← Back to context Comment by bryan0 1 year ago Yes but these were steps were not used in R1-zero where its reasoning capabilities were trained. 2 comments bryan0 Reply littlestymaar 1 year ago And as a result R1-zero is way too crude to be used directly, which is a good indication that it remains relevant.
littlestymaar 1 year ago And as a result R1-zero is way too crude to be used directly, which is a good indication that it remains relevant.
And as a result R1-zero is way too crude to be used directly, which is a good indication that it remains relevant.