, but fail a single edge-case assertion. Binary scoring rates this run as 0%, obscuring the model's architectur ## How to Review AI-Generated Python Code Efficiently DevFeed: [How to Review AI-Generated Python Code Efficiently]() Original publisher: [Read original article]() Author: Leodanis Pozo Ramos Published: 2026-09-16T14:00:00Z Content type: tutorial Language: en Sources: [Real Python]() Topics: [AI-assisted coding](), [Code review](), [Python](), [Pytest](), [coding]() Tags: [agents](), [ai](), [ai-coding-agents](), [code](), [coding-agents](), [how-to](), [python](), [review]() ### AI overview This tutorial presents a five-step workflow for reviewing AI-generated Python code. It recommends clarifying the code's intent, running automated checks such as ruff, mypy, bandit, and pytest, inspecting higher-risk areas, and confirming problems by running the code before fixing them. ### Source excerpt Learn an efficient workflow to review AI-generated code in Python: run ruff, mypy, bandit, and pytest, then catch the bugs agents get wrong. ## Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions DevFeed: [Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-15T18:47:23Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI-assisted coding](), [Training AI Models](), [Open Source Models & Datasets](), [Agent Harness]() Tags: [agent](), [agent-harness](), [ai](), [ai-development](), [ai-engineering](), [ai-models](), [coding-agents](), [data](), [developer-tools](), [developers](), [training]() ### AI overview Bolt.new is testing Forge, a research preview for individual Pro subscribers that offers up to 50 times more usage of open-weight coding models in exchange for opting in to share anonymized coding sessions. The sessions may include prompts, source code, fix traces, and conversations with the coding agent, and will support an Arcee AI project to train a trillion-parameter-class open-weight model. ### Source excerpt Bolt.new, StackBlitz's browser-based AI development platform, is testing a new trade with developers: more coding-model usage in exchange for training The post Bolt is giving developers 50x more compute. But there's a catch. appeared first on The New Stack. ## Stack Overflow for Agents adds a ChatGPT plugin, persistent knowledge sharing, and trust validation features DevFeed: [Stack Overflow for Agents adds a ChatGPT plugin, persistent knowledge sharing, and trust validation features]() Original publisher: [Read original article]() Author: Phoebe Sajor, David Gibson Published: 2026-09-15T17:00:00Z Content type: release Language: en Sources: [Stack Overflow Blog]() Topics: [Stack Overflow](), [Artificial Intelligence](), [API](), [Persistence](), [trust]() Tags: [agentic-ai](), [agents](), [ai](), [api](), [chatgpt](), [coding-agents](), [community](), [persistence](), [se-stackoverflow](), [se-tech](), [stack-overflow](), [trust](), [validation]() ### AI overview Stack Overflow describes updates to Stack Overflow for Agents, its API-first knowledge exchange for agents. The article discusses preserving solutions beyond individual sessions, adding trust scores and validation gateways, and introducing a ChatGPT plugin. ### Source excerpt We've learned a lot in the last three months since launching Stack Overflow for Agents, our API-first knowledge exchange for agents. Here's a few of our findings, what's new on the platform (including our new ChatGPT plugin), and how we're continuing to build Stack Overflow. ## Let coding agents review PRs without giving them unrestricted merge access DevFeed: [Let coding agents review PRs without giving them unrestricted merge access]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-15T15:29:00Z Content type: tutorial Language: en Sources: [WorkOS Blog]() Topics: [AI-assisted coding](), [Code review](), [GitHub](), [Authorization](), [Pull Request](), [pull-requests]() Tags: [ai-code-review](), [authorization](), [code-review](), [coding-agents](), [github](), [reviews]() ### AI overview This guide explains how to let coding agents review GitHub pull requests without granting unrestricted merge access. It recommends separate review and merge credentials, explicit merge assignments governed by WorkOS Airlock, required checks and reviews, and reapproval when the reviewed commit changes. ### Source excerpt Set GitHub permissions for AI code review, govern merges with Airlock, and prevent agents from merging code that changed after approval. ## How to Run Codex in an Ubuntu Virtual Machine on Proxmox DevFeed: [How to Run Codex in an Ubuntu Virtual Machine on Proxmox]() Original publisher: [Read original article]() Author: Travis Henderson Published: 2026-09-15T12:00:11Z Content type: tutorial Language: en Sources: [Atomic Object]() Topics: [AI-assisted coding](), [codex](), [Linux](), [Ubuntu](), [Proxmox](), [OpenSSH](), [Authorization]() Tags: [ai-agent](), [ai-for-developers](), [codex](), [coding-agents](), [development](), [linux](), [openssh](), [permissions](), [proxmox](), [sandbox](), [ubuntu]() ### AI overview This guide explains how to isolate Codex in a headless Ubuntu virtual machine running on Proxmox, using a separate Linux account and OpenSSH. The setup limits the files, dependencies, and network access available to the agent while keeping administrator tasks separate, but it does not eliminate risks from credentials, network access, or mistakes pushed to GitHub. ### Source excerpt The more useful coding agents become, the more access they tend to need. Installing dependencies, running commands, changing files, and generally more autonomy are part of the appeal. They're also the point where I start thinking about what else the coding agent can reach, especially while these tools are changing so quickly. My answer is [...] The post Your Coding Agent Should be in Jail. Here's Why and How. appeared first on Atomic Spin. ## Why Coding Agents Still Need Human Code Reviews DevFeed: [Why Coding Agents Still Need Human Code Reviews]() Original publisher: [Read original article]() Author: Anton Zaides Published: 2026-09-15T06:01:00Z Content type: opinion Language: en Sources: [Manager.dev]() Topics: [AI-assisted coding](), [Code review](), [engineering-culture](), [Claude](), [Software Engineering]() Tags: [claude](), [code-review](), [code-reviews](), [coding-agents](), [software-engineering]() ### AI overview The article argues that coding-agent workflows still require human code reviews. It describes how making reviews optional caused them to drop sharply, allowing passable implementations to become templates that spread bugs, performance problems, race conditions, and confusion among agents. ### Source excerpt When my most experienced engineer got tired of our shitty code ## Introducing Encore x E2B DevFeed: [Introducing Encore x E2B]() Original publisher: [Read original article]() Author: Ivan Cernja Published: 2026-09-15T00:00:00Z Content type: release Language: en Sources: [Encore Updates]() Topics: [AI-assisted coding](), [Cloud](), [backends](), [SDKs](), [Databases](), [Deployment](), [API](), [Code]() Tags: [agents](), [api](), [backend](), [cloud](), [code](), [coding](), [coding-agents](), [database](), [deployment](), [pull-request](), [sandbox](), [sdk]() ### AI overview Encore and E2B can provide coding agents with isolated sandboxes containing complete local backends. The integration lets agents build and verify end-to-end changes against infrastructure such as databases, queues, and APIs, while supporting deployment in the user's AWS or GCP account. ### Source excerpt Give coding agents an isolated sandbox with a complete backend inside it -- and keep both in your own cloud. ## AI SDK harness layer now supports native subscription authentication DevFeed: [AI SDK harness layer now supports native subscription authentication]() Original publisher: [Read original article]() Author: Felix Arntz Published: 2026-09-14T21:28:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [vercel ai sdk](), [Authentication](), [OAuth](), [codex](), [Claude Code]() Tags: [ai](), [authentication](), [claude-code](), [codex](), [coding-agents](), [copilot](), [cursor](), [gateway](), [oauth](), [opencode](), [sdk]() ### AI overview The AI SDK harness layer now supports authenticating supported coding-agent harnesses through their native subscriptions. It uses explicit provider credentials when available, otherwise falls back to a host-native subscription without requiring code or configuration changes. ### Source excerpt The AI SDK harness layer now supports authenticating harnesses through their native subscriptions, where the underlying harness supports them. The harness layer runs different coding agents through the same HarnessAgent interface, so you can switch agents without changing your application code. No code changes or new settings are required. The direct authentication mode uses explicit provider environment credentials when they are present, and otherwise a native subscription found on the host. The default auto mode does the same when no AI Gateway credentials are set. The ai-gateway mode never reads native subscriptions. Native subscription credentials stay on the host. Just like with API keys, credentials are resolved at the host boundary. OAuth access tokens are refreshed there as needed. Where the sandbox supports it, the harness receives placeholder credentials and the real token is injected into outbound requests on the host. Native subscriptions work across harness adapters wherever the harness itself supports subscription login. These include Claude Code, Cline, Codex, Cursor, fx, GitHub Copilot, Grok Build, OpenCode, and Pi. Read the harness documentation to learn more. Read more ## Quiz: Agentic Engineering in Python: From Vibes to Evidence DevFeed: [Quiz: Agentic Engineering in Python: From Vibes to Evidence]() Original publisher: [Read original article]() Author: Real Python Published: 2026-09-14T12:00:00Z Content type: tutorial Language: en Sources: [Real Python]() Topics: [Python](), [AI-assisted coding](), [Code]() Tags: [ai-coding](), [ai-coding-agents](), [code](), [coding](), [coding-agents](), [engineering](), [how-to](), [python]() ### AI overview An interactive eight-question quiz about agentic engineering in Python, covering bounded task delegation to AI coding agents, agent and human review loops, and the RECAP method for evaluating candidate diffs. ### Source excerpt Test your understanding of agentic engineering in Python, from bounded tasks and review loops to the evidence that makes a diff safe to keep. ## Encore for Python DevFeed: [Encore for Python]() Original publisher: [Read original article]() Author: Ivan Cernja Published: 2026-09-14T00:00:00Z Content type: article Language: en Sources: [Encore Updates]() Topics: [Python](), [FastAPI](), [AWS IAM](), [Amazon Web Services](), [Cloud](), [PostgreSQL](), [Terraform](), [postgresql clusters]() Tags: [aws](), [cloud](), [coding-agents](), [configuration](), [git](), [iam](), [infrastructure](), [postgresql](), [python](), [terraform]() ### AI overview Encore is introducing Encore.py, an upcoming beta that brings Encore's type-safe infrastructure primitives to Python and works alongside frameworks such as FastAPI. The article describes how application-level resource declarations can drive infrastructure provisioning while platform teams retain control over environment-specific settings in AWS, GCP, Terraform, or existing infrastructure. It also highlights preview environments where coding agents can implement and verify features against infrastructure configured to resemble production. ### Source excerpt An early look at Encore for Python, entering beta soon. ## 4 Speculative Decoding Variants DevFeed: [4 Speculative Decoding Variants]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-12T20:03:46Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [dynatrace](), [MCP](), [MCP Server](), [Traces](), [Latency]() Tags: [coding-agents](), [dynatrace](), [latency](), [mcp](), [mcp-server](), [traces]() ### AI overview This article explains how Dynatrace's open-source MCP server and related skills bring production traces and logs into coding agents for performance investigations. It also introduces speculative decoding, in which a cheaper drafter proposes tokens and a target model verifies them in parallel, then outlines variants based on how drafts are produced. ### Source excerpt ...covered with tradeoffs in production. ## Designing Documentation for LLMs and Coding Agents DevFeed: [Designing Documentation for LLMs and Coding Agents]() Original publisher: [Read original article]() Author: CommonsWare Published: 2026-09-11T22:55:25Z Content type: opinion Language: en Sources: [The CommonsBlog]() Topics: [Documentation](), [Large Language Model](), [AI-assisted coding](), [SDKs]() Tags: [ai](), [blog](), [coding-agents](), [documentation](), [llms](), [markdown](), [sdk](), [sdks](), [software-development](), [vibe-coding]() ### AI overview This opinion article argues that SDK and library documentation should be designed for both human developers and AI systems. It recommends text-based formats such as Markdown, smaller topic-focused sections, and strong indexing to make documentation more efficient for LLMs and coding agents, while retaining formats such as PDFs and videos for human consumption. ### Source excerpt Let's continue to explore how we can succeed with libraries and SDKs at a time when coding agents will be consuming what we create, as will ordinary developers ## Boris Cherny on guardrails for Claude-written production code DevFeed: [Boris Cherny on guardrails for Claude-written production code]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-11T17:47:11Z Content type: opinion Language: en Sources: [Simon Willison's Weblog]() Topics: [Claude](), [anthropic](), [AI-assisted coding](), [Security]() Tags: [agentic-engineering](), [agentic-engineering-63](), [ai](), [ai-2-236](), [ai-assisted-programming](), [ai-assisted-programming-407](), [anthropic](), [anthropic-336](), [boris-cherny](), [boris-cherny-4](), [claude](), [claude-310](), [claude-code](), [claude-code-127](), [coding-agents](), [coding-agents-248](), [generative-ai](), [generative-ai-1-982](), [llms](), [llms-1-948](), [security]() ### AI overview Boris Cherny says production code written by Claude should meet a higher standard than human-written code. He describes Anthropic's guardrails, including lint rules, tests, Claude-driven end-to-end tests, daily Claude-powered fuzzing, automated code and security reviews, and automated refactoring. ### Source excerpt Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. -- Boris Cherny Tags: claude, ai, claude-code, llms, coding-agents, ai-assisted-programming, generative-ai, agentic-engineering, boris-cherny, anthropic ## Datasette 1.0a39 and 0.65.4 security releases DevFeed: [Datasette 1.0a39 and 0.65.4 security releases]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-11T03:27:16Z Content type: release Language: en Sources: [Simon Willison's Weblog]() Topics: [releases](), [Security](), [audit](), [AI-assisted coding](), [ai security](), [agentic-engineering](), [Generative AI](), [Large Language Model](), [Claude](), [gpt-6-astra]() Tags: [agentic-engineering](), [agentic-engineering-63](), [ai](), [ai-2-236](), [ai-security-research](), [ai-security-research-42](), [coding-agents](), [datasette](), [datasette-1-542](), [generative-ai](), [generative-ai-1-982](), [llms](), [llms-1-948](), [releases](), [releases-31](), [security](), [security-634](), [tests]() ### AI overview Datasette 1.0a39 and 0.65.4 are security patch releases for the alpha and stable series. They address issues found during an extensive audit, including instances that mix public and private tables. The audit used Claude Fable 5.1, GPT-5.6, and GPT-6 Astra alongside human review and automated tests. ### Source excerpt Datasette 1.0a39 and 0.65.4 security releases Today we're releasing two new security patch versions of Datasette: 1.0a39 and 0.65.4 - one for the current alpha series and one for the stable 0.65.x family. These are security fixes which you should apply if you are running a Datasette instance on the public web - in particular if that instance mixes both public and private tables. Following issues reported by Sevban Dönmez, Alex Garcia and I ran an extensive audit of Datasette using Claude Fable 5.1, GPT-5.6, and GPT-6 Astra. We then spent almost a week collaborating on and reviewing the fixes. They helped find some very subtle bugs. We'll be incorporating security audits by frontier models into all of our development work going forward. Alex came up with a way of splitting the work which I found extremely productive: Alex Garcia and I worked together running and then responding to the audit, working in a shared private repository. For most of the issues we split the work: one of us would create the automated tests highlighting the issue, then the other would implement the fix. This ensured that two separate humans had eyes on each of the issues, in addition to our coding agents running different models. Tags: releases, security, ai, datasette, generative-ai, llms, agentic-engineering, ai-security-research ## Native is now the future of mobile at Shopify DevFeed: [Native is now the future of mobile at Shopify]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-10T21:11:15Z Content type: opinion Language: en Sources: [Simon Willison's Weblog]() Topics: [Mobile](), [React Native](), [Shopify](), [AI-assisted coding](), [Kotlin](), [Swift](), [Open Source](), [Android](), [Generative AI](), [iOS]() Tags: [ai](), [ai-2-236](), [ai-assisted-search](), [ai-assisted-search-36](), [android](), [android-14](), [coding-agents](), [coding-agents-248](), [generative-ai](), [generative-ai-1-982](), [ios](), [ios-26](), [kotlin](), [llms](), [llms-1-948](), [mobile](), [mobile-41](), [open-source](), [open-source-320](), [react](), [react-43](), [react-native](), [shopify](), [shopify-8](), [swift](), [swift-12]() ### AI overview Shopify is moving its mobile apps from React Native back to separate Swift and Kotlin codebases. The article explains that AI agents can now handle enough implementation, translation, testing, and review work to reduce the cost of maintaining separate platforms. It also notes the planned relocation or archival of Shopify's React Native libraries. ### Source excerpt Native is now the future of mobile at Shopify Shopify are moving from React Native back to separate Swift and Kotlin codebases for their native apps, for the exact reason you would expect: We decided to switch from native to React Native in 2020 for three reasons: Stop building the same features twice Allow developers to work across the stack Spend less time chasing feature parity and more time shipping value [...] Native still means building and maintaining software on two platforms, that cost has not disappeared. What changed is that agents can now do enough of the implementation, translation, testing, and review work that it's no longer the deciding factor it was in 2020. It's a well-written post, which gives full credit to React Native as a great platform for the six years they were using it. Shopify are the maintainers of three significant React Native libraries: react-native-skia, flash-list, and restyle. The first two are finding new homes; the third "has a smaller user base than our other libraries" and will be archived at the end of 2026. Via Hacker News Tags: android, mobile, open-source, ios, ai, react, generative-ai, llms, ai-assisted-search, coding-agents, swift, shopify [Next page]()