(((ل()(ل() 'yoav))))👾(@yoavgo):so: - any task/environment that you can score reliably and invest enough money (= an obscene amount) in bruteforcing its training, will be solved - every challenging and popular benchmark will meet this bar - abilities won't necessarily transfer how can we measure progress?

2026.09.04 06:53

so: - any task/environment that you can score reliably and invest enough money (= an obscene amount) in bruteforcing its training, will be solved - every challenging and popular benchmark will meet this bar - abilities won't necessarily transfer how can we measure progress?