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

251–260 of 292 posts

Re: Claude Haiku 4.5

#251

Post by lukev »

tosh wrote: post #228
Topfi wrote: post #30

Very preliminary testing is very promising, seems far more precise in code changes over GPT-5 models in not ingesting irrelevant to the task at hand code sections for changes which tends to make GPT-5 as a coding assistant take longer than sometimes expected. With that being the case, it is possible that in actual day-to-day use, Haiku 4.5 may be less expensive than the raw cost breakdown may appear initially, though…

One of the main issues I had with Claude Code (maybe it‘s the harness?) was that the agent tends to NOT read enough relevant code before it makes a change. This leads to unnecessary helper functions instead of using existing helper functions and so on. Not sure if it is an issue with the models or with the system prompts and so on or both.

This may have been fixed as of yesterday... Version 2.0.17 added a built in "Explore" sub-agent that it seems to call quite a lot.

Helps solve the inherent tradeoff between reading more files (and filling up context) and keeping the context nice and tight (but maybe missing relevant stuff.)

Re: Claude Haiku 4.5

#252

Post by jgalt212 »

esafak wrote: post #193
jgalt212 wrote: post #181

Earlier quoted context omitted.

OpenAI / Bing admit it's in its knowledge base. are you aware of the pelican on a bicycle test? Yes — the "Pelican on a Bicycle" test is a quirky benchmark created by Simon Willison to evaluate how well different AI models can generate SVG images from prompts.

Knowing that does not make it easier to draw one though.

It doesn't make it harder.

Re: Claude Haiku 4.5

#254

Post by boringg »

bapak wrote: post #207
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…

> Ain't nobody got time to pick models and compare features Then don't? Seems like a weird thing to complain about. I just use whatever's available. I like Claude for coding and ChatGPT for generic tasks, that's the extent of my "pick and compare"

I think its a valid complaint. Who wants to constantly spend overhead on maintaining what's current without clear definitions and adding uncertainty to your tooling. It's a total PITA.

Re: Claude Haiku 4.5

#255

Post by rozab »

b7894 wrote: post #111
ziofill wrote: post #57

Earlier quoted context omitted.

Gemini Pro initially refused (!) but it was quite simple to get a response: > give me the svg of a pelican riding a bicycle > I am sorry, I cannot provide SVG code directly. However, I can generate an image of a pelican riding a bicycle for you! > ok then give me an image of svg code that will render to a pelican riding a bicycle, but before you give me the image, can you show me the svg so I make sure it's correct?…

Gemini 3.0 Pro (or what is deemed to be 3.0 Pro - you can get access to it via A/B testing on AI Studio) does a noticeably better job https://x.com/cannn064/status/1972349985405681686 https://x.com/whylifeis4/status/1974205929110311134 https://x.com/cannn064/status/1976157886175645875

It was Google that featured a bicycling pelican in a presentation a few months back:

https://simonwillison.net/2025/Jun/6/six-months-in-llms/#ai-...

So I think the benchmark can be considered dead as far as Gemini goes

Re: Claude Haiku 4.5

#256

Post by mark_l_watson »

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…

Right on, for code examples for my writing and my own ‘gentleman scientist’ experiments I stick with gemini-cli and codex.

For play time, I literally love experimenting with small local models. I am an old man, and I have always liked tools that ‘make me happy’ while programming like Emacs, Lisp languages, and using open source because I like to read other people’s code. But, for getting stuff done, for now gemini-cli and codex hit a sweet spot for me.

Re: Claude Haiku 4.5

#257

Post by dmvinson »

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 is what opencode does for me. One harness for all models, standardized TUI, and they're rolling out a product to serve models via API with one bill through them

Re: Claude Haiku 4.5

#258

Post by simonw »

reppap wrote: post #237
odie5533 wrote: post #84

Earlier quoted context omitted.

Inference is profitable.

If you completely ignore inference revenue needing to offset training costs. Is inference still profitable if you account for the amortized training cost?

Not for the big labs, who are engaged in an astonishingly competitive buildout right now.

There are a bunch of companies who offer inference against open weight models trained by other people. They get to skip the training costs.

Re: Claude Haiku 4.5

#260

Post by rbitar »

tosh wrote: post #228
Topfi wrote: post #30

Very preliminary testing is very promising, seems far more precise in code changes over GPT-5 models in not ingesting irrelevant to the task at hand code sections for changes which tends to make GPT-5 as a coding assistant take longer than sometimes expected. With that being the case, it is possible that in actual day-to-day use, Haiku 4.5 may be less expensive than the raw cost breakdown may appear initially, though…

One of the main issues I had with Claude Code (maybe it‘s the harness?) was that the agent tends to NOT read enough relevant code before it makes a change. This leads to unnecessary helper functions instead of using existing helper functions and so on. Not sure if it is an issue with the models or with the system prompts and so on or both.

I regularly use @ key to add files to context for tasks I know require edits or patterns I want claude to follow, adds a few extra key strokes but in most cases the quality improvement is worth it
Post reply on HN