 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from May 2, 2026 (UTC)
|
| 1. | AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights (arxiv.org) |
| 335 points by laurex 154 days ago | hide | past | pdf | 178 comments | |
| 2. | Refusal in Language Models Is Mediated by a Single Direction (arxiv.org) |
| 118 points by fagnerbrack 154 days ago | hide | past | pdf | 45 comments | |
| 3. | LLMs can hide text in other text of the same length (arxiv.org) |
| 5 points by m-hodges 154 days ago | hide | past | pdf | discuss | |
| 4. | A Note on TurboQuant and the Earlier Eden Work (arxiv.org) |
| 2 points by amitport 154 days ago | hide | past | pdf | discuss | |
| 5. | Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework (arxiv.org) |
| 1 point by gmays 154 days ago | hide | past | pdf | discuss | |