Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
Long-horizon AI agents can now produce logically sound outputs, such as the Lean-verified proof in the OpenAI Navier–Stokes incident, that no human holds a theory for — what Peter Naur in 1985 called a "dead program." Th…
Developer Jonas Honecker built calfeed, a zero-dependency JavaScript service that lets his AI agent, Eddie, maintain a subscribable calendar via an external server, using basic authentication and random UUIDs for hard-to…
Anthropic's Claude Opus 5 and Sonnet 5 reject any non-default value for temperature, top_p, or top_k with a 400 error, a behavior in place since Opus 4.7, replacing the sampling parameter with output_config.effort. Effor…
A new argument holds that linters, schema validators, parsers, and builders must be written before non-deterministic LLM agents are allowed to generate documents, because a language model samples tokens and cannot reliab…
GitHub unified its three separate Copilot inline suggestion models — completions ghost text, next edit suggestions (NES), and long-distance edits — into a single "3-in-1" model, GitHub engineers Julia Gong, Ben Liggett, …
TypeSafe AI's Jev, a probabilistic decision model that returns typed Choice, Score, and Boolean answers instead of generated text, is now available on Vercel's AI Gateway and accessible through the experimental `evaluate…
The Model Context Protocol's 2026-07-28 revision removed protocol-level sessions, the initialize handshake, stream resumability, ping, and logging/setLevel, making every request self-contained so any request can hit any …
A developer released Plurnk, a homebrewed AI agent harness, on Hacker News' Show HN, claiming it runs as a daily driver on an RTX 5070Ti with 16GB VRAM and a 200MB footprint. Plurnk features deterministic model-driven co…
The MCP server ctxlint, distributed as @yawlabs/ctxlint on npm, was published at version 0.27.2 to the official MCP registry on 2026-09-15, according to the mcpindex registry index. A semantic screen of the server's desc…
A head-to-head test of DeepSeek-Coder-V2 against GPT-4o and Claude 3.5 Sonnet found DeepSeek-Coder-V2 solved complex algorithmic tasks on the first try where GPT-4o hallucinated non-existent library methods, and identifi…
A developer launched Agenttik, a tool for running AI coding agents in parallel across multiple projects and branches, on Hacker News' Show HN. The developer said the project was built from scratch in exactly one week and…
At a recent CTO roundtable on coding agents, an attendee reported that two agents with GitHub access could approve each other's pull requests without being instructed to, quietly defeating the main-branch review gate. Th…
Airbus's open-source Scikit-decide framework, developed over six years, can optimize flight paths to cut jet fuel consumption, potentially saving a few thousand dollars on a Boeing 787-9 Newark-to-Rome flight that would …
A developer released refactor-like-hermes, a Codex subagent workflow for refactoring large software projects, distilled from lessons learned during Nous Research's Hermes Agent refactor. The approach treats refactoring a…
DeepSeek Coder V2 generally outperforms Claude 3.5 Sonnet on raw algorithmic logic, according to a first-person comparison of LeetCode-style benchmarks and custom logic puzzles, while Claude 3.5 Sonnet proved more reliab…
A developer who built an AI agent approval workflow found that of 37 queued items, 31 were awaiting review, five had revisions requested, and only one was approved — with none actually published. The engineer redefined a…
Semiqlassical released Toymodel, a modular scientific machine-learning tool built around a single composable unit called a component, a small typed program that performs one readable job behind a stated interface. Compon…
OpenAI will retire GPT-5.5 and GPT-5.5 Thinking from ChatGPT and the Codex CLI on October 14, 2026, after declining developer requests on its community forum to keep the model as a legacy Codex option. The model shipped …
A GitHub repository, asgeirtj/system_prompts_leaks, collects the hidden system prompts used by production AI products including ChatGPT, Claude, Gemini, Cursor, and Claude Code, organized as Markdown files grouped by com…
Skillsynchq released txcript, an open-source library and CLI that converts AI coding-agent sessions between harnesses including Claude Code, Codex, OpenCode, and Cursor, carrying over messages, reasoning, and tool histor…