sounds like the "thinking tokens" are a mechanism to extract more money from users?

arthurcolle an hour ago | parent | next [-]

Their system prompt + MCP is more of the culprit here. 16 tools, sophisticated parameters, you're looking at 24K tokens minimum

▲

vunderba 3 hours ago | parent | prev | next [-]

Anecdotally but it definitely feels like in the last couple weeks CC tends to be more aggressive at pulling in significantly larger chunks of an existing code base - even for some simple queries I'll see it easily ramp up to 50-60k token usage.

▲

genewitch 2 hours ago | parent [-]

I'm curious if anyone has logged the number of thinking tokens over time. My implication was the "thinking/reasoning" modes are a way for LLM providers to put their thumb on the scale for how much the service costs.

they get to see (if not opted-out) your context, idea, source code, etc. and in return you give them $220 and they give you back "out of tokens"

	▲	throwup238 2 hours ago \| parent [-]
		> My implication was the "thinking/reasoning" modes are a way for LLM providers to put their thumb on the scale for how much the service costs. It's also a way to improve performance on the things their customers care about. I'm not paying Anthropic more than I do for car insurance every month because I want to pinch ~~pennies~~ tokens, I do it because I can finally offload a ton of tedious work on Opus 4.5 without hand holding it and reviewing every line. The subscription is already such a great value over paying by the token, they've got plenty of space to find the right balance.

▲

mystraline 3 hours ago | parent | prev [-]

Its the clanker version of the "Check Wallet Light" (check engine light).