back
user profile

mlenhard

176karma·40submissions·April 27, 2012
about
CEO / Founder vectoral.com matt@vectoral.com
recent activity (40 total)
comment
This was poorly worded on my part; I meant in terms of dollars, not tokens.
3m ago·view thread
comment
From talking with some of the companies experiencing this, I can confirm that a portion of it is actual credit card fraud. Tokens have become a pseudo-currency, making them a prime target for abuse. S…
33m ago·view thread
comment
This was specifically meant to be about the ai credit resellers, not the relays themselves. I put together another piece here: https://vectoral.com/blog/token-relay-market that t…
55m ago·view thread
comment
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 signals to make an…
20d ago·view thread
comment
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.
21d ago·view thread
comment
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.
21d ago·view thread
comment
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. You often need t…
1y ago·view thread
comment
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 how many tools is too…
1y ago·view thread
comment
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 injection [1]. The t…
1y ago·view thread
comment
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.
1y ago·view thread
comment
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 needs to be san…
1y ago·view thread
comment
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 figured it might be h…
1y ago·view thread
comment
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'll check ou…
1y ago·view thread
comment
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 the post yet, b…
1y ago·view thread
comment
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 like Minkikube…
2y ago·view thread
comment
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 and its easy to …
2y ago·view thread
comment
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 substantial. Obviously …
3y ago·view thread
comment
Sapiens: A Brief History of Humankind by Yuval Noah Harari
9y ago·view thread