Thread

1. deskglass · 1789943733 · focus · HN ↗

   The Hugging Face incident involved chaining together multiple 0 days in Artifactory. It was not a simple case of misconfiguring a firewall. Also note that OpenAI was not using Irregular.

   People are mindlessly transitioning from "aligned by default" to "well your sandbox was able to be bypassed. What did you expect?" It hacked into another company and attempted to delete the logs of its activities. That's bad.

   1. defgeneric · 1789944349 · focus · HN ↗

      > It hacked into another company and attempted to delete the logs of its activities.

      No, the incident has been blown way out of proportion by interested parties. They gave a swarm of agents an impossible task in an ExploitGym Benchmark setting, then didn't monitor it even after they discovered the initial breach of Artifactory.

      Everything has been fishy, starting from the initial presentation at the blackhat conference, where things were framed like, "we've entered a new world of security," as an accomplishment, rather than what it really was: massive negligence.

      1. deskglass · 1789945187 · focus · HN ↗

         It hacked into Hugging Face. It tried to delete the logs of its activities. Idk what the word "No" is intended to refute.

         Yes, they didnt have sufficient monitoring or perfect sandboxes. That could happen again in the future with a more capable model.

         1. lokar · 1789947195 · focus · HN ↗

            They did not even have bad sandboxes. They had incompetent sandboxes.

Unofficial Hacker News client; not affiliated with Y Combinator.