about
Stories from October 22, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. The alien space of science: Coherent but cognitively unavailable directions (arxiv.org)
214 points by martincsweiss 26 days ago | hide | past | pdf | 89 comments
2. Why is AI-generated language so hard to understand? (arxiv.org)
4 points by ersinesen 26 days ago | hide | past | pdf | discuss
3. Team of Gemini 4 Argon agents beats Minecraft (arxiv.org)
2 points by taylorbuley 26 days ago | hide | past | pdf | discuss
4. Every Time I Hire a Linguist, Inference Costs Go Down (arxiv.org)
2 points by surprisetalk 26 days ago | hide | past | pdf | discuss
5. Language models transmit behavioral traits via hidden signals in data (arxiv.org)
2 points by convict 26 days ago | hide | past | pdf | discuss
6. Compaction Laundering:Provenance Destruction in Context-Compacting Coding Agents (arxiv.org)
2 points by ersinesen 26 days ago | hide | past | pdf | discuss
7. How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? (arxiv.org)
2 points by brazukadev 27 days ago | hide | past | pdf | discuss
8. XYEval: Agents say yes to bad advice (arxiv.org)
2 points by xnx 27 days ago | hide | past | pdf | discuss
9. TorchTPU: Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU (arxiv.org)
1 point by matt_d 26 days ago | hide | past | pdf | 1 comment
10. Why are all LLMs Obsessed with Japanese Culture? [pdf] (arxiv.org)
1 point by thinkingemote 26 days ago | hide | past | pdf | discuss