The reasoning modes are really weird with 4.7 In my tests, asking for "none" rea... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		XCSme 19 hours ago \| parent \| context \| favorite \| on: Claude Opus 4.7 The reasoning modes are really weird with 4.7 In my tests, asking for "none" reasoning resulted in higher costs than asking for "medium" reasoning... Also, "medium" reasoning only had 1/10 of the reasoning tokens 4.6 used to have.

		help

XCSme 19 hours ago | [–]

Oh, and also, the "none" and "medium" variants performed the same (??)

nisarg2 16 hours ago | | [–]

Insane! Even Haiku doesn't make such mistakes.

XCSme 9 hours ago | | [–]

I am not sure it's a mistake, this might be their new "adaptive reasoning" + hidden reasoning trace, so we can't verify.

amelius 12 hours ago | [–]

Claude is known for its shitty metering.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact