|
|
|
Stories from August 12, 2025 (UTC)
|
| 1. |
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models [pdf] (arxiv.org) |
|
417 points by SerCe on Aug 12, 2025 | hide | past | pdf | 83 comments
|
|
| 2. |
Training language models to be warm and empathetic makes them less reliable (arxiv.org) |
|
358 points by Cynddl on Aug 12, 2025 | hide | past | pdf | 375 comments
|
|
| 3. |
AI agents fail tasks 70% of the time (arxiv.org) |
|
23 points by JTbane on Aug 12, 2025 | hide | past | pdf | 8 comments
|
|
| 4. |
Capabilities of GPT-5 on Multimodal Medical Reasoning (arxiv.org) |
|
5 points by Anon84 on Aug 12, 2025 | hide | past | pdf | discuss
|
|
| 5. |
SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model (arxiv.org) |
|
2 points by ra7 on Aug 12, 2025 | hide | past | pdf | discuss
|
|
| 6. |
G-Core: A Simple, Scalable and Balanced RLHF Trainer (arxiv.org) |
|
2 points by PaulHoule on Aug 12, 2025 | hide | past | pdf | discuss
|
|
| 7. |
Tricks or Traps? A Deep Dive into RL for LLM Reasoning (arxiv.org) |
|
2 points by elashri on Aug 12, 2025 | hide | past | pdf | discuss
|
|
|
|
