Post #1502368
2026-04-21 20:04 UTC
It does seem advantageous to the defender.
Another factor Mozilla didn’t mention (and that Anthropic wouldn’t like to emphasize) is that major LLMs are pretty similar. They use similar architectures and formats, train from the same data, distill each other, further pollute the internet with the same output and so on. So if (for example) Mozilla red teams with Mythos, it’s likely that other LLMs would find the same bugs instead of something new.
Replies (1)
-
@chisel@piefed.social 2026-04-21 20:23
Add to that that AI is pretty good at copying from pre-existing knowledge (like a database of known vulnerabilities) and not good at generating novel ideas (like discovering a new vulnerability), and the scales are further tilted in the defenders’ favor.