Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: I built a camera that you talk with instead of seeing your own face(makiroll.app ↗)
    discuss
  2. I Don't Want to Read What You Didn't Write(colinbreck.com ↗)
    discuss
  3. Bunker mentality: the Nordics' cold war shelters being given a new lease of life(theguardian.com ↗)
    discuss
  4. How to Bring a Geothermal Well Back from the Dead(wired.com ↗)
    discuss
  5. A unified evolutionary explanation of Parkinson's disease(nih.gov ↗)
    1comments
  6. Show HN: I analysed 169,123 Chess Olympiad moves and gave out 132 silly awards(olympiadstats.fun ↗)
    discuss
  7. ChatGPT Is a Nightmare (A Lesson on Bad UX)(saasexperts.co ↗)
    2comments
  8. Abolish Patents(gomakethings.com ↗)
    discuss
  9. Website toolbox with super simple AI builder(nanomo.app ↗)
    discuss
  10. Visions in Uzbekistan(animationobsessive.substack.com ↗)
    discuss
  11. How to Make Your AI Agent EU AI Act Compliant: A Practical Guide(medium.com/mirarshadtalpur ↗)
    discuss
  12. Show HN: Sokkan – an HITL Claude Code cockpit that remembers, at session startup(github.com/ninabot-ch ↗)
    1comments
  13. Show HN: Open-source shared memory for teams of AI coding agents(github.com/motif-labs ↗)
    discuss
  14. Googlebook: The laptop your Android phone has been waiting for(blog.google ↗)
    1comments
  15. Australia considers banning the use of smart glasses in government buildings(reuters.com ↗)
    1comments
  16. You're Already a Meat Proxy(twitter.com/obie ↗)
    discuss
  17. Et Tu, MacBook? Unprivileged Keystroke Inference via Built-In IMU Side Channel(arxiv.org ↗)
    discuss
  18. DeepSeek is training a 2T-parameter model and plans to build an 8T-parameter one(twitter.com/wallstengine ↗)
    discuss
  19. OpenAI Weighs Funding Round at over $1.2T Valuation(bloomberg.com ↗)
    discuss
  20. HP Googlebook 14c(hp.com ↗)
    discuss
  21. Beyond Ukraine: Why Europe is preparing for a wider conflict(cnn.com ↗)
    discuss
  22. LM Studio is a free desktop app to run local LLMs on your own computer(lm-studio.net ↗)
    1comments
  23. Leaving US Big Tech in a Week(yves.vg ↗)
    discuss
  24. A never-ending childhood of malaria(ourworldindata.org ↗)
    discuss
  25. Show HN: Jev-CLI – CLI wrapper for JEV typesafe AI model(github.com/joshlong145 ↗)
    discuss
  26. Amazon blocks Meta's Muse AI assistant in new standoff over agentic shopping(geekwire.com ↗)
    1comments
  27. DBison: Free Modern Database Explorer(dbison.app ↗)
    discuss
  28. Kimi Code Desktop(kimi.com ↗)
    discuss
  29. Longitudinal survey finds little evidence that social tech predicts satisfaction(phys.org ↗)
    discuss
  30. Show HN: I built Founder.best Product Hunt alternative for LLM product discovery(founder.best ↗)
    1comments

Show HN: Witdem – Did your AI Agent accomplish its task? and at what cost?

3 pointsby 2h agodemo.witdem.com
5 comments
2h agoHN ↗

i really like this. the “the agent finished” vs. “the agent actually did what it was supposed to do” distinction is something i don't see addressed very well by most observability tools.

traces, tokens, latency etc. are great, but in the end i care about whether the job got done. i think this is a pretty interesting way of looking at it. - and it is free, right?

1h agoHN ↗

It is totally free and open-source we are looking for the first design partners to ship the enterprise version on production. The enterprise repo is using the OSS as the core and make it easily scalable. There are some differences in the technologies used tho.

1h agoHN ↗

Cool tool, now I know how much I've spend on AI xD. But how exactly can you measure if the outcome of a flow was successful?

1h agoHN ↗

The way I do it is actually by Defining Yaml contracts, to define the business outcome so using the traces you can understand if it reaches the goal. Evaluations also play a big role