Claude Haiku 4.5 • Hacker News Board

Re: Claude Haiku 4.5

#111

Post by b7894 » Wed, Oct 15, 2025, 8:41 PM UTC

ziofill wrote: post #57

simonw wrote: post #18

Pretty cute pelican on a slightly dodgy bicycle: https://tools.simonwillison.net/svg-render#%3Csvg%20viewBox%...

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

Re: Claude Haiku 4.5

#112

Post by quentin-smr » Wed, Oct 15, 2025, 8:43 PM UTC

Comparing haiku and sonnet for a question needing a code doc fetch:

haiku https://claude.ai/share/8a5c70d5-1be1-40ca-a740-9cf35b1110b1 sonnet https://claude.ai/share/51b72d39-c485-44aa-a0eb-30b4cc6d6b7b

haiku invented the output of a function and gave a bad answer. sonnet got it right

Re: Claude Haiku 4.5

#113

Post by parkersweb » Wed, Oct 15, 2025, 8:46 PM UTC

RickHull wrote: post #13

If I'm close to weekly limits on Claude Code with Anthropic Pro, does that go away or stretch out if I switch to Haiku?

I’m also really interested in this - in fact it’s the first thing I went looking for in the announcement…

Re: Claude Haiku 4.5

#114

Post by caymanjim » Wed, Oct 15, 2025, 8:49 PM UTC

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 care.

I just want consistent tooling and I don't want to have to think about what's going on behind the scenes. Make it better. Make it better without me having to do research and pick and figure out what today's latest fashion is. Make it integrate in a generic way, like TLS servers, so that it doesn't matter whether I'm using a CLI or neovim or an IDE, and so that I don't have to constantly switch tooling.

Re: Claude Haiku 4.5

#115

Post by _ink_ » Wed, Oct 15, 2025, 8:52 PM UTC

Tiberium wrote: post #31

leetharris wrote: post #29

The main thing holding these Anthropic models back is context size. Yes, quality deteriorates over a large context window, but for some applications, that is fine. My company is using grok4-fast, the Gemini family, and GPT4.1 exclusively at this point for a lot of operations just due to the huge 1m+ context.

Is your company Tier 4? Anthropic has had 1M context size in beta for some time now. https://docs.claude.com/en/docs/build-with-claude/context-wi...

Is it possible to get that in Claude Code with Pro? Or is it already a 1M context window?

Re: Claude Haiku 4.5

#116

Post by jdoe1337halo » Wed, Oct 15, 2025, 8:56 PM UTC

knes wrote: post #34

At augmentcode.com, we've been evaluating Haiku for some time, it's actually a very good model. We found out it's 90% as good as Sonnet and is ~34% faster than sonnet! Where it doesn't shine much is on very large coding task. but it is a phenomenal model for small coding tasks and the speed improvement is much welcome

Do you have a definition of what is considered a small vs large coding task?

Re: Claude Haiku 4.5

#117

Post by meander_water » Wed, Oct 15, 2025, 8:57 PM UTC

> The score reported uses a minor prompt addition: "You should use tools as much as possible, ideally more than 100 times. You should also implement your own tests first before attempting the problem."

I'm not sure if the SWE benchmark score can be compared like for like with OpenAIs scores because of this.

Re: Claude Haiku 4.5

#118

Post by joshuahedlund » Wed, Oct 15, 2025, 8:58 PM UTC

meander_water wrote: post #117

> The score reported uses a minor prompt addition: "You should use tools as much as possible, ideally more than 100 times. You should also implement your own tests first before attempting the problem." I'm not sure if the SWE benchmark score can be compared like for like with OpenAIs scores because of this.

https://en.wikipedia.org/wiki/Goodhart%27s_law "When a measure becomes a target, it ceases to be a good measure"

I'm also curious what results we would get if SWE came up with a new set of 500 problems to run all these models against, to guard against overfitting.

Re: Claude Haiku 4.5

#119

Post by andrewstuart » Wed, Oct 15, 2025, 9:01 PM UTC

Claude has stopped showing code in artifacts unless it knows the extension.

I used to be able to work on Arduino .ino files in Claude now it just says it can’t show it to me.

And do we have zip file uploads yet to Claude? ChatGPT and Gemini have done this for ages.

And all the while Claude’s usage limits keep going up.

So yeah, less for more with Claude.

Re: Claude Haiku 4.5

#120

Post by philipp-gayret » Wed, Oct 15, 2025, 9:05 PM UTC

singularity2001 wrote: post #89

philipp-gayret wrote: post #75

Tried it in Claude Code via /config, makes it feel like I'm running on Cerebras. It's seriously fast, bottleneck is on human review at this point.

Do you need Pro?

All I know is I'm on the Claude Code 5x max plan and it works on my machine.