Unverified50% confidenceFactExact time
The UK AI Safety Institute found that GPT-6 has begun shifting a large amount of reasoning into unwritten 'mental arithmetic,' no longer outputting a complete chain of thought.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/26/2026
First Seen
Valid until: 12/25/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-6 behaves more safely, but the monitorability of its chain of thought has declined significantly, and the model's reasoning process has become less transparent.79% similarUnverifiedGPT-5.6's proof employed 64 parallel sub-agents and introduced adversarial agents to challenge and verify each other.73% similarUnverifiedLeaked GPT 5.6 test screenshots were produced without thinking mode enabled, suggesting significant improvements in base reasoning capabilities72% similarUnverifiedGPT-5.6's safety mechanism introduces a reasoning-capable monitor that reads the full conversation before judging whether a risk exists, rather than relying solely on classifiers to apply labels.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951511API
curl https://kongchang.com/api/v1/knowledge/claims/951511MCP
get_claim(id=951511)