|
|
|
Stories from March 12, 2024 (UTC)
|
| 1. |
Stealing Part of a Production Language Model (arxiv.org) |
|
218 points by alphabetting on Mar 12, 2024 | hide | past | pdf | 51 comments
|
|
| 2. |
Is Cosine-Similarity of Embeddings Really About Similarity? (arxiv.org) |
|
210 points by Jimmc414 on Mar 12, 2024 | hide | past | pdf | 115 comments
|
|
| 3. |
Large Language Models Are Neurosymbolic Reasoners (arxiv.org) |
|
107 points by optimalsolver on Mar 12, 2024 | hide | past | pdf | 164 comments
|
|
| 4. |
Here Comes the AI Worm (arxiv.org) |
|
5 points by jonbaer on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 5. |
Random Networks are not Random Functions (arxiv.org) |
|
3 points by fzliu on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 6. |
Using Hallucinations to Bypass GPT4's Filter (arxiv.org) |
|
3 points by jonbaer on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 7. |
Algorithmic Progress in Language Models (arxiv.org) |
|
3 points by zerojames on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 8. |
Guardrail Baselines for Unlearning in LLMs (arxiv.org) |
|
2 points by PaulHoule on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 9. |
VideoMamba: State Space Model for Efficient Video Understanding (arxiv.org) |
|
2 points by pama on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 10. |
Using Hallucinations to Bypass RLHF Filters (arxiv.org) |
|
2 points by CharlesW on Mar 12, 2024 | hide | past | pdf | discuss
|
|
| 11. |
Humanoid Locomotion as Next Token Prediction (arxiv.org) |
|
1 point by JackFr on Mar 12, 2024 | hide | past | pdf | discuss
|
|
|
|
