Live data from Hacker News

Viewing profile — cheekygeeky

cheekygeeky

HN member
Joined
Wed, May 13, 2026, 4:58 PM UTC
HN karma
3
Public activity
18 items

About cheekygeeky

Interested in everything in the universe, on a rotating basis.

Recent public activity

  1. comment
    Comment #48928453

    [flagged]

  2. comment
    Comment #48928428

    Suggestion: Save the article as an .md file. Upload it to Fable 5 with the prompt: "Agree or disagree. Be verbose." I learned a lot: Where he's right. Where he's wrong. A 'deliciou…

  3. comment
    Comment #48928387

    [flagged]

  4. comment
    Comment #48910629

    Didn't Ai make cloning ANYTHING easier?

  5. comment
    Comment #48666136

    They do. See: Claude Code leak.

  6. comment
    Comment #48664435

    [flagged]

  7. story
  8. comment
    Comment #48645597

    [flagged]

  9. comment
    Comment #48644992

    [flagged]

  10. comment
    Comment #48575032

    Thank you for providing this! Your Windows instructions say: scoop bucket add tamnd https://github.com/tamnd/ Returns: ERROR ' https://github.com/tamnd/scoop-bucket ' doesn't look …

  11. comment
    Comment #48570743

    [flagged]

  12. comment
    Comment #48570267

    This is way cool and will hopefully speed its adoption by the browser makers. How does the filesize compare to an identical webp?

  13. comment
    Comment #48544630

    Our software dev (smartest guy I ever met) is using OpenCode and Tmux with Open Source models. He says the DeepSeek is his model of choice for coding (he call's it "pretty GOOD". H…

  14. comment
    Comment #48496568

    Google will want him terminated immediately and will probably make him some settlement (combined with a threat) to keep his mouth shut, going forward. Meanwhile, the media will be …

  15. comment
  16. comment
    Comment #48127588

    ...unless you are trying to get Google's attention for a job interview. :)

  17. comment
    Comment #48127573

    [flagged]

  18. comment
    Comment #48124520

    > He removed MLP from Qwen and the model still could do transformation tasks on input but lost knowledge. But not deterministic?