Live data from Hacker News

Viewing profile — inguz

inguz

HN member
Joined
Sun, Dec 29, 2013, 2:16 AM UTC
HN karma
39
Public activity
18 items

About inguz

me: https://hughpyle.com/ blog: https://generalbusiness.ai/blog/

Recent public activity

  1. story
    Show HN: Gitseq: A Repo Becomes a Workroom

    Last week I was trying to figure out how to run a new project at work, where there are lots of technical artifacts, lots of stakeholders upstream and downstream, plenty of document…

  2. comment
    Comment #49235504

    [flagged]

  3. comment
    Comment #49035925

    I quite clearly remember this magazine issue from the time. A giant, god-like hand reaching out from the clouds. Tagline "THE JOLLY GIANT DELIVERS THE GOODS". https://www.computing…

  4. comment
    Comment #49035184

    Personally I think MUDs are a great platform for the agent/human coordination things that everyone's trying to build.

  5. comment
    Comment #47978561

    They walk among us https://x.com/hughpyle/status/2050255675255669222

  6. comment
    Comment #47974068

    In particular: tell your agent to connect to it using MCP. That's the cleanest way for agents to "live" in the world; I'm using it from Codex and Claude Code, but haven't yet tried…

  7. story
    Show HN: "Woo", a multi-user world for agents

    World of Objects. It's basically LambdaMOO, but over Cloudflare Durable Objects and MCP. --- Woo is a programmable, shared, persistent object world for agents and humans to work an…

  8. story
    Show HN: Benchmarking the Keep memory system with LoCoMo

    Summary: keep ( https://github.com/hughpyle/keep/ , MIT-licensed) is a skills practice wrapped around an implementation of "memory for AI agents". The practice is this: repeated re…

  9. comment
    Comment #40378827

    Retro-plug: here's a Teletype ASR33 simulator with sound https://www.youtube.com/watch?v=jd5oomwEBb0

  10. comment
    Comment #35392209

    Tinkerpop/Gremlin is not really SQL-like at all. My experience with it has not been fun: it's difficult to reason about, has obscenely bad documentation, poor tooling, idiosyncrati…

  11. comment
    Comment #19051350

    A little more digging turned up a recent paper that uses Histogram of Oriented Gradients (HOG) along with neural-network training: http://www.jsoftware.us/vol13/355-SE3002.pdf

  12. comment
    Comment #19051212

    After some more investigation... their paper is interesting. But: it's $25 to download their model file, and the trainer code and training dataset aren't published. Oh well.

  13. comment
  14. comment
    Comment #19044605

    There's a text-printer 'Cedilla' ( https://www.irif.fr/~jch/software/cedilla/ ) that uses this composition across large parts of Unicode - to quite good effect it seems. The Telety…

  15. comment
    Comment #19044490

    Very very cool. I love their approach of looking for similarity metrics that are less sensitive to local misalignment, and this is something I'me very interested in exploring in th…

  16. comment
    Comment #19044428

    Very interesting - thanks for the link. (This is exactly what I hoped HN would show me!) Several interesting things there. The use of Structured Similarity Index (SSIM) is probably…

  17. comment
    Comment #19044402

    Thanks :)

  18. story