Anthropic summarizes the thinking blocks past the first ~500 tokens. See the section titled Differences in thinking across model versions.
Yeah, these are the outputs from a single prompt exchange and the token length wasn’t sufficient to produce summary blocks, furthermore aren’t the summary blocks supposed to be signed as well? https://platform.claude.com/docs/en/build-with-claude/extended-thinking#thinking-encryptionSomething doesn’t add up for me.
Anthropic summarizes the thinking blocks past the first ~500 tokens. See the section titled Differences in thinking across model versions.
Yeah, these are the outputs from a single prompt exchange and the token length wasn’t sufficient to produce summary blocks, furthermore aren’t the summary blocks supposed to be signed as well?
https://platform.claude.com/docs/en/build-with-claude/extended-thinking#thinking-encryption
Something doesn’t add up for me.