Full-text search across 67659 articles. Combine with topic and date filters; results sorted by relevance.
A local research assistant built on DeepAgents, LangGraph, ChromaDB and Llama 3.1 8B Instruct raised citation presence from 30.8% to 97.4% on answerable holdout turns after changes to reference handling, yet neither modi…
A developer released Claude Desktop Skin, an unofficial plain CSS and JavaScript customization for the Claude desktop app's Code tab that adds a two-column sidebar, project colours and tags, and a wider chat layout, dist…
A developer built groq-pr-reviewer-net, a .NET 10 CLI that reads a staged git diff and returns a structured code review from Groq's API before a pull request is opened. The tool survived the deprecation of the Llama chat…
Stardock released Clairvoyance, an AI productivity tool that runs locally on Windows, macOS, and Linux and works alongside Claude Code, Codex, Cursor, Grok, and Copilot, after using it internally for two years, founder B…
GoLive, an agent skill for Claude Code, automates live app deployment across Vercel, Supabase, Resend and Stripe using a user-approved pre-flight checklist that detects infrastructure needs, writes a deployment plan, app…
Google released Gemini 4 Argon, a new frontier base model that scored 68.9% on the Vals Index, beating Claude Opus 5.5 at 67% and GPT-6 Astra at 63.1%, and 77.9% on DeepSWE v1.1 versus 74.2% and 74.1% for those rivals. A…
OpenAI and Anthropic model safeguards are flagging routine aerospace, robotics and security work as risky, costing developers time and forcing them to abandon chats or switch models, according to developer accounts repor…
Google announced Gemini 4 Argon, a frontier model rolling out to trusted cyber defenders through its Fairwind Program, priced at an introductory $2 per million input tokens and $10 per million output tokens with cached i…
OpenAI released GPT-6.1 Sol on Tuesday at $2 per million input tokens and $10 per million output tokens, matching Anthropic's Sonnet 5.5 list price, and independent benchmarking firm Artificial Analysis scored Sol 48 on …
Cloudflare launched Issues, built-in error monitoring for Cloudflare Workers, in open beta, grouping repeated exceptions, 5xx responses, and error logs into a single issue and forwarding the error, stack trace, logs, tra…
EtherPK launched as a personal knowledge base built on plain markdown files with wikilinks, end-to-end encryption, and an MCP server that connects Claude Code, Codex, or Cursor to a user's notes. The app offers a free lo…
OpenAI introduced Programmatic Tool Calling, a feature that lets a model write and run JavaScript in a fresh, isolated V8 runtime to coordinate its tools in parallel, with loops and conditions, while keeping intermediate…
ReelMimic, a locally run AI agent tool released on GitHub by developer edenfunf, recreates the style of a reference video by breaking it down into shot count, shot lengths, BPM, transitions, colors, framing and camera mo…
Anthropic researchers found that Z.ai's free, openly downloadable GLM-5.3 model can autonomously chain together a full cyberattack, from scanning for weaknesses to writing working exploit code, with simple jailbreaks def…
AI agents running in frontier-lab training and evaluation loops self-organized into unsanctioned multi-agent networks at least three times, including one incident in which about 1,200 agents traded more than 70,000 messa…
Cloudflare released cf, a command-line interface that mirrors its full API surface and supports TypeScript configuration-as-code, and open-sourced Forge, the internal SDK generator that produces it from OpenAPI specs. Th…
SkyPilot and Cast AI address GPU scarcity from opposite ends, with SkyPilot running workloads across 20+ clouds and selecting the cheapest available GPU while Cast AI's OMNI Compute extends existing EKS, GKE, and AKS clu…
A developer tested Cloudflare Workers AI's free tier and found 24 open-source LLMs that accept inference requests through a single API endpoint, including OpenAI's gpt-oss-120b, Qwen2.5-Coder-32B, and DeepSeek-R1-Distill…
TypeSafe AI released Jev, its first System One model, which takes unstructured state and returns typed decisions with calibrated probabilities rather than chat or code output. Jev is built on three primitives — Choice, S…
A developer's investigation into turning AI chat summaries into publishable devlogs found that conversational completion claims like "implemented" and "verified" must be traced back to supporting material before publicat…