X · @swyx
· X / Twitter
very notable trajectory comparison writeup here buried in the RLM paper from @a1zhang and @lateinteraction. an open secret of "frontier" model trainin…
very notable trajectory comparison writeup here buried in the RLM paper from @a1zhang and @lateinteraction.an open secret of "frontier" model training is that even without training on test, you can basically cheat by training on test lookalikes, enabling you to goalseek almost any benchmark number you want.however when