about
211. Harness-of-Harness: Multi-day autonomous software development (arxiv.org)
1 point by fourfire 28 days ago | hide | past | pdf | discuss
212. Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure (arxiv.org)
1 point by sbulaev 29 days ago | hide | past | pdf | discuss
213. Language Models Need Inductive Biases to Count Inductively (2024) (arxiv.org)
1 point by wslh 29 days ago | hide | past | pdf | discuss
214. Language Models Can Control Their Own Attention (arxiv.org)
1 point by Anon84 29 days ago | hide | past | pdf | discuss