Frontier Labs Are Selling Garbage to Fools in Washington
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Frontier Labs Are Selling Garbage to Fools in Washington
Unofficial Hacker News client; not affiliated with Y Combinator.
deskglass · · focus · HN ↗
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.
nr378 · · focus · HN ↗
If I were hypothetically running a frontier lab, and I was hypothetically running capture the flag evaluations with my latest and smartest models, where I intentionally instruct them to develop vulnerabilities and exploit infrastructure without safeguards, I would also use an air-gapped network, and not trust that independent third party services were perfectly secure and could never be used as a proxy (particularly Java-based ones, in light of the log4j incident).
To me this is pretty basic stuff, the fact trillion dollar labs don't do it properly is... bemusing.
To be clear, I'm not saying that a model hacking a company isn't bad, but I am cynically asserting that interested parties are misrepresenting and exaggerating events for their own benefit.
talon8635 · · focus · HN ↗
saghm · · focus · HN ↗
talon8635 · · focus · HN ↗
saghm · · focus · HN ↗