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

401–410 of 540 posts

Re: Measuring Claude 4.7's tokenizer costs

#401

Post by samuelknight »

_fat_santa wrote: post #62

A question I've been asking alot lately (really since the release of GPT-5.3) is "do I really need the more powerful model"? I think a big issue with the industry right now is it's constantly chasing higher performing models and that comes at the cost of everything else. What I would love to see in the next few years is all these frontier AI labs go from just trying to create the most powerful model at any cost to ac…

The cost of intelligence is non-linear, with slightly dumber models costing much less. For a growing surface of problems you do not need frontier intelligence. You should use frontier intelligence for situations where you would otherwise require human intervention throughout the workflow, which is much more expensive than any model.

Re: Measuring Claude 4.7's tokenizer costs

#402

Post by ericol »

cadamsdotcom wrote: post #331
ericol wrote: post #266

I did some work yesterday with Opus and found it amazing. Today we are almost on non-speaking terms. I'm asking it to do some simple stuff and he's making incredible stupid mistakes: This is the third time that I have to ask you to remove the issue that was there for more than 20 hours. What is going on here? and at the same time the compacting is firing like crazy. (What adds ~4 minute delays every 1 - 15 minutes) |…

> he’s making .. mistakes Claude and other LLMs do not have a gender; they are not a “he”. Your LLM is a pile of weights, prompts, and a harness; anthropomorphising like this is getting in the way. You’re experiencing what happens when you sample repeatedly from a distribution. Given enough samples the probability of an eventual bad session is 100%. Just clear the context, roll back, and go again. This is part of the…

You are being downvoted but I actually agree with your statement.

Re: Measuring Claude 4.7's tokenizer costs

#404

Post by thrwaway55 »

fragmede wrote: post #200
louiereederson wrote: post #38

Earlier quoted context omitted.

I meant reference Toby Ord's work here. I think his framing of the performance/cost frontier hasn't gotten enough attention https://www.tobyord.com/writing/hourly-costs-for-ai-agents

That post doesn't address the human factor of cost, and I don't mean that in a good way. Even if AI costs more than a human, it's tireless, doesn't need holidays, is never going to have to go to HR for sexual harassment issues, won't show up hungover or need an advance to pay for a dying relative's surgery. It can be turned on and off with the flip of a switch. Hire 30 today, fire 25 of them next week. Spin another 5…

Why do you think it can't sexually harass someone or drive people to suicide. There are already lawsuits coming in on it causing suicides.

This is an architecture that people are increasing begging to give network connectivity that can't differentiate its system prompt from user input

Re: Measuring Claude 4.7's tokenizer costs

#405

Post by GorbachevyChase »

bisonbear wrote: post #188
cced wrote: post #187

Earlier quoted context omitted.

So they nerfed 4.6 to make way for 4.7? Progress. /s

> they nerfed 4.6 to make way for 4.7? > Progress. /s pretty much, lmao. my theory is 4.6 started thinking less to save compute for 4.7 release. but who knows what's going on at anthropic

A fun conspiracy theory I have is that Mythos isn’t actually dangerous in any serious sense. They just can’t reliably serve a 10T model. So they have to make up a reason to limit customers.

Re: Measuring Claude 4.7's tokenizer costs

#407

Post by arcanemachiner »

solenoid0937 wrote: post #249
zozbot234 wrote: post #207

Earlier quoted context omitted.

> We need more voices like this to cut through the bullshit. Open models are not bullshit, they work fine for many cases and newer techniques like SSD offload make even 500B+ models accessible for simple uses (NOT real-time agentic coding!) on very limited hardware. Of course if you want the full-featured experience it's going to cost a lot.

I fell for this stuff, went into the open+local model rabbit hole, and am finally out of it. What a waste of time and money! People that love open models dramatically overstate how good the benchmaxxed open models are. They are nowhere near Opus.

There is absolutely a use case for open models... but anyone expecting to get anywhere near the GPT 5.x or Claude 4.x experience for more demanding tasks (read: anything beyond moderate-difficulty coding) will be sorely disappointed.

I love my little hobby aquarium though... It's pretty impressive when Qwen Coder Next and Qwen 3.5 122B can accomplish (in terms of general agentic use and basic coding tasks), considering that the models are freely-available. (Also heard good things about Qwen 3.5 27B, but haven't used it much... yes I am a Qwen fanboi.)

Re: Measuring Claude 4.7's tokenizer costs

#409

Post by noosphr »

bornfreddy wrote: post #294
lbreakjai wrote: post #281

Earlier quoted context omitted.

The cost to hire a human is highly predictable. The cost of AI isn't. I, as a human, need food and shelter, which puts a ceiling to my bargaining power. I can't withdraw my labour indefinitely. The power dynamics are also vastly against me. I represent a fraction of my employer's labour, but my employer represents 100% of my income. That dynamic is totally inverted with AI. You are a rounding error on their revenue s…

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.

Re: Measuring Claude 4.7's tokenizer costs

#410

Post by noisy_boy »

At this point, as an experienced developer, unless they can promise consistent very high quality, which they can't, I would rather lean towards almost as good but faster. At this point, that compromise is Codex.

I would rather steer quickly, get ideas because I'm moving quickly, do course correction quickly - basically I'm not happy blocking my chain of thought/concentration and fall prey to distractions due to Claude's slowness and compaction cycles. Sometimes I don't even notice that Codex has compacted.

For architectural discussions, sure I'll pick Claude. I'm mentally prepared for that. But once we are in the thick of things, speed matters. I would they rather focus on improving Sonnet's speed.

Post reply on HN