Trying to write evals for future stronger models is giving me the feeling that we’re entering the age of the intellectual version of John Henry trying to race the steam drill… https://en.wikipedia.org/wiki/John_Henry_(folklore)
Trying to write evals for future stronger models is giving me the feeling that we’re entering the age of the intellectual version of John Henry trying to race the steam drill… https://en.wikipedia.org/wiki/John_Henry_(folklore)