Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Bend 2 and the Vibe-Coding Trap(liampwll.com ↗)
    11comments
  2. I don't like passkeys(hawksley.dev ↗)
    1comments
  3. OpenJev(openjev.com ↗)
    114comments
  4. ZCode, the GLM coding agent, silently uploads your Git history(tokenstead.ai ↗)
    17comments
  5. Jemalloc 5.4.0(github.com/jemalloc ↗)
    54comments
  6. Microsoft exec called AI scraping 'the largest theft of labor in human history'(techcrunch.com ↗)
    240comments
  7. Cekura (YC F24) Is Hiring(ycombinator.com ↗)
    discuss
  8. The scourge of x86 emulation(fex-emu.com ↗)
    37comments
  9. Subnormal floating-point numbers are expensive on Intel processors(lemire.me ↗)
    3comments
  10. Astra for Law(openai.com ↗)
    609comments
  11. Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint(prismml.com ↗)
    146comments
  12. Replacing Pull Requests with Delta(zed.dev ↗)
    18comments
  13. Bend – A language that blocks AI mistakes via proof, on CPU and GPU(bend-lang.com ↗)
    239comments
  14. Warren Buffett Steps Down as Berkshire Chairman, Names Son to Replace Him(nytimes.com ↗)
    20comments
  15. Qwen 3.8 Omni Flash(qwen.ai ↗)
    91comments
  16. Hister: A private search engine for the pages you visit and the files you keep(github.com/asciimoo ↗)
    173comments
  17. Wax motor(wikipedia.org ↗)
    77comments
  18. When the fractional part of a float fixes your shader(crocidb.com ↗)
    8comments
  19. Fujitsu launches made-in-Japan next-generation CPU FUJITSU-MONAKA(global.fujitsu ↗)
    236comments
  20. Pre-Greek: The lost language hidden within Ancient Greek(linguisticdiscovery.com ↗)
    47comments
  21. Dr Julius Neubronner's Miniature Pigeon Camera(publicdomainreview.org ↗)
    discuss
  22. How to Write with an LLM(sockpuppet.org ↗)
    133comments
  23. A heap overflow and SSO misconfiguration to compromise OpenAI internal repos(hacktron.ai ↗)
    161comments
  24. Shapelearn Qwen 3.8 27B (13.1 GB VRAM)(byteshape.com ↗)
    17comments
  25. Ask A Monk – A digital wilderness for thoughts with no immediate answer(askamonk.online ↗)
    27comments
  26. Flet 1.0 – Build cross-platform apps in Python(flet.dev ↗)
    69comments
  27. Telstra outage: The night a network decided the year was 2006(netnod.se ↗)
    29comments
  28. Diplodocus, Long Thought Exclusively American, Turns Up in Spain(sci.news ↗)
    45comments
  29. Speeding up gearhash on ARM64(sam.dev ↗)
    discuss
  30. Why I didn’t sign the Fields medallists’ letter(gowers.wordpress.com ↗)
    376comments

Code Scans

23 pointsby 9h agodevin.ai
6 comments
7h agoHN ↗

Yeah, but now with “agentic mapreduce”! A “talent dense” team of prompters selling to the Feds.

6h agoHN ↗

Their sample prompt takes me back a year or two:

Find unused code in our web app. Exclude generated files and test fixtures, and check for indirect references before recommending a removal.

If I "/goal remove unused code" in Claude today, I would not even think to specify "check for indirect references" and "don't consider generated code dead code," those sorts of intuitions have been "built in" to the frontier models for a while now.

So I'm pretty confused by this, what does it do that I can't with an agent swarm?

2h agoHN ↗

Improve SEO

Reduce maintenance overhead

Make your application compile faster

Find unused code in our web app. Exclude generated files and test fixtures, and check for indirect references before recommending a removal.

If someone came to me with these requirements, I would laugh in their face. These reek of busy work with no actual business benefit. Have these people actually built real software before?

1h agoHN ↗

I would categorize these all as grunt work, but definitely not busywork or even a lack of business value. Improving SEO has direct business value. And the fact that it's unglamorous and laborious feels like a really good reason to have agents do it.