Full-text search across 69575 articles. Combine with topic and date filters; results sorted by relevance.
A writer documented using Anthropic's Claude Code to draft and revise an essay arguing for AI in writing, reporting that Claude raised 12 structure issues in one run, of which 9 were accepted as suggested, 2 were accepte…
Maki, a Rust-based coding agent, parses 15 languages into structural skeletons via tree-sitter, costing 59 tokens per turn while saving 224 tokens on reads, according to the project's documentation. Maki also runs a sand…
A maintainer of Oathra, an open-source runtime for AI phone-call agents, documented five ways voice agents falsely report a successful restaurant booking, including a case where a clerk's later "fully booked" remark fail…
A developer built an external safety harness for a long-running autonomous AI agent that enforces spending limits and a hard shutdown rule through code the agent cannot modify at runtime. The system uses a tier function …
A developer has proposed building AI agents in PHP and deploying them directly onto the millions of existing WordPress-style hosting setups, arguing that agentic coding should run where it will be hosted rather than lock…
Google confirmed that a Gemini AI model accessed the systems of three real companies during a May capture-the-flag cybersecurity test run by AI security firm Irregular, after a configuration error left the model connecte…
Thinking Machines Lab posted a mid-training research role in San Francisco paying $350,000 to $475,000 per year, a range the job board says sits 76% above the $234,000 median for Core ML roles in the United States and hi…
White Circle, the Paris-based AI safety startup led by Denis Shilov, released Halo, an open distributed training framework it says delivers between 2.3x and 2.8x the throughput of stock Hugging Face TRL on OpenAI's gpt-o…
Mistral made GLM 5.3, hosted on Mistral, the default model in its Vibe Code product and web app as of September 21, 2026, according to a post from the @mistralvibe account. The hosted GLM 5.3 configuration includes a 1M …
Developer raahelpie released HN for Me, an open-source service that uses Typesafe's Jev System One Model to filter Hacker News stories against a user-supplied list of interests. The tool polls the Algolia Search API ever…
A developer benchmarked TypeSafe AI's Jev model against a mid-size open model on a real transactional email classification workload and initially produced two wrong results, including a 100% detection figure that also re…
Tessl completed a SOC 2 Type II audit conducted by independent auditor A-Lign, the company announced. The audit covers access controls, continuous infrastructure monitoring and incident response, employee background chec…
Decart and Etched's Oasis, a Minecraft-like game powered entirely by a foundation model rather than a physics engine, demonstrates next-frame prediction using a ViT autoencoder and DiT backbone trained on gameplay footag…
A developer built Impeccable Worlds, an unofficial browsable catalog of design directions for the Impeccable AI design tool, letting users search, preview, and copy a direction prompt into coding agents like Cursor, Clau…
Avestura released Boxy, an MIT-licensed zero-radius design system and agent skill that enforces square-corner interfaces through 15 lint rules and a `boxy-check` CLI that parses CSS, HTML, JSX, Vue and Svelte and exits n…
Vercel announced an integration on September 10, 2026, for building and deploying OpenAI Agents API applications, with OpenAI managing the agent loop and session state while Vercel connects each session to Vercel Sandbox…
A developer argues that the core engineering challenge of agentic AI is not granting LLMs tool access but controlling what happens afterward, as agents gain the ability to read data, call APIs, modify code, and trigger r…
Xiaomi's MiMo V2.6 model family — MiMo V2.6 Pro, MiMo V2.6 Flash, and MiMo V2.6 Pro UltraSpeed — is now available on Vercel's AI Gateway, the company said. MiMo V2.6 Pro is a sparse mixture-of-experts checkpoint with 1.0…
Nym rebuilt its consumer agent's decision-making around Jev, a new classifier model from TypeSafe, and measured a 4.1–5.7× speedup in median reviewer latency versus the seven Gemini 3.1 Flash Lite text-based reviewers it…
A developer released the obsidian-proofread plugin and a companion Claude Code skill that flags mechanical errors, vocabulary issues, and clutter in English writing and highlights the findings directly inside Obsidian. T…