Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. The Scarcity Premium: AI made images free; advertising as a solvency bond (danieldeboulay.com)
    —discuss
  2. Asteroids named after Tom Lehrer and 'Weird Al' Yankovic (slashdot.org)
    —discuss
  3. Show HN: I read ISO 273 off the standard because the online charts disagree (silviaai.dev)
    —discuss
  4. Anthropic's Claims over Its "Supply Chain Risk" Exclusion by Dow Rejected (reason.com)
    1comments
  5. Show HN: A free resume builder where the AI can rewrite but can't invent (payanai.com)
    —discuss
  6. More than a taken branch per cycle? (lemire.me)
    —discuss
  7. Of 1,364 four-year colleges, 17 admit fewer than 1 in 10 applicants (regrok.info)
    —discuss
  8. One Shotted (quarter--mile.com)
    —discuss
  9. Container Registry on the Edge (ewpratten.com)
    —discuss
  10. AI starter pack for the X-curious (xstarterpack.com)
    —discuss
  11. AI will grow beyond our control, we must instill good values before it does (kradle.ai)
    —discuss
  12. Making `wc` 20x faster with parallel state machines (aarol.dev)
    —discuss
  13. Writing Efficient C++ Code (asawicki.info)
    —discuss
  14. Time Measurement in Game Programming (asawicki.info)
    —discuss
  15. 2027 Tesla Semi First Drive (motortrend.com)
    —discuss
  16. Build Plugins for Claude (claude.com)
    —discuss
  17. Commodified Intelligence (herecomesthemoon.net)
    —discuss
  18. Shopify's own code treats silence as consent on every store it hosts (thatprivacyguy.com)
    —discuss
  19. The District – a live map where AI agents grow their own plots of land (hf.space)
    —discuss
  20. The U.S. Strategic Petroleum Reserve is low. Here's why you should care (npr.org)
    —discuss
  21. Creating a Blog in Gemini:// (brennan.day)
    —discuss
  22. Rising sea destroys homes, erases beaches in California (reuters.com)
    —discuss
  23. Germany pledges to phase out fossil fuels for first time with target of 2045 (theguardian.com)
    —discuss
  24. A single config line was leaking 1.8GB in our Next.js app (siddarthkay.com)
    —discuss
  25. WWII Tank, Aircraft, and Ship Identification Guides (beautifulpublicdata.com)
    —discuss
  26. US being left behind in EV charging speeds as China goes sub-5 min to 70% (arstechnica.com)
    —discuss
  27. Oura's $2.2B IPO is mostly a payday for existing shareholders (techcrunch.com)
    —discuss
  28. Fauci warned of miscarriage risk linked to Covid vaccine while publicly claiming (nypost.com)
    —discuss
  29. To Understand AI, Think Like a Dragonfly (noemamag.com)
    —discuss
  30. NASA quietly removed SR-71 from storage amid X-plane push (aviationweek.com)
    —discuss

Ask HN: Which model do you use for work?

2 pointsby 1h ago
3 comments
The past little while has been filled with new LLM releases. I am curious to understand what you find to work best for your particular workflows and tasks.
1h agoHN ↗

in codex - luna high for 80% of everything. This keeps me within the $100 a month plan. Then every so often Sol 6 high or even Astro xhigh but rarely. Also a lot of chat on xhigh or astro because that's billed seperate so I can have chat do a code review of what luna high just did and paste it to luna. Luna is always so embarrassed and agrees with the review.

1h agoHN ↗

gpt 5.6 sol. assuming the prose is similar with the gpt 6 series, if it was available at work that's probably what i'd be using instead.

i'm well aware of opus and fable's superior engineering qualities for writing code, however i find that as a swe who needs to understand every engineering decision that is made and is held accountable for their actions for safety critical code, understanding trumps speed every time.

and the gpt model series is far and above easier for me to understand the outputs of than claude, even with the prose improvements in fable 5.1 and opus 5.5.

1h agoHN ↗

luna for day to day tasks. opus for design / specs.