Live data from Hacker News

Viewing profile — tacoooooooo

tacoooooooo

HN member
Joined
Fri, Jun 17, 2022, 3:52 PM UTC
HN karma
193
Public activity
69 items

About tacoooooooo

alex.jacobs08@gmail.com

Recent public activity

  1. comment
    Comment #48998099

    it does seem to be moving in that direction. There were really specific things (large, complex json outputs) that gemini-2.5 flash was basically the only model that seemed capable …

  2. comment
    Comment #48998067

    they say the model(s) found and exploited a zero day

  3. comment
    Comment #48994634

    its not always that simple. dropping in a new model is trivial, but highly specific workflows may rely on specific _invisible_ aspects of a model. when that model gets deprecated, …

  4. comment
    Comment #48645330

    you'll need the Max Plus plan for that, buddy

  5. comment
    Comment #47510679

    > Yes I understand airports are complex. So you have a computer and a human, and they work together. how do you think it works today? some guy with binoculars?

  6. comment
    Comment #47502506

    pydantic-ai

  7. comment
    Comment #47501804

    whats wrong with .env files?

  8. comment
  9. story
  10. story
    Show HN: TinyFn – 500 deterministic utility APIs for AI agents (via MCP)

    Hey HN, I built TinyFn because LLMs are bad at the boring stuff — counting letters, validating emails, converting units. But they're even worse at things that are literally impossi…

  11. comment
    Comment #46890609

    same--this is exactly why I built this

  12. comment
    Comment #46886889

    LLMs absolutely do not have access to the same tools unless they're explicitly given access to them. Running on a computer means nothing. It sounds like you don't like LLMs! In tha…

  13. comment
    Comment #46885827

    Humans are also bad at math! So we created calculators. LLMs should have the same access to tools to give them the best opportunity to succeed

  14. story
    Show HN: TinyFn – Your agent sucks at math

    I built TinyFn because I kept watching AI agents confidently get basic things wrong — math, string counting, unit conversions, validations. The classic "how many R's in strawberry"…

  15. comment
    Comment #46878152

    They're building a moat with data. They're building their own datasets of trusted sources, using their own teams of physicians and researchers. They've got hundreds of thousands of…

  16. comment
    Comment #46863352

    saying they aren't pioneering is very different than saying they aren't a major player in the space. There're only like 5-7 players with a foundational model that they can serve at…

  17. comment
    Comment #46621260

    https://alex-jacobs.com

  18. comment
    Comment #46593227

    This is an interesting read, and while I support being nice to every_thing_ in principle. Most of the research into this actually shows that being mean yeilds better results

  19. comment
    Comment #46593145

    This looks pretty cool. I keep seeing people (an am myself) using claude code for more an more _non-dev_ work. Managing different aspects of life, work, etc. Anthropic has built th…

  20. story
  21. comment
    Comment #46567377

    fizsh sounds really cool, but the last commit was 7+ years ago. do you run into any issues? https://github.com/zsh-users/fizsh

  22. comment
    Comment #46554364

    not sure there are any models yet that you can get the quality out you need to do this and run on your mbp

  23. comment
    Comment #46542254

    This is a wildly out of touch thing to say

  24. story
  25. comment
    Comment #46435873

    correct afaik :( https://github.com/timescale/pgvectorscale/issues/113