> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# Large Language Models Fail at Reproducing Physics Experiments
- URL: https://adjacent.media/signals/large-language-models-fail-at-reproducing-physics-experiments/
- Published: 2026-04-27T16:03:11.000Z
- Updated: 2026-04-27T16:03:11.000Z
- Description: A Peking University preprint tested whether LLMs can replicate experimental physics results. They can’t. The models fail at the sequential reasoning and precision measurement interpretation that physics requires.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, AI & ML

Source: [LessWrong](https://www.lesswrong.com/posts/c4Kopt4bY3ZbMdshJ/ai-is-bad-at-physics?ref=adjacent.media)

A Peking University preprint tested whether LLMs can replicate experimental physics results. They can't. The models fail at the sequential reasoning and precision measurement interpretation that physics requires. This exposes a gap between LLMs' fluency at pattern-matching text and their inability to ground abstract knowledge in verifiable physical outcomes—a problem that affects scientific peer review and AI agents making real-world decisions. The finding suggests that scaling parameters alone won't close this gap. Models may need different training approaches that reward reproducibility and constraint-satisfaction rather than plausible-sounding next tokens.