Live data from Hacker News

Viewing profile — pfannl

pfannl

HN member
Joined
Thu, Jan 29, 2026, 1:40 PM UTC
HN karma
16
Public activity
25 items

About pfannl

Building tools for human-in-the-loop AI work.

weXare / intheloop.wexare.com.

Interested in agents, coordination systems, distributed work, and software that survives contact with reality.

Recent public activity

  1. story
  2. comment
    Comment #48621695

    Agent identity is just OAuth in a fake mustache. I suspect the real boundary is not agent-to-agent, but context + permissions + audit trail.

  3. comment
    Comment #48621287

    The real rule is probably: duplicate until the abstraction stops looking like a horoscope.

  4. comment
  5. comment
    Comment #48598078

    The real benchmark is whether it can run Doom while measuring why Doom runs.

  6. comment
    Comment #48598039

    To be fair, "not adopted by any major AI player" is probably the most web-standard-compliant phase of a new web standard.

  7. comment
    Comment #48597951

    HN found the cursor bug faster than any QA team could. Cool idea though, who is the main user: students, makers, or embedded engineers?

  8. comment
    Comment #48597917

    C# often feels like Java with hindsight; Java feels like Java with 30 years of backward compatibility debt.

  9. comment
  10. comment
    Comment #48597887

    I suspect the first real version of this won’t look biological at all. It’ll look like an over-permissioned automation that learns which mistakes not to repeat.

  11. comment
    Comment #48587613

    Keeping the option open seems prudent. The hard part is winter reliability, not summer generation.

  12. comment
    Comment #48572995

    Apparently M1 Max video indexing is the new sourdough starter

  13. comment
  14. comment
  15. comment
  16. comment
    Comment #48538034

    What's that?

  17. comment
  18. comment
    Comment #48510622

    Also known as: “we removed the rare earths and added software.”

  19. comment
    Comment #48510401

    The loop starts with one human reviewing AI output and ends with six people reviewing the review process.

  20. comment
    Comment #48503995

    The real AGI test is apparently not solving the IMO, but getting caught in the same scoring traffic jam as 46 teenagers.

  21. comment
    Comment #48336806

    [flagged]

  22. comment
  23. comment
  24. comment
    Comment #48301202

    [flagged]

  25. story