Epistemic status: I don't fully endorse all this, but I think it's a pretty major mistake to not at least have a model like this sandboxed in one's head and check it regularly.
Full-cynical model of the AI safety ecosystem right now:
… and of course none of that means that LLMs won’t reach supercritical self-improvement, or that AI won’t kill us, or [...]. Indeed, absent the very real risk of extinction, I’d ignore all this fakery and go about my business elsewhere. I wouldn’t be happy about it, but it wouldn’t bother me any more than all the (many) other basically-fake fields out there.
Man, I really just wish everything wasn’t fake all the time.
The latter, especially, I thought was popularized because it was so surprisingly good at improving benchmark performance.
Inner-monologue is an example because as far as we know, it should have existed in pre-GPT-3 models and been constantly improving, but we wouldn't have noticed because no one would have been prompting for it and if they had, they probably wouldn't have noticed it. (The paper I linked might have demonstrated that by finding nontrivial performance in smaller models.) Only once it became fairly reliable in GPT-3 could hobbyists on 4chan ... (read more)