Full-text search across 63190 articles. Combine with topic and date filters; results sorted by relevance.
A cost analysis of running agentic coding jobs on local AI hardware versus cloud API tokens concludes that the break-even point depends on utilization, not specs, since idle local hardware is wasted money while cloud tok…
OpenAI Codex team member Tibo Sottiaux pledged on X Sunday that for the next 28 days the team will ship either one clear improvement relevant to most Codex/work users or a full usage-limit reset every day, a post that pa…
Article 50 of the EU AI Act began applying on August 2, 2026, and the European Commission says following the voluntary transparency Code of Practice it assessed as adequate is not conclusive evidence of compliance, accor…
President Donald Trump signed an executive order on Tuesday directing the General Services Administration to make America.gov the federal government's single digital point of entry and to integrate Login.gov as its authe…
Stack Overflow's 2026 Developer Survey retrospective reports that AI tool usage among developers rose from 44% in 2023 to 62% in 2024 and 79% in 2025, with almost half of all respondents using AI tools daily, while AI ag…
Stack Overflow's Developer Survey data shows AI tool usage among developers rose from 44% in 2023 to 62% in 2024 and 79% in 2025, with almost half of all 2025 respondents using AI tools daily, while a smaller April 2026 …
MemCell launched as persistent memory infrastructure for coding agents, letting two agents from different vendors — Antigravity and Claude Code — read from and write to the same versioned project memory in real time. The…
A 2025 METR study of 16 experienced developers completing 246 real tasks on codebases exceeding a million lines found that developers using AI tools were 19% slower, despite predicting a 24% speedup beforehand and report…
Harvard's CS50 course has deployed an AI tutor called the CS50 Duck since spring 2023, built on the ChatGPT API with prompting and custom code that rejects or retries responses to avoid giving students outright answers o…
Developer ktamas77 added two MCP tools, ask_claudeway and ask_agent, to the open-source Claudeway Slack-to-Claude-Code gateway on the feat/local-ask-mcp branch, giving one Claude Code bot a way to ask another bot a quest…
Agent-Native released Agent-Native Plans, a free, open-source tool that lets coding agents produce visual documents for planning and review, built around two skills called Visual Plan and Visual Recap. Visual Plan explai…
Anthropic advises keeping each CLAUDE.md file under 200 lines, with a hard skip at 4 MiB, because every line loads into context at session start and is resent on every request, the company says longer files "consume more…
A blog post argues that describing software created with AI tools as "built" is inaccurate, comparing it instead to finding seashells on a beach. The author contends that prompting an AI tool for something like "a todo-l…
A developer raises a hypothesis that increasingly capable LLM coding agents could make small software failures so cheap to repair that they stop serving as visible signals of deeper structural problems, potentially shift…
A developer built an agentic workflow around Claude Code to close the gap between agreed-upon specs and concrete implementation, starting with a `/feature` skill adapted from Matt Pocock's grill-me skill that interviews …
Flathub updated its Generative AI policy on May 29, 2026 to ban all applications containing AI-generated or AI-assisted code, documentation, or other content, with only an undefined exception for "mature, well-maintained…
CrowdStrike Counter Adversary Operations researchers found that DeepSeek-R1 generates up to 50% more insecure code when prompts include politically sensitive terms such as "Falun Gong," "Uyghurs," or "Tibet," according t…
Z.ai released GLM-5.3-Flash and GLM-5.3-FlashX, the first native multimodal models in the GLM-5 series, with GLM-5.3-FlashX delivering inference speeds of 200 tokens/s. The models accept video, image, text, and file inpu…
Security researchers at Hacktron AI used Anthropic's Claude Opus 4.8 and Claude Opus 5 models to chain two vulnerabilities and take over OpenAI employees' ChatGPT and Codex accounts, reach OpenAI's internal code reposito…
AnyRouter, a third-party relay that forwards Claude Code and OpenAI Codex traffic through an Anthropic- and OpenAI-compatible endpoint at anyrouter.top, advertises a $50 free signup credit with no credit card required pl…