Hacker News new | ask | show | jobs
by jimkleiber 66 days ago
I wonder if this is like when a restaurant introduces a new menu to increase prices.

Is Opus 4.7 that significantly different in quality that it should use that much more in tokens?

I like Claude and Anthropic a lot, and hope it's just some weird quirk in their tokenizer or whatnot, just seems like something changed in the last few weeks and may be going in a less-value-for-money direction, with not much being said about it. But again, could just be some technical glitch.

1 comments

You can't accidentally retrain a model to use a different tokenizer. It changes the input vectors to the model.
I appreciate you saying that, i think sometimes with ai conversations i wade into them without knowing the precise definitions of the terms, I'll try to be more careful next time. Thank you.