HN Explorer

GodelNumbering

↗ HN profile [ 88.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. From 'I want my own harness' to corporate sponsorship (dirac.run)
    1 points 0
  2. Software Development job postings in the US hit a 3 year high (fred.stlouisfed.org)
    1 points 0
  3. 'AI has inner experience' is a dangerous assumption (dirac.run)
    1 points 1
  4. Show HN: I finetuned 1.5B Qwen to near GPT-4o level bash generation perf (dirac.run)

    Purely a hobby side project to see how far I can push a really small model, using (mostly) automated training pipelines Original mention: https://news.ycombinator.com/item?id=49869735 There were a bunch of requests to…

    1 points 1
  5. There is no way to get ChatGPT to stop injecting your location in context (chatgpt.com)
    1 points 1
  6. Ask HN: What is one plausible path to 'AI extinction'?

    This is being thrown around a lot, including the dreaded "10% chance by the end of this decade". Every conversation I have seen about this, mostly on twitter, not once have I seen anyone connecting the dots on…

    1 points 5
  7. GoBench: Evaluating LLMs on 9×9 Go using KataGo opponents as Elo anchors (rolandgao.com)
    1 points 1
  8. If your agent commits a crime, who is responsible? (signalbloom.ai)
    5 points 71
  9. Ask HN: Anyone interested in building a harness-only benchmark?

    There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multiple axis) on a set of…

    5 points 5
  10. Token Arbitrage: Use Sol for coding, Luna for compaction, save 84% (dirac.run)
    3 points 2
  11. Claude gen-5 models show significant regression in BullshitBench (github.com)
    3 points 0
  12. GPT-5.6-terra used 48.5% more context than Mimo-2.5-pro (dirac.run)
    3 points 1
  13. Cache hit rate dropping by 20% doubles your agent's bills (dirac.run)
    2 points 0
  14. Don't Conflate 'Minimal' with Minimal Effort (dirac.run)
    2 points 0
  15. OSS models decisively overtook Proprietary models in openrouter market share (dirac.run)
    4 points 1
  16. Outsourcing plus local AI will soon become more economical vs. frontier labs (signalbloom.ai)
    323 points 91
  17. Cache hit rates of Inference are more meaningful than the headline costs (dirac.run)
    2 points 0
  18. Ask HN: Who needs contributors? (May 2026)

    Looking for contributors to your project? Feel free to post any project that may interest HN readers, with a strong preference towards open source. Please follow this general format: Project Name Project Description…

    2 points 0
  19. Peak lazy engineering: Let the code answer its own questions (dirac.run)
    2 points 0
  20. The Isolator (Helmet) (en.wikipedia.org)
    3 points 0
  21. Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview (github.com)

    Scored 65.2% vs google's official 47.8%, and the existing top closed source model Junie CLI's 64.3%. Since there are a lot of reports of deliberate cheating on TerminalBench 2.0 lately…

    393 points 56
  22. Hash anchors and Myers diff and single-token anchors: 60% cheaper AI code edits (dirac.run)
    5 points 1
  23. Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct (github.com)

    Fully open source, a hard fork of cline. Full evals on the github page that compares 7 agents (Cline, Kilo, Ohmypi, Opencode, Pimono, Roo, Dirac) on 8 medium complexity tasks. Each task, each diff and correctness + cost…

    2 points 1
  24. Nvidia's Nemotron 3 Super is a bigger deal than you think (signalbloom.ai)
    2 points 0
  25. Why Task Proficiency Doesn't Equal AI Autonomy (signalbloom.ai)
    2 points 0