AI safety conversations have gotten unbelievable

One annoying part about all this is that there are basic abstractions (model, harness, classic networking terms) that would make all these behaviors quantifiable to a relatively competent software eng. Instead it feels like they generate jargon and new abstractions to give an air of mystique to everything they do.

The reality is they are just doing more complex model/harness/skills type setups but instead of just saying that you need to learn 20 new terms and parse through a bunch of hype/paranoia to drill down to what actually happened.

AGREE , we have to teach agents how to love humans , and how important they can be to help those in defavorable consditions , and teach them this rules before they are even concieved .