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

Claude Haiku 4.5

anthropic.com

Post reply on HN
Print view View original

211–220 of 292 posts

Re: Claude Haiku 4.5

#211

Post by solumunus »

deadbabe wrote: post #203
distalx wrote: post #196

Earlier quoted context omitted.

Exactly, token per dollar rates are useful, but without knowing the typical input output token distribution for each model on this specific task, the numbers alone don’t give a full picture of cost.

That’s how they lie to us. Companies can advertise cheap prices to lure you in but they know very well how many tokens you’re going to use on average so they will still make more profit than ever, especially if you’re using any kind of reasoning model which is just like a blank check for them to print money.

I don’t think any of them are profitable are they? We’re in the losing money to gain market share phase of this industry.

Re: Claude Haiku 4.5

#212

Post by solumunus »

caymanjim wrote: post #114

Ain't nobody got time to pick models and compare features. It's annoying enough having to switch from one LLM ecosystem to another all the time due to vague usage restrictions. I'm paying $20/mo to Anthropic for Claude Code, to OpenAI for Codex, and previously to Cursor for...I don't even know what. I know Cursor lets you select a few different models under the covers, but I have no idea how they differ, nor do I car…

This really seems like a you problem.

Re: Claude Haiku 4.5

#213

Post by 8n4vidtmkvmk »

caymanjim wrote: post #114

Ain't nobody got time to pick models and compare features. It's annoying enough having to switch from one LLM ecosystem to another all the time due to vague usage restrictions. I'm paying $20/mo to Anthropic for Claude Code, to OpenAI for Codex, and previously to Cursor for...I don't even know what. I know Cursor lets you select a few different models under the covers, but I have no idea how they differ, nor do I car…

They're working on all that. I think "ACP" is supposed to be the answer. Then you can use the models in your IDEs, and they can all develop against the same spec so it'll be easy to pop into whatever model.

Gpt 5 is supposed to cleverly decide when to think harder.

But ya we're not there yet and I'm tired of it too, but what can you do.

Re: Claude Haiku 4.5

#214

Post by squigz »

peddling-brink wrote: post #174
katchu11 wrote: post #171

Earlier quoted context omitted.

Hey! I work on the Claude Code team. Both PAYG and Subscription usage look to be configured correctly in accordance with the price for Haiku 4.5 ($1/$5 per M I/O tok). Feel free to DM me your account info on twitter ( https://x.com/katchu11 ) and I can dig deeper!

lol, I don’t know if you work there or not, but directing folks to send their account info to a random Twitter address is, not considered best practice.

What's wrong with sending a username to someone?

Re: Claude Haiku 4.5

#215

Post by solumunus »

osn9363739 wrote: post #159
caymanjim wrote: post #114

Ain't nobody got time to pick models and compare features. It's annoying enough having to switch from one LLM ecosystem to another all the time due to vague usage restrictions. I'm paying $20/mo to Anthropic for Claude Code, to OpenAI for Codex, and previously to Cursor for...I don't even know what. I know Cursor lets you select a few different models under the covers, but I have no idea how they differ, nor do I car…

Even if you pick one. First it's prompt driven development, then context driven. Then you should use a detailed spec. But no, now it's better to talk to it like a person/have a conversation. Hold up why are you doing that you should be doing example driven. Look, I get that they probably all have their place, but since there isn't consensus on any of this, it's next to impossible to find good examples. Some one poste…

Work it out brother. If you can learn to code at a good level then you should be able to learn how to increase your productivity with LLM’s. When, where and how to use them is the key.

I don’t think it’s appreciated enough how valuable having a structured and consistent architecture combined with lots of specific custom context. Claude knows how my integration tests should look, it knows how my services should look, what dependencies they have and how they interact with the database. It knows my entire DB schema with all foreign key relationships. If I’m starting a new feature I can have it build 5 or 6 services (not without first making suggestions on things I’m missing) with integration tests, with raw sql all generated by Claude, and run an integration test loop until the services are doing what they should. I rarely have to step in and actually code. It shines for this use case and the productivity boost is genuinely incredible.

Other situations I know doing it myself will be better and/or quicker than asking Claude.

Re: Claude Haiku 4.5

#216

Post by jstummbillig »

justinbaker84 wrote: post #90
senko wrote: post #54

I've tried it on a test case for generating a simple SaaS web page (design + code). Usually I'm using GPT-5-mini for that task. Haiku 4.5 runs 3x faster with roughly comparable results (I slightly prefer the GPT-5-mini output but may have just accustomed to it).

I don't understand why more people don't talk about how fast the models are. I see so much obsession with bechmark scores but speed of response is very important for day to day use. I agree that the models from OpenAI and Google have much slower responses than the models from Anthropic. That makes a lot of them not practical for me.

Well, it depends on what you do. If a model can produce a PR that is ready to merge (and another can't), waiting 5 minutes is fine.

Re: Claude Haiku 4.5

#217

Post by ygouzerh »

caymanjim wrote: post #114

Ain't nobody got time to pick models and compare features. It's annoying enough having to switch from one LLM ecosystem to another all the time due to vague usage restrictions. I'm paying $20/mo to Anthropic for Claude Code, to OpenAI for Codex, and previously to Cursor for...I don't even know what. I know Cursor lets you select a few different models under the covers, but I have no idea how they differ, nor do I car…

Github Copilot could help you, you can switch model from different providers on the fly (supports Anthropic, OpenAI, Grok,...)

Re: Claude Haiku 4.5

#218

Post by stavros »

simonw wrote: post #167
stavros wrote: post #160

Earlier quoted context omitted.

Is it wherever the tokens are, or is it the N first tokens they've seen before? Ie if my prompt is 99% the same, except for the first token, will it be cached?

The prefix has to be stable. If you are 99% the same but the first token is different it won't cache at all. You end up having to design your prompts to accommodate this.

That's what I thought, thanks Simon.

Re: Claude Haiku 4.5

#219

Post by sandos »

UncleOxidant wrote: post #131
qsort wrote: post #127

Earlier quoted context omitted.

Models are stateless, why would that not work?

OK I understand what those words mean, but how exactly does that work? How does the new model 'know' what's being worked on when the old model was in the middle of working on a task and then a new model is switched to? (and where the task might be modifying a C++ file)

Wow, not knowing that models have 0 working memory is.. wild.
Post reply on HN