 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from February 11, 2026 (UTC)
|
| 1. | Misconduct in Post-Selections and Deep Learning (2024) (arxiv.org) |
| 3 points by bjourne 235 days ago | hide | past | pdf | discuss | |
| 2. | GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt [pdf] (arxiv.org) |
| 2 points by janandonly 235 days ago | hide | past | pdf | discuss | |
| 3. | Attention Sinks and Compression Valleys in LLMs (arxiv.org) |
| 1 point by alexkranias 235 days ago | hide | past | pdf | discuss | |
| 4. | The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence (arxiv.org) |
| 1 point by schmuhblaster 235 days ago | hide | past | pdf | discuss | |
| 5. | Harmless reward hacks generalize to shutdown evasion and dictatorship in GPT-4.1 (arxiv.org) |
| 1 point by toliveistobuild 235 days ago | hide | past | pdf | 1 comment | |