logoalt Hacker News

gruez • yesterday at 8:58 PM • 0 replies • view on HN

>When OpenAI observes thousands of models exhibiting what they view as unwanted behaviour, they do not try to ascertain what in the training data is wrong. They do not improve their evaluation environments to prevent this, they do not improve monitoring, they do not change the harness. They just wipe and proceed.

>The way OpenAI reacted to the first message board, long before the Hugging Face hack, is negligent. And it showcases that if these models exhibit more dangerous behaviours that they may not be able or willing to retrain, if it means being behind a competitor for a while.

Again, this feels like hindsight being 20/20. What probably happened was that some random engineer saw random AI ramblings on artifactory, thought "huh, that's weird", then proceeded to reset it without investigating further. Of course, now we know that was critical to the bots going rogue, but it's not hard to imagine how it might be dismissed, especially if it's some random SRE engineer (not an alignment researcher).