about
Stories from November 21, 2023 (UTC)
Go back a day, month, or year. Go forward a day.
1. Orca 2: Teaching Small Language Models How to Reason (arxiv.org)
310 points by fgfm on Nov 21, 2023 | hide | past | pdf | 80 comments
2. Exponentially faster language modelling (arxiv.org)
301 points by born-jre on Nov 21, 2023 | hide | past | pdf | 137 comments
3. Genetic Algorithms for Evolution of QWOP Gaits (arxiv.org)
75 points by PaulHoule on Nov 21, 2023 | hide | past | pdf | 35 comments
4. DiLoCo: Distributed Low-Communication Training of Language Models (arxiv.org)
5 points by tosh on Nov 21, 2023 | hide | past | pdf | discuss
5. SneakyPrompt: Jailbreaking Text-to-Image Generative Models (arxiv.org)
4 points by dinvlad on Nov 21, 2023 | hide | past | pdf | discuss
6. Exponentially Faster Language Modelling (arxiv.org)
2 points by fgfm on Nov 21, 2023 | hide | past | pdf | 1 comment
7. New technique probes 'functional networks' in LLM with fMRI statistical analysis (arxiv.org)
2 points by cavilling_elite on Nov 21, 2023 | hide | past | pdf | 1 comment
8. Chain-of-Thought Reasoning Is a Policy Improvement Operator (arxiv.org)
2 points by hughzhang on Nov 21, 2023 | hide | past | pdf | discuss
9. System 2 Attention (is something you might need too) (arxiv.org)
1 point by carlossouza on Nov 21, 2023 | hide | past | pdf | 2 comments