Live data from Hacker News

Viewing profile — jesse_portal

jesse_portal

HN member
Joined
Thu, Mar 07, 2024, 4:32 PM UTC
HN karma
5
Public activity
16 items

About jesse_portal

No profile information was provided.

Recent public activity

  1. comment
    Comment #48224584

    Yeah 100%. For the reputation we'll have rating. Instead of rating per server/gpu though like vast.ai and clore.ai it will be for the provider, and it will match bond/credit rating…

  2. comment
    Comment #48200001

    I rent and manage GPUs on sites like vast.ai and clore.ai. The prices are all over the place. You will see 5090s from $0.30/hr to $5/hr, plus bandwidth which is set by the gpu owne…

  3. comment
    Comment #48194373

    [flagged]

  4. story
  5. story
  6. story
  7. comment
    Comment #44309717

    Hey Hacker News, I built a simple registry to make it easier to find and share remote MCP servers: https://remote-mcp-servers.com I know there are a lot of MCP server registries, b…

  8. story
  9. comment
    Comment #44248388

    Have been implementing MCP resource support in my app. Took the approach of letting users add resources directly to their current message which adds a snapshot of the resource to t…

  10. story
  11. comment
    Comment #44160490

    Hi HN, Jesse from Portal One here. We all know AI agents get lost or struggle with complex, multi-step tasks. Our article explores a way to make agents more reliable using dynamic …

  12. story
    Dynamic AI agent guidance with a stateful MCP server

    Hi HN, Jesse from Portal One here. We all know AI agents get lost or struggle with complex, multi-step tasks. Our article explores a way to make agents more reliable using dynamic …

  13. comment
    Comment #44043706

    Sharing our experience implementing our production MCP server using OAuth, TypeScript, and the new ProxyOAuthServerProvider class from the MCP SDK. Check out the companion GitHub r…

  14. comment
  15. story
  16. comment
    Comment #39631031

    Yeah, I was also going to recommend litellm. I've been using it for my LLM assistant app and was able to add support for pretty much any model or provider endpoint by switching out…