Live data from Hacker News

Viewing profile — bilbo-b-baggins

bilbo-b-baggins

HN member
Joined
Sat, Jun 15, 2024, 9:19 PM UTC
HN karma
111
Public activity
72 items

About bilbo-b-baggins

No profile information was provided.

Recent public activity

  1. comment
    Comment #49164444

    > executive branch interagency body with appropriate national security expertise Pete and his drinking buddies, probably.

  2. comment
    Comment #49164436

    It’s not them trying to make nice. It’s them trying to extort China and China fucking knows it. God I hate this timeline.

  3. comment
    Comment #48930166

    Fuse is already a ssh fs driver project

  4. comment
    Comment #48875068

    They are. There’s been a bunch of studies already showing how Google skews its results to align with oligarch interests.

  5. comment
    Comment #48604263

    I would say since your focus is on structural or programmatic detection, and not LLM heuristics, the problem depends on language a lot. In Rust or Go there’s super clear test marke…

  6. comment
    Comment #48520938

    You seem to assume rational actors. Bezos et. al. are definitely not that.

  7. comment
    Comment #48513757

    On the day of the SpaceX IPO with no evidence? Yeah. Pull the other one it’s got bells on.

  8. comment
    Comment #48429532

    [flagged]

  9. comment
    Comment #48390599

    You forgot BM25 embeddings. https://github.com/MikeS071/ai-engram https://github.com/lamost423/openclaw-hybrid-memory https://medium.com/@qdrddr/agentic-memory-framework-hindsigh..…

  10. comment
    Comment #48350284

    Bro just rediscovered software best practices and thinks its a novel AI thing. Fuck, we’re so cooked.

  11. comment
    Comment #48231386

    Look at the juxt/allium plugin. It’s a more mature version of what you’re attempting. Also big requirements/tasks files will rot your context opening up hallucinations and drift. S…

  12. comment
    Comment #48132339

    Claude code runs as a nearly stateless server using session JSONL files as a conversation database, sending stateless API requests to Anthropic, etc. This post doesn’t seem to unde…

  13. comment
    Comment #47582598

    Man there is a LOT of people who have no idea how these GPT-LLM services actually work, despite there being large amount of documentation on the APIs and whitepapers and so forth.

  14. comment
    Comment #46928757

    Love this thread reminding me that most experts in computers are unhinged lunatics doing convoluted and tortured things on a daily basis that they consider perfectly normal and eve…

  15. comment
    Comment #46921774

    Their series on LLMs, neural nets, etc., is amazing.

  16. comment
    Comment #46853177

    So… store heat in an insulated swimming pool 10ft deep, 30ft wide, and 90ft long, at 185F, above the service temp for XPS foam, got it, ok. At least you could also use it to sous v…

  17. comment
    Comment #46840248

    Unless you know someone at Google with a little swagger to get things done you’re shit out of luck.

  18. comment
    Comment #46729059

    The solution that Anthropic uses for Claude Code Web for repository access is to not give the LLM any secrets at all - anything requiring escalated privilege is done through a prox…

  19. comment
    Comment #46439254

    Good Christ. Imagine having decided that your price structures should be a JSON file instead of persisted in a database and then thinking that any decision made by that person/team…

  20. comment
    Comment #46427793

    Your site advertises careers in San Francisco/Remote. California law requires compensation disclosures.

  21. comment
    Comment #46409062

    I’ve used pre-commit the tool and now prek for the better part of a decade and never had these issues even using rebase flows exclusively. This seems like an operator error.

  22. comment
    Comment #46226406

    You totally can build it using unsafe and generics. I’ve done it with mmap-backed byte slices for arbitrary object storage.

  23. comment
    Comment #46226392

    Man this person is mediocre at best. You can do fully manual memory management in Go if you want. The runtime is full of tons of examples where they have 0-alloc, Pools, ring buffe…

  24. comment
    Comment #46042706

    [flagged]

  25. comment
    Comment #45935423

    My personal best is probably the metaclass tree formation in HumbleDB. Best I’ve seen is probably the Golang arm64 NEON asm implementation of maphash using AES before the 1.24 upda…