@d_model_ai We're working directly with frontier-lab researchers to do this work with bleeding-edge models.
We expect to produce many more blog posts like this as our research program grows symbiotically with our RL-env work.
And we're hiring :)
https://t.co/GVBxLeCFCZ
I've shifted my research to focus on automated alignment research. We will have automated AI research very soon and it's important that alignment can keep up during the intelligence explosion.
I'm doing research @d_model_ai now! Very excited about the team and mission. We're teaching computers to teach computers to teach computers to be good people.
@TheZvi Good at fiction writing and surprisingly eager to do it, without the self-conscious Assistant breaking the fourth wall all the time. Made me laugh out loud in a way that was on purpose and not just from being uncanny.