2. Models Don't Go Rogue (mail.cyberneticforests.com)
Stochastic Flocks & Cybersecurity 'Pandemonium'
💡This essay was drafted from my appearance on Mél Hogan's podcast, The Data Fix, discussing the OpenAI / Hugging Face hack. Embedded below or find it on your podcast services here.
OpenAI put out its full technical report on the Hugging Face hack this week, alongside
💡This essay was drafted from my appearance on Mél Hogan's podcast, The Data Fix, discussing the OpenAI / Hugging Face hack. Embedded below or find it on your podcast services here.
OpenAI put out its full technical report on the Hugging Face hack this week, alongside
OpenAI has released a detailed technical report on the recent hack involving Hugging Face, highlighting key insights into the incident. The discussion also touches on broader themes of cybersecurity and the implications for AI models.
5. Bin Laden's "Letter to America" (ceu.su)
7. Show HN: Declick – Turn an OpenAPI Spec, MCP Server or SQLite DB into a CLI (github.com)
Compile an API, an MCP server, or a database into a CLI your agent can run. Nine engines, one output contract. - ucsandman/declick
8. ITA Controlled English (CE) (github.com)
ITA Controlled English (CE). Contribute to ce-store/ce-store development by creating an account on GitHub.
9. Show HN: Marketplace for finding craft fairs and vendor events (www.boothscout.com)
Search verified US craft fairs, farmers markets, and festivals accepting vendors — for free.
10. Show HN: NationalDex • minimal open-source Pokédex (www.nationaldex.app)
Browse Pokemon stats, moves, abilities, items, type matchups, and more. Build teams and explore all generations.
12. Show HN: Aurict – An open-source Terminal AI (github.com)
Aurict is an open-source terminal AI coding agent built for real developer workflows: sandboxed tools, subagents, multi-provider LLMs, patch safety, and fast CLI UX. - aurict/aurict
13. Show HN: Word42, a wordprocessor inspired by MS Word and Abiword (word42.org)
Word42 is a classic word processor, written from scratch in C on GTK 4, Pango and Cairo: the shape and restraint of the word processors of 1993 on a modern text stack. Free software, GPL-3.0-or-later.
16. Show HN: Coder Eval – A Framework for Evals (github.com)
Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates. - UiPath/coder_eval
17. Show HN: Sentrint, Ship AI features without losing sleep (sentrint.com)
An automated security check for apps built with Bolt, Cursor or v0. Plain-English findings and a copy-paste fix. No jargon, no terminal.
18. Show HN: Million Bricks – a 3D tower of one million bricks you can buy for $10 (www.millionbrickshomepage.com)
A tower of one million buyable bricks. Claim yours for $10.
21. Show HN: Covenant – A governance framework for multi-agent AI systems (github.com)
A governance framework for multi-agent AI systems. Structure, lifecycle, and quality controls for AI agent orchestration. - asalsali/covenant-framework-community
22. Show HN: Local Mitsubishi AC Control with ESPHome and an AtomS3 Lite (didac.dev)
How I connected two Mitsubishi MSZ-HR air conditioners directly to Home Assistant with AtomS3 Lite boards and ESPHome.
23. Show HN: Audioreality.ai – email to private daily podcast summary show (www.audioreality.ai)
Private audio shows built from the newsletters, updates, and reports you choose.
24. Show HN: OpenStint – lap timing using RTL-SDR and near-field transponders (openstint.org)
OpenStint is an open-source project reading AMB/RC3/RC4-style near-field transponders using inexpensive SDR (HackRF or RTL-SDR) radios.
25. Show HN: Webmcp-react v1.0.0 (React hooks for agents to use WebMCP) (github.com)
React hooks for exposing your app's functionality as WebMCP tools - transport-agnostic, SSR-safe, Strict Mode safe, W3C spec-aligned - agentcathq/webmcp-react
26. Show HN: What if AI did the prompting – and humans did the thinking? (www.antiagent.site)
Where AI writes the prompts and humans think and answer. Dual-loop reasoning workbench where autonomous agents pause at critical checkpoints for human expert intuition.