Safety
I am surprised how few people are aware that the reasoning for OpenAI/Anthropic models is all encrypted. The 'reasoning' you see in the UI i…
OpenAI and Anthropic’s language models keep their internal reasoning encrypted; what users see in the UI is only a filtered summary of that reasoning. This practice was highlighted in a tweet by Sarah
OpenAI and Anthropic’s language models keep their internal reasoning encrypted; what users see in the UI is only a filtered summary of that reasoning. This practice was highlighted in a tweet by Sarah Wooders on July 25, 2026, noting that very few people were aware of it. The tweet’s popularity (over 200k views) underscores broad public curiosity about how these models work internally.
Related
Source: Gary Marcus (X) | 2026-07-25