Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Australia considers banning the use of smart glasses in government buildings(reuters.com ↗)
    discuss
  2. You're Already a Meat Proxy(twitter.com/obie ↗)
    discuss
  3. Et Tu, MacBook? Unprivileged Keystroke Inference via Built-In IMU Side Channel(arxiv.org ↗)
    discuss
  4. DeepSeek is training a 2T-parameter model and plans to build an 8T-parameter one(twitter.com/wallstengine ↗)
    discuss
  5. OpenAI Weighs Funding Round at over $1.2T Valuation(bloomberg.com ↗)
    discuss
  6. HP Googlebook 14c(hp.com ↗)
    discuss
  7. Beyond Ukraine: Why Europe is preparing for a wider conflict(cnn.com ↗)
    discuss
  8. LM Studio is a free desktop app to run local LLMs on your own computer(lm-studio.net ↗)
    1comments
  9. Leaving US Big Tech in a Week(yves.vg ↗)
    discuss
  10. A never-ending childhood of malaria(ourworldindata.org ↗)
    discuss
  11. Show HN: Jev-CLI – CLI wrapper for JEV typesafe AI model(github.com/joshlong145 ↗)
    discuss
  12. Amazon blocks Meta's Muse AI assistant in new standoff over agentic shopping(geekwire.com ↗)
    discuss
  13. DBison: Free Modern Database Explorer(dbison.app ↗)
    discuss
  14. Kimi Code Desktop(kimi.com ↗)
    discuss
  15. Longitudinal survey finds little evidence that social tech predicts satisfaction(phys.org ↗)
    discuss
  16. Show HN: I built Founder.best Product Hunt alternative for LLM product discovery(founder.best ↗)
    1comments
  17. Raspberry Pi blocks changing RAM chips(raspberrypi.com ↗)
    2comments
  18. Your cloud survived everything except the real world – AWS(theregister.com ↗)
    discuss
  19. A Doomsday Scenario for American AI(thefp.com ↗)
    discuss
  20. SpaceX Restricts Airspace over McGregor Facility Ahead of Tesla Roadster Event(driveteslacanada.ca ↗)
    discuss
  21. Stanford, Silicon Valley, and the pursuit of power [video](youtube.com ↗)
    discuss
  22. A build graph that rolls dice(fzakaria.com ↗)
    discuss
  23. JevBench: Benchmark for Jev-Class Models(benchmarkheaven.com ↗)
    discuss
  24. A functional test cannot be failed on biological grounds(leoferres.blog ↗)
    discuss
  25. Ask HN: Is it impossible to disable Siri on macOS 27?
    discuss
  26. Show HN: JevGeni, the fruit-fly claw machine overator(jevgeni.vercel.app ↗)
    discuss
  27. Planly(github.com/drkokorev ↗)
    2comments
  28. There is no way to get ChatGPT to stop injecting your location in context(chatgpt.com ↗)
    2comments
  29. OpenAI Codex Is Retiring the Last Model That Behaves Like an Assistant(vincentschmalbach.com ↗)
    1comments
  30. The Campaign for North Africa(wikipedia.org ↗)
    discuss

Ask HN: How do you guys stay on top of the code that is generated?

3 pointsby 1h ago
3 comments
I have been working on a new service from scratch and AI has spat out 1000s of LOC and while I leveraged on it quite a bit for the design of the service, I need to know exactly what is happening in every single line of code. This has increasingly become a problem for me, especially when working on something new from scratch, is there any plugin, skill, prompt that makes it easier to understand a codebase in-depth?
1h agoHN ↗

I think a lot of folks ended up in a world where you write specs and designs in Markdown documents and use that to drive the outcome (the code, the system, tests, etc). So you drive intend through those specifications and design docs.

Lately though, I've switched tact a bit and have resurrected some ~20yr old research called Behaviour Tree Engineering or Behaviour Trees, so I'm now writing specifications called BT specs.

e.g: https://bte.mills.io/s/v4Mjbyf0OBJWm5YRLwG5XiIH

52m agoHN ↗

Two distinct strategies.

For tools and architecture,I design data structures and let the LLM write the code, in small steps. Lots of discussion with the LLM. What Cory Doctorow calls centaur mode - a human mind augmented with a more powerful body. Applies to side projects and $DAYJOB.

For applications, I rewrote a framework of mine that I used 2003-2009. It is highly constrained so the LLM has few options to improvise. I can just tell it what features to add and it adds them without much in the way of slop. I still find code repetition which I just tell it to clean up.

48m agoHN ↗

ponytail plugin is good for reducing amount of code. i have a different ai that code reviews it and i tell it that it is smarter than the ai that wrote the code. i had to tweak it to not be too nitty.