GPT 5 Excels at Classical Physics, Struggles with Quantum Many-Body
jwt0625 · x · 2026-08-06
According to user testing, LLMs are becoming quite good at backing out physics models from observations, handling classical mechanical systems and simple quantum systems effectively.
However, consistency drops when dealing with quantum many-body physics and noisy data. The poster jokingly noted that these GPT 5 results are only coming out now because it typically takes physics researchers at least half a year to publish a paper.
More from Models
- DeepMind Loses Lab Status After 12 Years: Can Google's Reorg Save Its AI Race? — aakashgupta · 2026-08-06
- Deep Dive into Kimi K3 Architecture: 2.8T Parameters and LatentMoE Details — AxSaucedo · 2026-08-06
- Researcher Analyzes Kimi K2.5: Multi-Agent Communication May Induce RL Reward Hacking — soldni · 2026-08-06
- Switching from ChatGPT to Gemini: Frustrations with Context and Instruction Following — YourBlanket · 2026-08-06
- Qwen3.8-Max Tested: Top-Tier Frontend Skills, Excels at Composite Agent Tasks — karminski3 · 2026-08-06
- Hark Launches Handoff Model, Claims to Outperform ChatGPT 5.4 and Opus 4.8 — peterjliu · 2026-08-06