Post #4107677
2026-07-23 10:43 UTC
@jcoglan@mastodon.social Kind of. It wasn't totally isolated from the Internet but had a "a curated allowlist that permits routine package installation". The AI got past the allowlist, and then successfully attacked an external company. It's still potentially worrying, even if only because more people are likely to be running poorly-isolated hacking AIs. https://simonwillison.net/2026/Jul/22/openai-cyberattack/
Replies (2)
-
@jcoglan@mastodon.social 2026-07-23 10:54
@TheoEsc@mastodon.social ok but that means they found a bug in the firewall, not that the AI "disobeyed its instructions" which is the framing of these types of stories, and one which makes no sense at a conceptual level
-
@shaknais@mastodon.social 2026-07-23 11:10
@TheoEsc@mastodon.social "got passed the allowlist" still means it had access to arbitrarily execute code. And arbitrary code execution leads to... Arbitrary code execution.