Live data from Hacker News

Viewing profile — menzoic

menzoic

HN member
Joined
Wed, Jul 03, 2013, 3:14 AM UTC
HN karma
1,016
Public activity
396 items

About menzoic

No profile information was provided.

Recent public activity

  1. comment
    Comment #48081701

    The difference is not that it’s “worthless”. The difference is that now it’s “practical” to implement given the low effort. I wouldn’t be sad about defeating lower complexity chall…

  2. comment
    Comment #47886647

    API prices may be profitable. Subscriptions may still be subsidized for power users. Free tiers almost certainly are. And frontier labs may be subsidizing overall business growth, …

  3. comment
    Comment #47759410

    I just put your question into GPT-5 Pro

  4. comment
    Comment #47561346

    I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…

  5. story
  6. comment
    Comment #47137838

    I'm at Airbnb now working primarily with LLMs

  7. comment
    Comment #47136659

    I’ve found there are two major mindset shifts that helped me start passing tech interviews consistently: 1. Study the algorithms and patterns, not the questions 2. Treat it like a …

  8. story
  9. comment
    Comment #47136563

    I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…

  10. story
  11. comment
    Comment #47125488

    It's basically the typical SDLC boosted with LLMs. Especially the part where you can explore tradeoffs and alternative approaches rapidly.

  12. comment
    Comment #47125457

    LOL, honestly I hated Codex when it first came out. It was backed by o3 at the time. But literally as soon as GPT-5 came out in Codex and with the "high" option, I completely switc…

  13. comment
    Comment #47125423

    > get the best results when the context window is right around 70% I used to be trigger happy with /compact or using the hand off technique to transfer knowledge between sessions w…

  14. comment
    Comment #47125194

    I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…

  15. story
  16. comment
    Comment #46955372

    I would think it’s due to the non determinism. Leaking context would be an unacceptable flaw since many users rely on the same instance. A/B test is plausible but unlikely since th…

  17. comment
    Comment #46510575

    Leetcode problem

  18. comment
    Comment #45702331

    Studies on rats have shown significant similarities between sugar consumption and drug-like effects, including bingeing, craving, tolerance, withdrawal, dependence, and reward. Som…

  19. comment
    Comment #45286222

    Why does skyfall.dev block Nigeria?

  20. comment
    Comment #45132524

    >At that point, a shared ledger implemented with traditional databases / protocols would be faster, easier, and more transparent. This is missing the fundamental idea behind blockc…

  21. comment
    Comment #44931221

    GPT-5 is a text only model. ChatGPT uses 4o for images still

  22. comment
    Comment #44831155

    The idea is that AGI will be able to self improve at an exponential rate. This is where the idea of take off comes from. That self improvement part isn’t happening today.

  23. story
  24. comment
    Comment #44587430

    Genius transition plan

  25. comment
    Comment #44335597

    How is the security risk propaganda?