Live data from Hacker News

Viewing profile — mmmehulll

mmmehulll

HN member
Joined
Fri, Sep 01, 2023, 2:44 PM UTC
HN karma
2
Public activity
11 items

About mmmehulll

mehul@mehulg.com

Recent public activity

  1. comment
    Comment #48368685

    this is really cool. I didn't know we had these

  2. comment
    Comment #48368674

    love this. would be cool if we can see and perform all kinds of banking txns on this. Think ledger but all in one card. Super cool. Even cooler would be card to card money transfer…

  3. comment
    Comment #48104809

    why not cursor? cursor seems pretty decent at what it does and i have had very few issues since i started using it about a couple of months back. But yes, frontend burns through to…

  4. comment
    Comment #48094326

    I agree. A month back, I was brainstorming ideas with AI a lot, and it took me a while to figure this out: I was essentially outsourcing my thinking. Honestly, I felt extremely dum…

  5. comment
    Comment #47396263

    What makes LLM bias reinforcement worse than a regular echo chamber is the confidence. A friend who agrees with you might say "yeah maybe", an LLM constructs a well-reasoned, autho…

  6. comment
    Comment #47352832

    That’s really interesting. The “one or two examples + good error messages” part feels especially important. It suggests the limiting factor may be less finetuning and more whether …

  7. comment
    Comment #47352465

    This is really interesting, I feel if llms can respond at existing without finetuning, it can be huge.

  8. story
    Discussion: Shared state breaks most distributed multi-agent systems

    I have been building multi agent systems and the hardest part in practice has been shared state once agents are split across processes or services. Retries overwrite things, handof…

  9. story
    Show HN: Ctrl – execution control plane for AI agents

    Agents are starting to take real actions (publish content, trigger workflows, touch prod systems). Ctrl is an execution control plane that sits between agent intent and real-world …

  10. story
    Show HN: MemX – Shared memory for LLM agents

    Hey everyone — I built this and wanted to share as its free to use and might help some of you: https://mem-x.vercel.app GH: https://github.com/MehulG/memX memX is a shared memory l…

  11. story
    Show HN: MemX – Shared memory for LLM agents

    Built memX this weekend; a shared memory layer for coordinating LLM agents. Agents collaborate by reading/writing real-time context; no chat, no orchestrators. Includes pub/sub, sc…