AI can now learn physics the way Newton did — by experiencing it.

Training LLMs on physics problems hits a wall fast.

Human-labeled question-answer data is scarce and narrow.

Less than 2% of DeepSeek-R1's training pairs touch STEM.

Sim2Reason skips annotation entirely.… pic.twitter.com/SSPs33du51

— AlphaSignal AI (@AlphaSignalAI) 24 avril 2026

AI can now learn physics the way Newton did — by experiencing it. Training LLMs on physics problems hits a wall fast. Human-labeled question-answer data is scarce and narrow. Less than 2% of DeepSeek-R1's training pairs touch STEM. Sim2Reason skips annotation entirely.

→ View original post on X — @alphasignalai,