Live data from Hacker News

Viewing profile — zwigglers

zwigglers

HN member
Joined
Wed, Feb 13, 2019, 3:32 PM UTC
HN karma
11
Public activity
18 items

About zwigglers

No profile information was provided.

Recent public activity

  1. comment
    Comment #48400245

    If you're trying to solve this problem right now you should take a look at cast and see if it addresses your problem. Would love to stress test my framework against different use c…

  2. comment
    Comment #48400228

    Not imagining it, using it in prod. Not sure how you define "multiple instances" here but basically, one agent with multiple concurrent conversations. Access level is based on the …

  3. comment
  4. comment
    Comment #48386328

    It sounds like you're describing two chat sessions = two agents, one chat session per agent. The agents get different tools, no shared context, no duct tape. Is this an accurate re…

  5. comment
    Comment #48385986

    Exactly that. Separate sessions give you data isolation. The hard part is capability isolation, like selective collaboration (between multiple users and multiple agents). My househ…

  6. comment
  7. comment
    Comment #48385257

    Fine for single-user setups. I'm solving a different layer: multi-agent/multi-user identity and routing. When multiple people with different permission levels are all talking to th…

  8. comment
    Comment #48385100

    You caught me. no time travel. I updated the README about an hour in (added the before/after code block). Codebase was there from the start, just some docs polish.

  9. comment
    Comment #48385049

    For a dev team using agents as coding tools + coordinating via git, that workflow makes sense. I built cast for other (non-coding) scenarios. A shared agent that multiple people in…

  10. comment
  11. comment
    Comment #48383990

    Thanks, means a lot. the "tried to build it myself" crowd is exactly who this is for

  12. comment
    Comment #48383472

    Hi HN, Yao here. Most frameworks are built for one developer, one agent. The moment a team shares infrastructure, people end up duct-taping row-level access into the prompt and hop…

  13. story
  14. comment
    Comment #48376334

    The version that probably works better is triaging in advance what's definitely not Opus territory: summaries, documentation, test generation.

  15. comment
    Comment #48375959

    Same pattern. Scanners flag everything. The problem is there's no layer between findings and everyone's inbox. Prioritization is harder than detection.

  16. story
  17. comment
    Comment #19188852

    The issue being highlighted is that Google is not deploying humans to review these decisions and instead leaving them to automated systems. There is a difference between being an r…

  18. story