Topic
Everything filed under Developer Tools, newest first.
RSS · JSON · All topics
MAI Code 2 and Code 2 Flash: Everyday coding at scalable prices
Microsoft AI introduces MAI Code 2 and MAI Code 2 Flash, two coding models aimed at everyday enterprise coding tasks, pitched as delivering leading performance and speed at less than half the price of competing models.
3 min · 714 words
Linear shares data on how its code review changed as agents wrote more code: every PR is now agent-reviewed first and authors can self-approve, so 53% of merged PRs in October 2026 had no second human reviewer, with mandatory human review kept for sensitive areas.
10 min · 2,322 words
Introducing FrontierHarness Eval v1.1
Runta and Baseten ran 22 coding-agent harnesses with 5 models on the same 62 tasks, 4 times each (27,280 runs, 83B tokens), to test whether switching models should mean switching harnesses, and found 64% of inference spend went to runs that failed.
11 min · 2,500 words
kqr of Entropic Thoughts describes using the community fork of Maiao to work with stacked diffs in git, how the workflow compares with keeping a branch per atomic change, and the pitfalls of dependent and independent changes.
11 min · 2,532 words
Jiff 1.0: A datetime library for Rust
Andrew Gallant (BurntSushi) announces the Jiff 1.0 release, a Rust datetime library that puts time zone handling front and center, with a tour of its API and comparisons to Temporal.
42 min · 9,637 words
clice v1.0 Released: Welcome to Modern C++
ykiko announces the first stable release of clice, a new C++ language server, after 1,000 commits and four months of alpha testing, explaining what it does, why it was built instead of improving clangd, how the project got here, and where agents fit in.
19 min · 4,442 words
A collection of programs whose messages speak in a personified first person, from Git's 'Please tell me who you are' and GNU tar's 'Cowardly refusing' to Elm's chatty compiler errors, sudo insults and Nmap's birthday message, with thoughts on LLM agents.
3 min · 620 words
The xenodium.com author recaps their first upstream contributions shipped in Emacs 31, including hiding Dired's absolute location, a macOS speech recognition permission fix, a 'Send to…' sharing menu and restored macOS dictation, and encourages others to contribute and fund maintainers.
3 min · 697 words
Farid Zakaria explores Nix dynamic derivations, an experimental feature that lets a derivation produce other derivations, using a playful nested beer.drv example to show how build graphs can be created dynamically to rival Bazel and buck2.
6 min · 1,468 words
ESCAPES: a benchmark of 327 bugs that reached real users
breken's open ESCAPES benchmark rewinds 33 open-source products to 1 July 2026 code and scores 235 user-reported bugs: breken's run-based system caught 76 (32%) with 20 false alarms versus 37 for Claude Fable 5.1 in Claude Code; vendor-run results with public data and judge prompts.
16 min · 3,592 words
Designing nextest's install scripts
Rain explains why cargo-nextest took four and a half years to ship curl|sh and PowerShell install scripts, how the scripts work, and how coding agents were used under a high quality bar to build them.
10 min · 2,252 words
Lying to Zed to get its remote server running on FreeBSD
Hayzam Sherif explains how he got the Zed editor's remote development server running on FreeBSD by making Zed believe it was talking to a Linux host, using FreeBSD's Linux compatibility layer, and asks the Zed team to support FreeBSD remotes natively.
5 min · 1,157 words
Running coding agents without handing them my credentials
Antonio describes lend, an open-source tool that lets remote coding agents use credentials, SSH keys and tools on his laptop only with approval, covering leases, audit logs, answering agent prompts remotely, what it does not protect against, and prior art.
10 min · 2,391 words
Terminal borders that don't cost a cell
Ratatui maintainer Josh McKinney proposes a terminal protocol for thin lines drawn on cell edges, so borders, rounded corners and gridlines don't consume rows or columns, with a working Ghostty prototype and Ratatui demos.
12 min · 2,681 words
Makepad's Relax is an experimental live compiler and JIT runtime for Rust that runs a Cargo package straight from source without rustc, LLVM or a linker, compiling functions on first call and live-patching edits for faster iteration.
14 min · 3,117 words
Gemini 4 Hydrogen and Orchestrator
Google Antigravity rolls out Gemini 4 Hydrogen plus a new Orchestrator model option that dynamically hands work between Gemini 4 Carbon (planning) and Hydrogen (execution) within one trajectory, reaching near-Carbon success on Terminal-Bench 4.1 with 24% less quota and 19% faster completion.
3 min · 633 words
The Brave Search API now accepts agentic payments via the x402 protocol
Brave announces that its Search API now supports pay-as-you-go agentic payments via the open x402 protocol: agents pay per request in USDC on Base (about $0.005 per query) with no account or API key, using a 402 Payment Required challenge and signed payment retry.
2 min · 419 words
A2UI 1.0: Build delightful, fast, reliable, agentic experiences
Google releases A2UI 1.0, the first stable version of its open protocol for generative UI, letting AI agents answer with interactive screens such as forms and charts, with renderer SDKs for web, Android and iOS and agent SDKs for Python, TypeScript and Dart.
6 min · 1,493 words
Gemini Decisions API: Fast, calibrated multimodal decisions
Google introduces the Gemini Decisions API, powered by the new Gemini Decision 1 model, for fast, calibrated yes/no, multiple-choice and rubric-scoring decisions—up to 1,000 questions in a single pass across text, images, audio, video and PDFs.
4 min · 976 words
.NET 11 is released as a Standard Term Support version with C# 15, faster SDK tooling, runtime and library improvements, and new capabilities for web, mobile, desktop and AI apps across ASP.NET Core, .NET MAUI and Windows development.
14 min · 3,300 words