Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. You Are No Longer Invited to Dinner (derekthompson.org)
    147comments
  2. AI companies leak data to advertisers [pdf] (jorgegarciaherrero.com)
    52comments
  3. Delhi Cut Electricity Loss from 50 to 5 Percent (ieee.org)
    6comments
  4. Jeeves. Reasoning improves Jev-like decision models (github.com/posthog)
    27comments
  5. 500k facial scans at UK stations yield no arrests, 1 false positive (theguardian.com)
    67comments
  6. Using any C++ library in Godot (conan.io)
    23comments
  7. US sanctions force The Netherlands off Microsoft and toward alternative NixOS (tomshardware.com)
    45comments
  8. Booted up in 1993, this server still runs – but not for much longer (2017) (computerworld.com)
    46comments
  9. Phyllotaxis: An audio-reactive LED display (jagi.studio)
    24comments
  10. The systems that no one will test (christianperone.com)
    36comments
  11. Startup Nights 2026 is comming up on 5-6 Nov. in Switzerland (startup-nights.ch)
    12comments
  12. California farmers are struggling to sell grapes as demand for wine drops (kqed.org)
    683comments
  13. Show HN: Raven – The harness of harnesses, built for RSI (github.com/evermind-ai)
    6comments
  14. Software occlusion culling in Block Game (enikofox.com)
    4comments
  15. Pirating the Pirates (mubi.com)
    317comments
  16. Four CHI '26 papers I wish I wrote (countingfromzero.blog)
    3comments
  17. Tank Body Problem (jimsitu.com)
    30comments
  18. The Beatles have permeated research papers across academic disciplines (phys.org)
    —discuss
  19. MicroLLM Lab – Try 7 tiny LLM's in the browser (stateofutopia.com)
    92comments
  20. Evan Doorbell's Phone Tapes – Brought to You by Telephone World (evan-doorbell.com)
    3comments
  21. ESP32S3 cluster running 1.58-bit (BitNet) Language model (github.com/low-zi-hong)
    26comments
  22. 12,000-year-old Göbeklitepe burials explain scattered bones (archaeologymag.com)
    42comments
  23. Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms (github.com/firelex)
    200comments
  24. Optimizing x264 settings and per-title ladders (streaminglearningcenter.com)
    —discuss
  25. New Cyber-OSINT model released (twitter.com/0x0sojalsec)
    6comments
  26. Updated Google Maps shows destruction of the city of Rafah (twitter.com/aliabunimah)
    586comments
  27. Nvidia wants to put a watchdog chip next to every AI agent (cnbc.com)
    254comments
  28. Hijacking the PS5's RTMP stream (yashgarg.dev)
    87comments
  29. Sonnet 5.5 (anthropic.com)
    563comments
  30. Kids turned low-traffic NPR Spotify comments into a secret group chat (thisamericanlife.org)
    236comments

Show HN: Raven – The harness of harnesses, built for RSI

14 pointsby 3h agogithub.com
6 comments
27m agoHN ↗

RSI here is for "recursive self-improvement", instead of a harness being built to help users with repetitive strain injury like I first thought when reading the post title

19m agoHN ↗

I wish they had also compared it to omp and dsh, I’m curious how it stacks up

17m agoHN ↗

Interesting. Only thing, from someone who has built something similar, is that it moght tend to duplicate certain capabilities that those harnesses handle on their own. Some overlap is bound to happen.

16m agoHN ↗

This looks similar to https://paseo.sh/, if I understand correctly. I’ve recently tried it and liked it a lot. Would be nice to see a comparison. When’s the harness of harnesses of harnesses coming?

13m agoHN ↗

Agents editing their prompts and writing memory to markdown files is not and will never be RSI.