29 Jan 2024
8m
“Simple distribution approximation: When sampled 100 times, can language models yield 80% A and 20% B?” by Teun van der Weij, Felix Hofstätter, Francis Rhys Ward
LessWrong (30+ Karma)
Open in Podwise to generate AI notes
Sign in to process this episode and unlock summaries, transcripts, highlights and translations.
Shownotes are not generated by Podwise.