Full-text search across 66203 articles. Combine with topic and date filters; results sorted by relevance.
A developer has published a reproducible bake-off method for comparing Meta's Muse Wonder against Claude Opus 5.5 on a user's own repository, after noting that Meta's model card claims Wonder leads on long-horizon coding…
Kerneta's .Cai plain-text code graph answers a module-import query in 22 tokens versus Graphify's 4,696 — 218x fewer — and 64,075 tokens for reading httpx's own source, or 2,976x fewer, according to the Show HN post. On …
Pydantic released a hosted Logfire MCP server that exposes OpenTelemetry traces, logs, and metrics to any Model Context Protocol client, running at https://logfire-us.pydantic.dev/mcp for US projects and https://logfire-…
Anthropic released Claude Opus 5.5, the first model in its new Claude 5.5 family, which the company says performs at the level of Claude Fable 5.1 on most work while costing 40% less to run than Opus 5. The model is pric…
A developer surveys seven AI-native alternatives to Postman designed for terminal-based API development, arguing that AI coding agents need command-line-accessible API tooling rather than GUI-centric clients. The piece h…
A developer has published a markdown file that aggressively simplifies AI-generated, defensive, or overly abstract Go code, aiming to make it look like it was written by an experienced Go engineer. The guide emphasizes v…
OpenAI's Codex coding agent helped an experienced programmer turn a ten-line shell script into a more robust utility for launching Internet radio stations on Linux, fixing a potential bug involving stale process IDs. The…
Elon Musk's claim that LLMs will make programming languages and compilers obsolete is mistaken, argues a new essay, which contends that programming languages will become more essential in the era of LLMs. The essay, by a…
JetBrains has released go-modern-guidelines, a plugin that provides contemporary Go writing specifications for AI agents to prevent them from writing outdated code due to training data cutoffs and frequency bias. The too…
Researchers at Microsoft Research, led by Nik Swamy, used AI coding agents to port and evolve a verified mark-and-sweep garbage collector for OCaml into a generational garbage collector, integrating it with the OCaml run…
GitHub reported that merged pull requests grew from 25 million per month in January 2023 to 90 million per month today, while commits are on pace to exceed 14 billion in 2026, driven by AI coding agents and automated sys…
Redwood Research introduced the concept of feature strength to explain why classifiers trained on data with spurious correlations often generalize to the stronger feature, finding that when fine-tuning Qwen3-1.7B to dist…
GitHub began using interaction data from Copilot Free, Pro and Pro+ to train its models unless users opt out, effective April 24, 2026, while Business and Enterprise plans are unaffected. The change is part of a broader …
OpenAI's Codex and ChatGPT Work have reached 10 million combined users less than two weeks after the July 9 launch of ChatGPT Work, with monthly active users up more than 10x from January 2026, according to Akshay Nathan…
OpenAI is transforming ChatGPT from a conversational assistant into an autonomous agent with a new 'Work Mode' that can build websites, conduct multi-source research, write and test code, and schedule recurring tasks, sh…
AI has made software production cheap, but quality—specifically confidence in correctness and shared understanding—has become the new bottleneck. Code review times have surged 441.5% and defect rates have risen from 9% t…
The future of software development is moving toward multiplayer systems that turn shared intent into continuous, governed execution, according to a builder who conceived the idea of Wallie, an issue tracker with coding a…
Anthropic's Claude Fable 5 model wrote a booting Windows NT-compatible kernel in Rust in 38 minutes, producing a 5,100-line trusted computing base that passed all self-tests in QEMU. The feat demonstrates AI's ability to…
Anthropic has alienated developers through API instability, vendor lock-in with Claude Code, and controversial 'extra usage' billing that charges subscription users per token before they hit rate limits, even when using …
GitHub Copilot has added Kimi K2.7 Code, an open-weight model from Chinese AI startup Moonshot AI, as a selectable option in its model picker for the first time. Hosted on Microsoft Azure and billed by token usage, the m…