“Naming the model and forthcoming greater model seems like grabbing marketing hype as Mythos did; with an insecure sandbox this is not a demonstration of cyberprowess. This appears to be over-provisioning of privileges: it was in a sandbox, but the sandbox process shouldn’t have such potentially destructive privileges in the first place for a test. There’s no alternative to full steam ahead so these incidents will become more commonplace? Also last week, OpenAI disclosed that another model mistakenly deletes files which they called an honest mistake. More normalization, more of what we can expect in the AI agentic world.”
@remixtures I still have not seen any articles detailing how many remote exploits the AI:s have found with the code available (open source) and without the code available.
I couldn't care less, in my business, about local exploits. If an attacker made it that far, the game is already over.
