I expect this is a rare moment of clarity because maintaining updates takes a lot of effort and is now subject to optimization pressure.
Also imo most of the “good” alignment work in terms of eventual impact is being done outside the alignment label (eg as differential geometry or control theory) and will be merged in later once the connection is recognized. Probably this will continue to become more true over time.
can you say more about what makes you think that? I’m hoping to get recommendations out of it. I also expect to disagree that the work they’re doing weighs directly on the problem.
Thanks for making this map 🙏
I expect this is a rare moment of clarity because maintaining updates takes a lot of effort and is now subject to optimization pressure.
Also imo most of the “good” alignment work in terms of eventual impact is being done outside the alignment label (eg as differential geometry or control theory) and will be merged in later once the connection is recognized. Probably this will continue to become more true over time.
can you say more about what makes you think that? I’m hoping to get recommendations out of it. I also expect to disagree that the work they’re doing weighs directly on the problem.
Not speaking for him, but for a tiny sample of what else is out there, ctrl+F “ordinary”