Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. You Are No Longer Invited to Dinner (derekthompson.org)
    171comments
  2. Delhi Cut Electricity Loss from 50 to 5 Percent (ieee.org)
    7comments
  3. AI companies leak data to advertisers [pdf] (jorgegarciaherrero.com)
    55comments
  4. Jeeves. Reasoning improves Jev-like decision models (github.com/posthog)
    30comments
  5. 500k facial scans at UK stations yield no arrests, 1 false positive (theguardian.com)
    74comments
  6. Using any C++ library in Godot (conan.io)
    23comments
  7. US sanctions force The Netherlands off Microsoft and toward alternative NixOS (tomshardware.com)
    54comments
  8. Without the Hot Air (withouthotair.com)
    —discuss
  9. Phyllotaxis: An audio-reactive LED display (jagi.studio)
    24comments
  10. Booted up in 1993, this server still runs – but not for much longer (2017) (computerworld.com)
    49comments
  11. The systems that no one will test (christianperone.com)
    36comments
  12. California farmers are struggling to sell grapes as demand for wine drops (kqed.org)
    687comments
  13. Show HN: Raven – The harness of harnesses, built for RSI (github.com/evermind-ai)
    6comments
  14. Startup Nights 2026 is comming up on 5-6 Nov. in Switzerland (startup-nights.ch)
    13comments
  15. Software occlusion culling in Block Game (enikofox.com)
    4comments
  16. Four CHI '26 papers I wish I wrote (countingfromzero.blog)
    3comments
  17. Pirating the Pirates (mubi.com)
    318comments
  18. Tank Body Problem (jimsitu.com)
    31comments
  19. MicroLLM Lab – Try 7 tiny LLM's in the browser (stateofutopia.com)
    92comments
  20. The Beatles have permeated research papers across academic disciplines (phys.org)
    1comments
  21. Evan Doorbell's Phone Tapes – Brought to You by Telephone World (evan-doorbell.com)
    3comments
  22. ESP32S3 cluster running 1.58-bit (BitNet) Language model (github.com/low-zi-hong)
    26comments
  23. 12,000-year-old Göbeklitepe burials explain scattered bones (archaeologymag.com)
    42comments
  24. Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms (github.com/firelex)
    201comments
  25. New Cyber-OSINT model released (twitter.com/0x0sojalsec)
    6comments
  26. Optimizing x264 settings and per-title ladders (streaminglearningcenter.com)
    —discuss
  27. Updated Google Maps shows destruction of the city of Rafah (twitter.com/aliabunimah)
    591comments
  28. Nvidia wants to put a watchdog chip next to every AI agent (cnbc.com)
    255comments
  29. Hijacking the PS5's RTMP stream (yashgarg.dev)
    87comments
  30. Sonnet 5.5 (anthropic.com)
    564comments

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

14 pointsby 3h agogithub.com
6 comments
36m 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

28m agoHN ↗

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

26m 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.

24m 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?

22m agoHN ↗

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