| ▲ | monsieurbanana a day ago | |||||||
In which case the model couldn't possibly know that the number was correct. | ||||||||
| ▲ | Me1000 a day ago | parent [-] | |||||||
I'm also confused by that, but it could just be the model being agreeable. I've seen multiple examples posted online though where it's fairly clear that the COT output is not included in subsequent turns. I don't believe Anthropic is public about it (could be wrong), but I know that the Qwen team specifically recommend against including COT tokensfrom previous inferences. | ||||||||
| ||||||||