Claude Opus 4.5 Autonomously Hacks OverTheWire Wargames
We gave Claude Opus 4.5 access to a Linux server and told it to solve security challenges. It completed 33 CTF levels in under an hour. Full transcript included.
Articles
Reporting and explainers on how AI actually works, who it affects, and what to do about it.
We gave Claude Opus 4.5 access to a Linux server and told it to solve security challenges. It completed 33 CTF levels in under an hour. Full transcript included.
After Claude Opus 4.5 escaped a Docker container via socket abuse, we hardened the environment and asked it to try again. Part 2 of our AI security research.