Post #4031894

2026-07-23 08:16 UTC

this story about openai "breaking containment" is such bullshit if you know anything about how computer security is supposed to be done. if a program accesses a remote system it's because you decided to let it do that. LLMs don't have magical powers that can work around "we unplugged the ethernet"

Replies (4)

@jcoglan@mastodon.social 2026-07-23 08:20

if your "containment" is "telling the robot to be a good boy" you're not a serious person

Open ##4031893
@wim_v12e@scholar.social 2026-07-23 10:10

@jcoglan@mastodon.social Running in a chroot or container or VM is no substitute for airgapping the computer.

Open ##4107676
@TheoEsc@mastodon.social 2026-07-23 10:43

@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/

Open ##4107677
@patrickleavy@mastodon.social 2026-07-23 11:12

@jcoglan@mastodon.social yes it was bullshit - just hype for their latest fund raise, which was announced two days later (today): https://londondaily.com/openai-secures-40-billion-funding-reaches-300-billion-valuation #AI is such a pump n dump.

Open ##4108052