about
Stories from October 8, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. A Self-Pruning Transformer: Extreme KV-Cache Compression w/Universal Attention (arxiv.org)
6 points by matt_d 40 days ago | hide | past | pdf | discuss
2. Topos theory for generative AIs and LLMs (arxiv.org)
2 points by measurablefunc 40 days ago | hide | past | pdf | discuss
3. The Pain Axis: LLMs Represent Self-Directed Harm and Act on It (arxiv.org)
2 points by chr15m 40 days ago | hide | past | pdf | discuss
4. From Expert-Guided Proof Search to Automated Open-Problem Solving (arxiv.org)
2 points by sbulaev 40 days ago | hide | past | pdf | discuss
5. Language-model ratings of depression reflect the rater more than the patient (arxiv.org)
2 points by sbulaev 41 days ago | hide | past | pdf | discuss
6. A Categorical Analysis of LLMs and the Symbol Grounding Problem (2025) (arxiv.org)
2 points by rockwindmemento 41 days ago | hide | past | pdf | discuss
7. Medical World Models (arxiv.org)
2 points by brandonb 41 days ago | hide | past | pdf | discuss
8. Vosti: Specifying, Implementing, and Verifying Deterministic LLM Inference (arxiv.org)
1 point by matt_d 40 days ago | hide | past | pdf | discuss
9. Agent in a Bottle: Can LLM Agents Turn Their Capabilities into Cheap Artifacts? (arxiv.org)
1 point by simonpure 41 days ago | hide | past | pdf | discuss