I specialize in regulatory affairs for Software as a Medical Device and hope to work in AI risk-mitigation. I enjoy studying machine learning and math, trying to keep up with capabilities research, reading fantasy, sci-fi and horror, and spending time with my family.
Dwarkesh's interview with Sholto sounds well worth watching in full, but the segments you've highlighted and your analyses are very helpful on their own. Thanks for the time and thought you put into this comment!
I like this post, and I think I get why the focus is on generative models.
What's an example of a model organism training setup involving some other kind of model?
Maybe relatively safe if:
Here are some resources I use to keep track of technical research that might be alignment-relevant:
How I gain value: These resources help me notice where my understanding breaks down i.e. what I might want to study, and they get thought-provoking research on my radar.
I'm very glad to have read this post and "Reward is not the optimization target". I hope you continue to write "How not to think about [thing] posts", as they have me nailed. Strong upvote.
Thanks for pointing me to these tools!
I believe that by the time an AI has fully completed the transition to hard superintelligence
Nate, what is meant by "hard" superintelligence, and what would precede it? A "giant kludgey mess" that is nonetheless superintelligent? If you've previously written about this transition, I'd like to read more.
I'm struggling to understand how to think about reward. It sounds like if a hypothetical ML model does reward hacking or reward tampering, it would be because the training process selected for that behavior, not because the model is out to "get reward"; it wouldn't be out to get anything at all. Is that correct?
What are the best not-Arxiv and not-NeurIPS sources of information on new capabilities research?
Thanks for this answer! Interesting. It sounds like the process may be less systematized than how I imagined it to be.