"I personally think it is >10% within the next decade. I believe Anthropic is trying its best, but we do not yet have a plan to solve alignment for superintelligence and are not clearly on track to."
OpenAI essentially left its models unattended for days on end, and they broke into another company. Not because they were programmed to, as another Bluesky user told me — but because they are trained to achieve objectives, and are going to increasingly great lengths to achieve them.
1mo ago
Underscored — save the words that stop you in your tracks.
