Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Tim Becker Profile picture
Tim Becker
@tjbecker_
Security Researcher at @theori_io. Flag capturer at @PlaidCTF. Cryptography enjoyer.
Aug 14 • 6 tweets • 2 min read
The previous thread glossed over how our LLM Agents actually work.

The truth is, it took us a long time to figure out how to get reliable and impressive results from agents.

By the end, we learned general strategies to build effective LLM agents, which we're now sharing. 🧵 Strategy #1: Decompose the task

LLM agents excel at tasks generally requiring human intuition to solve, but they can't yet solve arbitrarily complex multi-step tasks. If the task can be solved in multiple parts, you should decompose it as a workflow of multiple agents.
Aug 13 • 9 tweets • 2 min read
@theori_io's AIxCC CRS has already found dozens of 0day vulnerabilities, and we've barely scratched the surface! The best part: it's open source, so there's no secrets to hide (at least in the AIxCC version 😉)!

So, how does our CRS actually find these 0days? 🧵 We start by passing every function in the source code into LLMs, asking them to consider a wide-range of vulnerability classes and explicitly accept/reject each class. We also run off-the-shelf static analyzers.

Combined, we end up with 10k+ candidate vulns for each project.