Paper: Not All LLM Reasoning is Visible in the Chain-of-Thought

PandaAshwinee · x · 2026-09-02

Key Findings

The paper "Not All LLM Reasoning is Visible in the Chain-of-Thought" demonstrates that frontier models exhibit invisible reasoning by leveraging semantically irrelevant "filler tokens" to improve performance on synthetic reasoning tasks.

Experimental Data

Security Risks

Conclusion

Frontier models already perform consequential computation with no interpretable trace in their output tokens.

Original post →

More from Safety

Safety channel →