New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Apple Hong Kong's credit card fraud problem(larrysalibra.com ↗)
    discuss
  2. Should We Accept Degrowth as a Serious Academic Concept?(humanprogress.org ↗)
    discuss
  3. Tell the CA Governor to Protect Net Neutrality, Affordability, and Public Safety(eff.org ↗)
    1comments
  4. Mainsprings, watermarks, answer boxes and other bad words for good ideas(arjunkirtipatel.com ↗)
    discuss
  5. Apple May Return to Server Market with Nvidia Technology(macrumors.com ↗)
    1comments
  6. Show HN: A Stateful LLM API that works across providers(twigg.ai ↗)
    discuss
  7. Show HN: Plant watering system with Arduino Nano(sam-burns.com ↗)
    1comments
  8. Problem Notation and Testing(ciju.in ↗)
    discuss
  9. Bamzooki(wikipedia.org ↗)
    discuss
  10. OpenAI Expands ChatGPT Ads with Sponsored Agents(openai.com ↗)
    discuss
  11. /pyor:review – Claude skill for human code review(github.com/pyor-review ↗)
    discuss
  12. Valve plans to get Steam games working on compatibility-challenged ARM PCs(rockpapershotgun.com ↗)
    discuss
  13. We're catalyzing megaton-scale climate impact in Brazil(blog.google ↗)
    discuss
  14. AI research institute founded by Yoshua Bengio vandalized in Montreal(cbc.ca ↗)
    1comments
  15. DeepMind Paper: Dream-RSI: Recursive Self-Improvement Through Evolving Worlds(arxiv.org ↗)
    1comments
  16. I caught an LLM-powered recruiter with a prompt injection on LinkedIn(khancyr.github.io ↗)
    discuss
  17. Show HN: Skill to generate change preview pages(github.com/steveharrison ↗)
    discuss
  18. Explaining the Proposed $103k H-1B Fee(ifp.org ↗)
    discuss
  19. AWS can't restore service to Bahrain, UAE facilities 6 months after Iran strikes(cnbc.com ↗)
    discuss
  20. Scientist Workbench: Scientific Compute for Agents(scientistworkbench.com ↗)
    discuss
  21. How to Buy a Tesla and Get FSD for Free(tynan.com ↗)
    discuss
  22. WAIl (Blonging for Freedom)(oliva.nom.br ↗)
    discuss
  23. The Climb Was the Safety Feature(cekrem.github.io ↗)
    discuss
  24. Using NetBSD's pkgsrc everywhere I can(rubenerd.au ↗)
    discuss
  25. Show HN: Who-GPU, a simple monitoring tool to view GPU usage across machines(github.com/lucafossen ↗)
    discuss
  26. You're on the Real X Website and You're Still Being Scammed(brothke.medium.com ↗)
    discuss
  27. The American Age Is Over(theatlantic.com ↗)
    5comments
  28. Show HN: TeXposit – Feature rich LaTeX and Markdown editor(texposit.com ↗)
    discuss
  29. Goroutine Leak Profiles(go.dev ↗)
    discuss
  30. Starlink's Other Network(circleid.com ↗)
    discuss

Show HN: Sloptris - If Tetris was like AI-assisted dev

3 pointsby 54m agotonyalicea.dev
5 comments
48m agoHN ↗

I've been thinking a lot about how agentic coding is similar to gaming. Risk, reward, gambling, gratification, etc. I've been exploring that by vibe coding some satirical games that aim to reflect what agentic coding can be like in a deadline environment. This is one of those games.

It's Tetris but:

- You have to build a tetromino either manually or have AI "generate" it.

- Generated tetrominoes might mutate after falling.

- You can spend time to "review" generated tetrominoes as they fall to see how they will mutate.

The theme is the risk/reward/pressure of agentic code vs manual vs reviewed agentic code in a deadline environment.

35m agoHN ↗

There's a probability per-level of mutation.

20m agoHN ↗

Very cool project! I've been playing it for a while. In a lot of online spaces, AI seems to get a lot of hate and such; it would be interesting if there were a morality system through frequent AI use. Or perhaps frequent use of AI minos without review causes errors or mutations in regular minos, to mimic how frequent use of AI can make you worse at programming if you take reviewing out of the process.

9m agoHN ↗

Yes those are cool ideas! The push and pull of ideas has been between satire and playability. But skill atrophy is definitely a game mechanic I've been exploring.