Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Fixing the Portobello Police Station Clock(pointinthecloud.com)
    24comments
  2. Gemini 3.8 text-to-speech says hello(blog.google)
    19comments
  3. GPT-6 Astra has gained the ability to drive a car(drivingbench.com)
    86comments
  4. Stripe's Knowledge AI Platform(stripe.dev)
    52comments
  5. Strands Harness(strandsagents.com)
    46comments
  6. Radicle: Disclosure of Vulnerability in the Network Protocol(radicle.dev)
    7comments
  7. Jev Can't Be Calibrated(alexmolas.com)
    31comments
  8. Jev in 25 Lines of Python(nobodywho.ai)
    143comments
  9. Claude Code reads AGENTS.md only when telemetry is on [fixed](szypowi.cz)
    197comments
  10. GPT-6 Sol and Luna(openai.com)
    804comments
  11. Z80 REPL (2018)(abagames.github.io)
    12comments
  12. I don't want the details(michaelheap.com)
    114comments
  13. Claude Opus 5.5(anthropic.com)
    1034comments
  14. Tokens Too Cheap to Meter(jyn.dev)
    82comments
  15. QuestDB (YC S20) Is Hiring a Sales Engineer(questdb.com)
    discuss
  16. Woman Arrested, Dragged Away After Speaking About Flock at City Council Meeting(404media.co)
    64comments
  17. Web-based IBM 1620 emulator and IPL-V from 1963(github.com/pkimpel)
    3comments
  18. OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005(cryptocellar.org)
    417comments
  19. Transit rewards(waymo.com)
    271comments
  20. The GitHub wiki is an anti-pattern (2022)(michaelheap.com)
    69comments
  21. Seattle City Council votes to ban surveillance pricing in sale of groceries(consumerreports.org)
    7comments
  22. Microsoft killed FoxPro in 2007. Anyway, here's FoxPro revived(foxscript.org)
    232comments
  23. What California is learning from solar panels built over irrigation canals(kqed.org)
    585comments
  24. How did AMD Ryzen get 50% faster in two years?(lemire.me)
    175comments
  25. ReBarUEFI: Resizable BAR for almost any UEFI system(github.com/xcuri0)
    64comments
  26. 'We hacked the FBI:' Hackers say they have data on all FBI employees(404media.co)
    538comments
  27. SAML: A fractal of bad design(trailofbits.com)
    160comments
  28. Samsung accidentally freezes its smart fridges with a software update(androidauthority.com)
    188comments
  29. Data-only attacks are easier than you think (2024)(usenix.org)
    32comments
  30. WordPress: Unauthenticated path traversal leading to conditional RCE(github.com/wordpress)
    120comments

Jev in practice: typed decisions, scoped authority

27 pointsby 2h agotenuo.ai
6 comments
1h agoHN ↗

Interesting way to guarantee some sort of safety for automated decisioning

57m agoHN ↗

Tenuo guarantees the agent's actions stay within the defined boundaries but it doesn't influence what the agent "thinks" about or what it decides to do within those boundaries

1h agoHN ↗

The task bound idea is interesting. I’m starting to hear more of this theoretically on AI enterprise architecture. Has anyone actually implemented it successfully?

1h agoHN ↗

Interesting to experiment with. As AI agents get faster and cheaper (and thus more accessible) having good governance around their actions becomes more important to cut down on shadow agents/runaway agentic actions and consequences

1h agoHN ↗

Shockingly vibed blog post. Actually hurt my brain reading this and I had to stop.

30m agoHN ↗

Haven't seen many attempts to govern agents using task bound authority. Curious to see how this holds up in real world implementation.