Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. The Video Game Industries Dark Night (isfine.org)
    —discuss
  2. AMD Acquires Fei-Fei Li's World Labs for $8.2B (youtube.com)
    —discuss
  3. Show HN: How distributed Claude Code is built on a tunnelling service (nfltr.xyz)
    —discuss
  4. 2026 in LLMs (so far) (simonwillison.net)
    —discuss
  5. Gargi Reflex: Autonomous Model Caching for System One Decisions (gargi.io)
    —discuss
  6. When oil prices spike, where does the money go? (theconversation.com)
    —discuss
  7. Clipboard Normalizer (jefftk.com)
    —discuss
  8. Global Cloud Status (globalcloudstatus.com)
    1comments
  9. Compiler Construction Fall 2018 (UCSD) (ucsd-cse131-s18.github.io)
    —discuss
  10. DHH has gone off the rails [video] (youtube.com)
    —discuss
  11. Histomap: Visualizing the 4k Year History of Global Power (visualcapitalist.com)
    —discuss
  12. User Model Extraction via Belief Self-Distillation (arxiv.org)
    —discuss
  13. Yet another Python book in Spanish (elalmacendigital.com.mx)
    —discuss
  14. Can AI self-improvement overcome diminishing returns? (rameznaam.com)
    —discuss
  15. The Spider and the Fly (poem) (wikipedia.org)
    —discuss
  16. Show HN: Skill file for humans on Basic Arithmetic (gist.github.com)
    1comments
  17. Don't Try on Thoughts (ben.page)
    —discuss
  18. Energy Timelines Photovoltaic (eia.gov)
    —discuss
  19. OpenAI scraps rollout of new model over safety concerns (bbc.com)
    —discuss
  20. Human in the Loop Control for OpenClaw (windley.com)
    —discuss
  21. Show HN: I turned Google Drive folders into professional photo galleries (scansgallery.com)
    —discuss
  22. AI risk is not sentience by computers, it is negligence by humans (seattletimes.com)
    1comments
  23. Anthropic warns AI may pose 'existential risks to humanity' in IPO filing (reuters.com)
    —discuss
  24. Jev vs. Fruit Fly Brain solving a maze in Roblox [video] (youtube.com)
    1comments
  25. Bananas That Don't Go Brown to Hit Supermarkets Thanks to DNA Editing (theguardian.com)
    2comments
  26. Manus 2.0 (manus.im)
    2comments
  27. AI Realist vs. 20 AI Optimists (Ft. Andrew Yang) [video] (youtube.com)
    —discuss
  28. The SaaSpocalypse was more like a RenaiSaaS (stripeeconomics.com)
    —discuss
  29. An article on frontier agentic work (medium.com/jonahturnquist)
    2comments
  30. Free AI slop checker: find the signs of AI writing (seodraft.app)
    —discuss

Show HN: Talktome - let your AI Agent call you

3 pointsby 2h agogithub.com
3 comments
I built TalkToMe, an open-source macOS app that lets an agent call you from its current session. You answer, talk, and hear its replies. The agent keeps its tools, files, and history.

It works with Codex (Tested extensively, quite smooth), Claude Code (not tested heavily), Hermes, and other agents that can run shell commands. You can use ElevenLabs or local models to power the conversation. It's really surreal to see your agent call you for something!

2h agoHN ↗

Actively working on getting remote agents supported with this, a thin client on your laptop and the server running with your agent

1h agoHN ↗

Cool! have been looking for something like this

17m agoHN ↗

ElevenLabs definitely sounds more natural for voice. Thanks for sharing!