Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Measuring Claude 4.7's tokenizer costs

claudecodecamp.com

Post reply on HN
Print view View original

101–110 of 540 posts

Re: Measuring Claude 4.7's tokenizer costs

#101

Post by arcanemachiner »

curioussquirrel wrote: post #51

Claude's tokenizers have actually been getting less efficient over the years (I think we're at the third iteration at the least since Sonnet 3.5). And if you prompt the LLM in a language other than English, or if your users prompt it or generate content in other languages, the costs go higher even more. And I mean hundreds of percent more for languages with complex scripts like Tamil or Japanese. If you're interested…

I would encourage you to post a link here, and also to submit to HN if you haven't already. :)

Re: Measuring Claude 4.7's tokenizer costs

#104

Post by therobots927 »

As a regular listener of Ed Zitron this comes as absolutely no surprise. Once you understand the levels of obfuscation available to anthro / OAI you will realize that they have almost certainly hit a model plateau ~1 year ago. All benchmark improvements since have come at a high compute cost. And the model used when evaluating said benchmarks is not the same model you get with your subscription.

This is already becoming apparent as users are seeing quality degrade which implies that anthropic is dropping performance across the board to minimize financial losses.

Re: Measuring Claude 4.7's tokenizer costs

#105

Post by simplyluke »

_pdp_ wrote: post #29

IMHO there is a point where incremental model quality will hit diminishing returns. It is like comparing an 8K display to a 16K display because at normal viewing distance, the difference is imperceptible, but 16K comes at significant premium. The same applies to intelligence. Sure, some users might register a meaningful bump, but if 99% can't tell the difference in their day-to-day work, does it matter? A 20-30% cost…

I'm seeing a lot of sentiment, and agree with a lot of it, that opus 4.6 un-nerfed is there already and for many if not most software use cases there's more value to be had in tooling, speed, and cost than raw model intelligence.

Re: Measuring Claude 4.7's tokenizer costs

#106

Post by dboreham »

mattkevan wrote: post #83
devmor wrote: post #58

Earlier quoted context omitted.

Skeptical is a light way to put it. It is essentially a forgone conclusion that once a company IPOs, any veil that they might be working for the global good is entirely lifted. A publicly traded company is legally obligated to go against the global good.

It’s not really, companies like GM used to boast about how well they treated their employees and communities. It was Jack Welch and a legion of like-minded arseholes who decided they should be increasingly richer no matter who or what paid for it.

See also HP. Pretty much only Costco left.

Re: Measuring Claude 4.7's tokenizer costs

#108

Post by _pdp_ »

_pdp_ wrote: post #29

IMHO there is a point where incremental model quality will hit diminishing returns. It is like comparing an 8K display to a 16K display because at normal viewing distance, the difference is imperceptible, but 16K comes at significant premium. The same applies to intelligence. Sure, some users might register a meaningful bump, but if 99% can't tell the difference in their day-to-day work, does it matter? A 20-30% cost…

Longer version of the comment https://www.linkedin.com/pulse/imperceptible-upgrade-petko-d...

Re: Measuring Claude 4.7's tokenizer costs

#110

Post by mfro »

technotony wrote: post #99

Not only that but they seem to have cut my plan ability to use Sonnet too. I have a routine that used to use about 40% of my 5 hour max plan tokens, then since yesterday it gets stopped because it uses the whole 100%. Anyone else experience this?

yeah it seems like sonnet 4.6 burns thru tokens crazy fast. I did one prompt, sonnet misunderstood it as 'generate an image of this' and used all of my free tokens.
Post reply on HN