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

411–420 of 540 posts

Re: Measuring Claude 4.7's tokenizer costs

#411

Post by sumedh »

what wrote: post #358
sumedh wrote: post #330

Earlier quoted context omitted.

> At that point you are beholden to your shareholders No not really, you can issue two types of shares, the company founders can control a type of shares which has more voting power while other shareholders can get a different type of shares with less voting power. Facebook, Google has something similar.

No, they still have to act in the interest of shareholders even if they have no voting power.

What will happen if they don't because the founders control the voting powe

Re: Measuring Claude 4.7's tokenizer costs

#412

Post by skissane »

noosphr wrote: post #409
bornfreddy wrote: post #294

Earlier quoted context omitted.

By continuously testing competitors and local LLMs? The reason for rising prices is that they (Anthropic) probably realized that they have reached a ceiling of what LLMs are capable of, and while it's a lot, it is still not a big moat and it's definitely not intelligence.

Anything but the simplest tooling is not transferable between model generations, let alone completely different families.

> Anything but the simplest tooling is not transferable between model generations, let alone completely different families.

It is transferable-yes, you will get issues if you take prompts and workflows tuned for one model and send them to another unchanged. But, most of the time, fixing it is just tinkering with some prompt templates

People port solutions between models all the time. It takes some work, but the amount of work involved is tractable

Plus: this is absolutely the kind of task a coding agent can accelerate

The biggest risk is if your solution is at the frontier of capability, and a competing model (even another frontier model) just can’t do it. But a lot of use cases, that isn’t the case. And even if that is the case today, decent odds in a few more months it won’t be

Re: Measuring Claude 4.7's tokenizer costs

#413

Post by throwaway041207 »

noosphr wrote: post #409
bornfreddy wrote: post #294

Earlier quoted context omitted.

By continuously testing competitors and local LLMs? The reason for rising prices is that they (Anthropic) probably realized that they have reached a ceiling of what LLMs are capable of, and while it's a lot, it is still not a big moat and it's definitely not intelligence.

Anything but the simplest tooling is not transferable between model generations, let alone completely different families.

If you're talking about APIs and SDKs, whether direct API calls or driving tools like Claude code or codex with human out of the loop, I think that's actually fairly straightforward to switch between the various tools.

If you're talking about output quality, then yeah, that's not as easy. But for product outputs (building a customer service agent or something like that), having a well-designed eval harness and doing testing and iteration can get you some degree of convergence between the models of similar generations. Coding is similar (iterate, measure), but less easy to eval.

Re: Measuring Claude 4.7's tokenizer costs

#414

Post by slopinthebag »

QuiEgo wrote: post #205
ezst wrote: post #171

Earlier quoted context omitted.

> It wouldn't surprise me if in 2-3 years the "max" plan is $800 or $2000 even. I'd rather be surprised if they are still doing business by then.

I would not be surprised at all, a $1,000/mo tool that makes your $20,000/mo engineer a lot more productive is an easy sell. I’m guessing we’re gonna have a world like working on cars - most people won’t have expensive tools (ex a full hydraulic lift) for personal stuff, they are gonna have to make do with lesser tools.

What about when there is a $100/month tool that makes your engineer 90% as productive as they were on the $1000/mo tool?

What if that tool is something you can run on prem, and over time make the investment back?

It's not so simple.

Re: Measuring Claude 4.7's tokenizer costs

#415

Post by cheesecakegood »

tremon wrote: post #275
whalesalad wrote: post #271

Earlier quoted context omitted.

I am having a shit experience lately. Opus 4.7, max effort. > You're right, that was a shit explanation. Let me go look at what V1 MTBL actually is before I try again. > Got it — I read the V1 code this time instead of guessing. Turns out my first take was wrong in an important way. Let me redo this in English. :facepalm:

> I read the V1 code this time instead of guessing Does the LLM even keep a (self-accessible) record of previous internal actions to make this assertion believable, or is this yet another confabulation?

No they do not (to be clear, not internal state, just the transcript). It’s entirely role-play. LLM apologies are meaningless because the models are mostly stateless. Every new response is a “what would a helpful assistant with XYZ prior context continue to say?”

Re: Measuring Claude 4.7's tokenizer costs

#416

Post by NewJazz »

ianm218 wrote: post #363
scuff3d wrote: post #352

Earlier quoted context omitted.

It's not gonna stay that way. Token cost is being massively subsidized right now. Prices will have to start increasing at some point.

This is hard to say definitively. The new Nvidia Vera Rubin chips are 35-50x more efficient on a FLOPS/ megawatt basis. TPU/ ASICS/ AMD chips are making similar less dramatic strides. So a service ran at a loss now could be high margin on new chips in a year. We also don’t really know that they are losing money on the 200/ month subscriptions just that they are compute constrained. If prices increase might be because…

What is your source on 35x more efficient? That seems like a wild performance improvement that I would have hears about.

My research shows claims of 10x efficiency, but that number is very questionable.

Re: Measuring Claude 4.7's tokenizer costs

#417

Post by Jweb_Guru »

mikert89 wrote: post #33

The compute is expensive, what is with this outrage? People just want free tools forever?

I'm mostly surprised that people found the output quality of Opus 4.6 good enough... 4.7 so far is a pretty sizable improvement for the stuff I care about. I don't really care how cheap 4.6 was per task when 90% of the tasks weren't actually being done correctly. Or maybe it's that people like the LLM agreeing with them blindly while sneakily doing something else under the hood? Did people enjoy Claude routinely disregarding their instructions? Not really sure I understand, I truly found 4.6 immensely frustrating (from the getgo, not just the "pre-nerf" version, whatever that means). 4.7 is a buggy mess, it's slow, and it costs a lot per token. It's also a huge breath of fresh air because it actually seems to make a good faith effort at doing the thing you asked it to do, and doesn't waste your time with irrelevant nonsense just to make it look busy or because it thinks you want that nonsense (I mean, it still does all of these things to some extent, but so far it seems like it does them much less than 4.6 did).

Disclaimer: I'm always running on max and don't really have token limits so I am in a position not to care about cost per token. But I am not surprised by the improved benchmark results at all, 4.6 was really not nearly as strong of a model as people seem to remember it being.

Re: Measuring Claude 4.7's tokenizer costs

#418

Post by panavm »

tabbott wrote: post #268

I find it interesting that folks are so focused on cost for AI models. Human time spent redirecting AI coding agents towards better strategies and reviewing work, remains dramatically more expensive than the token cost for AI coding, for anything other than hobby work (where you're not paying for the human labor). $200/month is an expensive hobby, but it's negligible as a business expense; SalesForce licenses cost fa…

[flagged]

Re: Measuring Claude 4.7's tokenizer costs

#419

Post by chis »

tabbott wrote: post #268

I find it interesting that folks are so focused on cost for AI models. Human time spent redirecting AI coding agents towards better strategies and reviewing work, remains dramatically more expensive than the token cost for AI coding, for anything other than hobby work (where you're not paying for the human labor). $200/month is an expensive hobby, but it's negligible as a business expense; SalesForce licenses cost fa…

Yeah completely agree. Even out of my own pocket I'd be willing to spend ~1k a month for the current AI, as compared to not having any AI at all. And I bet I could convince an employer to drop 5k a month on it for me. The consumer surplus atm is insane.
Post reply on HN