News for hackers. Stuff that matters.

A comment on Qwen3: Think deeper, act faster. Parent comment

Re:Qwen3: Think deeper, act faster by nopinsight on Tuesday April 29, 2025 @01:34AM (#43828967)
Current models are quite far away from human-level physical reasoning (paper below). An upcoming version of models trained on world simulation will probably do much better.

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

https://phybench-official.github.io/phybench-demo/

[ Parent | on HN ]
Re:Qwen3: Think deeper, act faster by horhay on Tuesday April 29, 2025 @06:30AM (#43830750)
This is more about a physics math aptitude test. You can already see that the best model in math is saturating it halfway. It might not indicate its usefulness in actual physical reasoning, or at the very least, it seems like a bit of a stretch.
[ Parent | on HN ]