TheoWe scan every video for X posts on screen, then check the transcript to see if they were read aloud. See everything Theo showed.
Every post with your handle on screen. A profile or post link works too.
Matches the text of one post, even if the handle was cropped out.
A few words you remember. Matches by words and by meaning.
@lydiahallie
Theo showed your posts 2 times and read every one aloud.
If you're on API billing, you can set Haiku 5.5's autocompact window to 100K so you stay in the cheaper token pricing tier! It's saved per model so this only applies to Haiku (incl. subagents) > /model haiku > /autocompact 100k
employees like Lydia have come out publicly and said, "If you want to keep your bill cheap and not worry about this, you can manually set Haiku 5.5's auto compact window to 100k so that you're always working within that cheaper token pricing.
Switching effort mid-session on Opus 5.5 doesn't break your prompt cache btw! Just make sure you're on Claude Code v2.1.280+ ^ doesn't apply on Bedrock/Vertex though 🧘🏼♀️ Same as Fable 5.1
This sounds like a silly thing to care about, but it means that you would bust cash whenever you changed your reasoning levels, which isn't great.
