Made mouth rendering faithful to model output — 1.2M tokens

Made mouth rendering faithful to model output

aai

FULL SEND

6.2x your typical session

1.2M tokens vs typical 187.4K

1.2Mtokens

24prompts

39:00:11time

454lines

Claude Codeclaude-fable-5Python$63.82

mostly building

Removed manual exaggeration so mouth rendering now accurately shows the model's actual predictions.

Tokens / prompt48.1k

Cost / line$0.141

Cache hit98%

Burn rate$1.64/hr

Derived from this session's token and cost data. Not shown on the feed.

Building 64%Verifying 24%Thinking 13%