Thanks for your thoughts and concerns! We’ve updated the blog post to address some of them. The most important changes involve adding nuance to language and being explicit everywhere that our measure of incoherence refers to the relative contribution of variance to error, and is separate from how overall error changes with model capability, or how self-consistent successful trajectories are.
The blog post was put together much more hastily than the paper. Probably a lot more cumulative effort will go into reading the blog than the paper, so this is the... (read more)
Thanks for your thoughts and concerns! We’ve updated the blog post to address some of them. The most important changes involve adding nuance to language and being explicit everywhere that our measure of incoherence refers to the relative contribution of variance to error, and is separate from how overall error changes with model capability, or how self-consistent successful trajectories are.
The blog post was put together much more hastily than the paper. Probably a lot more cumulative effort will go into reading the blog than the paper, so this is the... (read more)