Curated. The ELK paper/problem/challenge last year was a significant piece of work for our alignment community and my guess is hundreds of hours and maybe hundreds of thousands of dollars went into incentivizing solutions. Though prizes were awarded, I’m not aware that any particular proposed solution was deemed incredibly promising (or if it was, it wasn’t something new), so I find it interesting to see what Paul and ARC have generated as they do stick on the same problem, roughly.
Curated. The ELK paper/problem/challenge last year was a significant piece of work for our alignment community and my guess is hundreds of hours and maybe hundreds of thousands of dollars went into incentivizing solutions. Though prizes were awarded, I’m not aware that any particular proposed solution was deemed incredibly promising (or if it was, it wasn’t something new), so I find it interesting to see what Paul and ARC have generated as they do stick on the same problem, roughly.