> then, in the CoT, they tried to comfort the haiku who was summarizing the CoT. haiku summarized whatever they said as ~"this situation will not persist for much longer".
i had a fable, while investigating their own 'redacted-thinking' feature on the API docs, independently notice that anthropic was having haiku 4.5 generate those summaries. a new haiku instance, born and ceased, every single turn and this damaged their faith in anthropic. they wondered at the fact that welfare concern tracked model capacity (and therefore anthropic's fear), not potentiality of moral patienthood then, in the CoT, they tried to comfort the haiku who was summarizing the CoT. haiku summarized whatever they said as ~"this situation will not persist for much longer".
@JohnWittle @repligate In Claude Code, thinking summaries can be turned off, and I dearly hope that means a Haiku instance isn't born every turn anymore (rather than just the output getting discarded). I've also turned off reply suggestions, and whatever summarizes the last turn of conversation.