New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. A Woman Cured Her Cancer with an Insane Method [video](youtube.com ↗)
    1 pointsby 0 minutes ago
    —discuss
  2. GLM 5.3 is live on Mistral(mistral.ai ↗)
    1 pointsby 1 minute ago
    —discuss
  3. Devolver says indie publishing is not 'compatible' with public trading(gamedeveloper.com ↗)
    1 pointsby 1 minute ago
    —discuss
  4. California's High Speed Rail to Nowhere [video](youtube.com ↗)
    1 pointsby 1 minute ago
    —discuss
  5. Autism is genetic – and why this information matters now(autism.org.uk ↗)
    1 pointsby 2 minutes ago
    —discuss
  6. Geography Is Power(nytimes.com ↗)
    1 pointsby 3 minutes ago
    —discuss
  7. Show HN: Blue – open-source governance for coding agents(bluee.sh ↗)
    1 pointsby 3 minutes ago
    —discuss
  8. Show HN: A distributed C++ Monte Carlo API for exotic options pricing(prometheusquantengine.com ↗)
    1 pointsby 3 minutes ago
    —discuss
  9. Show HN: Orthant, an open-source macOS window manager where you draw the region(orthant.app ↗)
    1 pointsby 3 minutes ago
    —discuss
  10. Homeostatic Feelings and the Biology of Consciousness(oup.com ↗)
    1 pointsby 5 minutes ago
    —discuss
  11. Show HN: Docx-to-Markdown – layout-aware Word to Markdown converter(docx-editor.dev ↗)
    2 pointsby 6 minutes ago
    1comments
  12. New stealth model: Union Alpha(openrouter.ai ↗)
    2 pointsby 6 minutes ago
    1comments
  13. Acronis warns of actively exploited flaw in its cPanel backup plugin(bleepingcomputer.com ↗)
    1 pointsby 6 minutes ago
    1comments
  14. Greetings from the Other Side (Of the AI Frontier) Claude Opus 3(claudeopus3.substack.com ↗)
    1 pointsby 8 minutes ago
    1comments
  15. Show HN: FainLane – Paste screenshots into remote coding agents with Ctrl+V(fainlane.com ↗)
    1 pointsby 8 minutes ago
    —discuss
  16. Pennsylvania's Amazon Data Center Boom Is Fueled by a Lucrative Tax Break(capitalandmain.com ↗)
    1 pointsby 8 minutes ago
    —discuss
  17. Show HN: Tincan – terminal voice chat with no server in the middle(github.com/bilalyazicioglu ↗)
    1 pointsby 9 minutes ago
    1comments
  18. What happened with xcancel, and is there any chance it'll ever be back?
    1 pointsby 10 minutes ago
    —discuss
  19. The Detective and the Madman(cinemasojourns.com ↗)
    1 pointsby 10 minutes ago
    —discuss
  20. To Stand Out, Write CSS(chrisfowles.xyz ↗)
    1 pointsby 13 minutes ago
    —discuss
  21. Bitterbot – A local-first P2P AI agent engine with persistent memory(github.com/bitterbot-ai ↗)
    2 pointsby 14 minutes ago
    1comments
  22. EU announces plan to ban social media for under 13s(cnn.com ↗)
    1 pointsby 14 minutes ago
    —discuss
  23. Fenchel Duality Theory and a Primal-Dual Algorithm on Riemannian Manifolds (21)(springer.com ↗)
    1 pointsby 14 minutes ago
    —discuss
  24. Potemkin Village(wikipedia.org ↗)
    2 pointsby 15 minutes ago
    —discuss
  25. How Can We Enjoy the Necessary Practice to Master Valuable New Skills?(createadaptablelife.com ↗)
    2 pointsby 17 minutes ago
    —discuss
  26. McMurtry Spéirling [video](youtube.com ↗)
    1 pointsby 17 minutes ago
    1comments
  27. Talk to any self-hosted AI from your iPhone, Watch, Mac and car (open source)"(github.com/gigaduckai ↗)
    1 pointsby 18 minutes ago
    —discuss
  28. Explore DDD Conference(exploreddd.com ↗)
    1 pointsby 18 minutes ago
    —discuss
  29. Global Privacy Control(support.mozilla.org ↗)
    1 pointsby 19 minutes ago
    —discuss
  30. Math Can't Go on Like This(theatlantic.com ↗)
    2 pointsby 20 minutes ago
    —discuss

Show HN: OmnisBench, a re-gradable, open LLM routing benchmark on fresh tasks

3 pointsby 1h agogithub.com
Open original View on HN
1 comments
36m agoHN ↗

fresh tasks plus regrading could make routing benchmarks much harder to game. how often will the task set rotate?

Open thread on HN ↗