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

101–110 of 292 posts

Re: Claude Haiku 4.5

#101

Post by username223 »

simonw wrote: post #76

I went looking for the bit about if it blackmails you or tries to murder you... and it was a bit of a cop-out! > Previous system cards have reported results on an expanded version of our earlier agentic misalignment evaluation suite: three families of exotic scenarios meant to elicit the model to commit blackmail, attempt a murder, and frame someone for financial crimes. We choose not to report full results here beca…

It sounds like AI researchers have used too much of their own bad sci-fi as training data for models they don't understand. Goodhart's law wins again!

Re: Claude Haiku 4.5

#102

Post by Topfi »

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…

Update, Haiku 4.5 is not just very targeted in terms of changes but also really fast. Averaging at 220token/sec is almost double most other models I'd consider comparable (though again, far to early to make a proper judgement) and if this can be kept up, that is a massive value add over other models. That is nearly Gemini 2.5 Flash Lite speed for context.

Yes, we got Groq and Cerebras getting up to 1000token/sec, but not with models that seem comparable (again, early, not a proper judgement). Anthropic has been historically the most consistent in outperforming personal benchmarks vs public benchmarks, for what that is worth so I am optimistic.

If speed, performance and pricing are something Anthropic can keep consistent long term (i.e. no regressions), Haiku 4.5 really is a great option for most coding tasks, with Sonnet something I'd tag in only for very specific scenarios. Past Claude models have had a deficiency in longer term chains of tasks. Beyond 7 minutes roughly, performance does appear to worsen with Sonnet 4.5, as an example. That could be an Achilles heel for Haiku 4.5 as well, if not this really is a solid step in terms of efficiency, but I have not done any longer task testing yet.

That being said, Anthropic once again has a rather severe issue it seems, casting a shadow upon this release. From what I am seeing and others are reporting, Claude Code currently does count Haiku 4.5 usage the same as Sonnet 4.5 usage, despite the latter being significantly more expensive. They also did not yet update the Claude Code support pages to reflect the new models usage limits [0]. I really think such information should be public by launch day and hope they can improve their tooling and overall testing, it really continues to throw a shadow over their impressive models.

[0] https://support.claude.com/en/articles/11145838-using-claude...

Re: Claude Haiku 4.5

#103

Post by svdr »

stared wrote: post #48

Why I use cheaper models for summaries (a lot ogf gemini-2.5-flash), what’s the use case of cheaper AI for coding? Getting more errors, or more spaghetti code, seems never worth it.

I'm using the smaller models for things like searching and summarizing over a larger part of the codebase. The speed is really pleasant then.

Re: Claude Haiku 4.5

#104

Post by hnuser123456 »

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?…

"create svg code that will create an image of svg code that will create a pelican riding a bicycle"

https://chatgpt.com/share/68f0028b-eb28-800a-858c-d8e1c811b6...

(can be rendered using simon's page at your link)

Re: Claude Haiku 4.5

#106

Post by senko »

dheera wrote: post #52
steveklabnik wrote: post #14

I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.

I wonder what the next smaller model after Haiku will be called. "Claude Phrase"?

Claude Glyph.

Smallest, fastest model yet, ideally suited for Bash oneliners and online comments.

Re: Claude Haiku 4.5

#108

Post by matltc »

pacoWebConsult wrote: post #8
aliljet wrote: post #3

What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.

One big use-case is that claude code with sonnet 4.5 will delegate into the cheaper model (configurable) more specific, contextful tasks, and spin up 1-3 sub-agents to do so. This process saves a ton of available context window for your primary session while also increasing token throughput by fanning-out.

How does one configure Claude code to delegate to cheaper models?

I have a number of agents in ~/.claude/agents/. Currently have most set to `model: sonnet` but some are on haiku.

The agents are given very specific instructions and names that define what they do, like `feature-implementation-planner` and `feature-implementer`. My (naive) approach is to use higher-cost models to plan and ideally hand off to a sub-agent that uses a lower-cost model to implement, then use a higher-cost to code review.

I am either not noticing the handoffs, or they are not happening unless specifically instructed. I even have a `claude-help` agent, and I asked it how to pipe/delegate tasks to subagents as you're describing, and it answered that it ought to detect it automatically. I tested it and asked it to report if any such handoffs were detected and made, and it failed on both counts, even having that initial question in its context!

Re: Claude Haiku 4.5

#109

Post by matltc »

dlisboa wrote: post #10
aliljet wrote: post #3

What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.

For me speed is interesting. I sometimes use Claude from the CLI with `claude -p` for quick stuff I forget like how to run some docker image. Latency and low response speed is what almost makes me go to Google and search for it instead.

I use gh copilot suggest in lieu of claude -p. Two seconds latency and highly accurate. You probably need a gh copilot auth token to do this though, and truthfully, that is pointless when you have access to Claude code.

Re: Claude Haiku 4.5

#110

Post by matltc »

logankeenan wrote: post #94

I'm not seeing it as a model option in Claude Code for my Pro plan. Perhaps, it'll roll out eventually? Anyone else seeing it with the same plan?

You on latest version? Try running /update hook. Can also config autoupdates
Post reply on HN