Live data from Hacker News

Viewing profile — mlenhard

mlenhard

HN member
Joined
Fri, Apr 27, 2012, 4:23 AM UTC
HN karma
125
Public activity
35 items

About mlenhard

CEO / Founder vectoral.com matt@vectoral.com

Recent public activity

  1. comment
    Comment #49061107

    I don't think device fingerprinting is the right approach here. Client-side detection can always be sidestepped, and you need to intermediate the actual inference to get enough sig…

  2. comment
    Comment #49060260

    I was going to cover this in a follow-up article, but yeah, there are network of token brokers who buy unused credits from startups and then resell them.

  3. comment
    Comment #49059528

    Yeah, I should probably clean this up. The sentence is a bit hard to understand. What I was trying to show was the steep discounts offered by resellers.

  4. story
  5. story
  6. story
  7. comment
    Comment #43897514

    I actually came across Plandex the other day. I haven't had the chance to play around with it yet, but it looked really cool. But agree that even basic prompts can be a struggle. Y…

  8. comment
    Comment #43897235

    Agree on the unpredictability of results issue. Tool call selection is still sort of a black box. How do you know what variations of a prompt trigger a given tool to be called or h…

  9. story
  10. story
    Show HN: Open-source load balancer for distributed MCP server architecture

    Like many others, I’ve been hacking on MCP servers lately. The issue I ran into was that running multiple MCP servers behind a unified backend was hard. I needed a way to combine a…

  11. comment
    Comment #43691333

    This is pretty cool. You should also attempt to scan resources if possible. Similar to the tool injection attack Invariant Labs discovered, I achieved the same result via resource …

  12. comment
    Comment #43680675

    Yeah, you aren't far off with SQL injection comparison. That being said it's not really a fault of the MCP spec, more so with current client implementations of it.

  13. comment
    Comment #43680550

    One of the biggest issues I see, briefly discussed here, is how one MCP server tool's output can affect other tools later in the same message thread. To prevent this, there really …

  14. story
  15. comment
    Comment #43642957

    Yeah, I plan on improving the formatting and adding a few more examples. There were even still some typos in the piece. To be honest, I didn't plan on sharing it yet; I just figure…

  16. comment
    Comment #43633880

    Yeah, at its core it's just a proxy, so there are a lot of other tools out there that would do the job. It does have a nice UI and I try to support projects like it when I can. I'l…

  17. comment
    Comment #43633160

    I was in the same boat in regards to trying to find the actual JSON that was going over the wire. I ended up using Charles to capture all the network requests. I haven't finished t…

  18. comment
    Comment #39907383

    super cool. Debugging locally across multiple microservices can be a huge pain. A small feature request/idea - packaging this as a helm chart to make local development on something…

  19. comment
    Comment #37577516

    Congrats on the 1.0 Release, big milestone. I'm personally really excited about all of the recent tooling for postgres aggregates. Definitely a pain point for a lot of developers a…

  20. comment
    Comment #36988274

    Congrats on the launch! For those who have not experimented with columnar based databases, I would highly recommend toying around with them. The performance improvements can be sub…

  21. story
  22. story
  23. comment
    Comment #14859605

    Sapiens: A Brief History of Humankind by Yuval Noah Harari

  24. story
  25. story