Live data from Hacker News

Viewing profile — rjpruitt16

rjpruitt16

HN member
Joined
Wed, Aug 14, 2024, 8:32 PM UTC
HN karma
9
Public activity
37 items

About rjpruitt16

No profile information was provided.

Recent public activity

  1. story
  2. story
    Ask HN: How many AI agents do you actively use?

    I have around four for talking through ideas and three active coding agents. None of them are truly long-running. Is that typical? How many agents are you using regularly, and are …

  3. story
  4. story
  5. comment
    Comment #48392319

    [flagged]

  6. story
  7. comment
    Comment #48358581

    I have been working on open source traffic shaper for agents. I think it may help you better with prediction if requests don’t stampede you https://www.linkedin.com/posts/rahmi-pru…

  8. story
  9. story
  10. story
  11. story
  12. comment
    Comment #47982637

    Location: Memphis, TN (open to remote US) Remote: Yes Willing to relocate: Yes Technologies: Elixir (BEAM/OTP), Go, Python, Java, TypeScript, React, AWS (Lambda, SQS, DynamoDB, Kin…

  13. comment
    Comment #47978013

    I’m curious if you are looking into gleam at all. I have written elixir/gleam interop otp library. Probably will help a lot for safety in finance. I could help turn certain compone…

  14. comment
    Comment #47859071

    Yeah, thanks for checking it out. I know it’s a lot read. Keep me in mind if you run retry storms for agents.

  15. story
  16. comment
    Comment #47830731

    Where do you think AI web agents with be by 2027? How are people creating value today? Where will browsers use be at the end of the year?

  17. story
  18. comment
    Comment #47753251

    An api rate limit router - it’s gives a queue per user to solve noisy neighbors, it allows the user user to reroute 500s to other regions automatically, the api provider can tune t…

  19. comment
    Comment #47655698

    Ezthrottle works by sending the request and depending on what error code the user wishes to reroute on, it will send to another region. It give the user a chance to say something d…

  20. comment
    Comment #47498787

    Cool stuff.

  21. comment
    Comment #47434561

    Thanks for this. I was in the camp of trust the LLM but y’all have made valid points. After discussing with ChatGPT, it agree there are some areas where it should not be trusted as…

  22. comment
    Comment #47337359

    What do you use?

  23. comment
    Comment #47317981

    Im curious if you guys are seeing rate limiting issues. Agents sharing api keys tend to be retry storm monsters. I wonder how agent companies will address

  24. story
    Ask HN: How to scale agent systems when Layer 7 is unreliable?

    Agent workflows often involve 10+ API calls to different services (LLMs, data APIs, web scraping). Layer 7 being unreliable = workflows fail or cause retry storms. Common failure m…

  25. comment
    Comment #47147315

    interesting. What type of features did this enable. How was it maintaining redis. How many queues did you have.