Live data from Hacker News

Viewing profile — philipportner

philipportner

HN member
Joined
Sat, Jul 05, 2025, 11:34 AM UTC
HN karma
50
Public activity
12 items

About philipportner

ml systems, compilers, databases phd at tu berlin

Recent public activity

  1. comment
    Comment #49200716

    Congrats on the great job with the Altar II. If I didn't already have too many keyboards, I'd hop on the Kickstarter! FWIW, I fully agree with your opinion on including a `half wor…

  2. story
  3. comment
    Comment #48982245

    if you assume that training requires about 3x the compute of inference (one forward pass, one backward pass, parameter updates), and we take DeepSeek-V3 since their numbers are pub…

  4. comment
    Comment #48860030

    Hasn't changed at all since AI agents became a thing. tmux, nvim with a few plugins, mainly fzf and LSP support. If I do use an AI agent, I just run it in another tmux window.

  5. comment
    Comment #48474069

    > I'm not sure you can prompt a full, accurate, copy of a nontrivial codebase out of them. Even with zero temperature their accuracy is just not that high. Granted, these are some …

  6. comment
    Comment #48387227

    > My favorite side effect is that I now love all foods. Prior to this, I was a rather picky eater. Now I love everything! I feel like there's a burntsushi joke hiding in there some…

  7. comment
    Comment #48360755

    They reference the gist of 1cg in the honor code section of CS336. https://cs336.stanford.edu/

  8. comment
    Comment #47123858

    FYI: Claude has output styles, one of them is called `learning`. Instead of writing the code itself, it will add `TODO(human)` and comments to explain how to. Also adds `Insights` …

  9. comment
    Comment #47086868

    Did you publish anything you could link wrt. query rewriting?

  10. comment
    Comment #46905860

    Granted, these are some of the most widely spread texts, but just fyi: https://arxiv.org/pdf/2601.02671 > For Claude 3.7 Sonnet, we were able to extract four whole books near-verba…

  11. comment
    Comment #46905831

    This seems related, it may not be a codebase but they are able to extract "near" verbatim books out of Claude Sonnet. https://arxiv.org/pdf/2601.02671 > For Claude 3.7 Sonnet, we w…

  12. comment
    Comment #46120911

    There's a link to the AoCO2025 tag for his blog posts in the op.