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

Claude Sonnet 4.5

anthropic.com

Post reply on HN
Print view View original

241–250 of 819 posts

Re: Claude Sonnet 4.5

#241

Post by raincole »

cloverich wrote: post #108

Please y'all, when you list supportive or critical complaints based on your actual work, include some specifics of the task and prompt. Like actual prompt, actual bugs, actual feature, etc. I've had great success with both ChatGPT and Claude for years, am around 3x sustained output increase in my professional work, and kicking off and finishing new side projects / features that I used to simply not ever finish. BUT t…

I agree. I think we can start with cloverich including some specifics of the task and prompt.

Re: Claude Sonnet 4.5

#242

Post by PunchTornado »

rudedogg wrote: post #70

I just ran this through a simple change I’ve asked Sonnet 4 and Opus 4.1, and it fails too. It’s a simple substitution request where I provide a Lint error that suggests the correct change. All the models fail. I could ask someone with no development experience to do this change and they could. I worry everyone is chasing benchmarks to the detriment of general performance. Or the next token weight for the incorrect c…

Downvoted because you didn’t mention the prompt and the issue.

Re: Claude Sonnet 4.5

#243

Post by Philpax »

sigmoid10 wrote: post #214
Bjorkbat wrote: post #169

> Practically speaking, we’ve observed it maintaining focus for more than 30 hours on complex, multi-step tasks. Really curious about this since people keep bringing it up on Twitter. They mention it pretty much off-handedly in their press release and doesn't show up at all in their system card. It's only through an article on The Verge that we get more context. Apparently they told it to build a Slack clone and left…

This is obviously much more than just taking an LLM an letting it run for 30 hours. You have to build a whole environment together with external tool integration and context management and then tune the prompts and perhaps even set up a multi-agent system. I believe that if someone puts a ton of work into this you can have an LLM run for that long and still produce sellable outputs, but let's not pretend like this is…

Well, yes, that's Claude Code. And OpenAI Codex. And Google Gemini CLI.

Your average dev can just use those.

Re: Claude Sonnet 4.5

#244

Post by ethmarks »

yepyip wrote: post #199
peterdstallion wrote: post #157

I am a paying subscriber to Gemini, Claude and OpenAI. I don't know if it's me, but over the last few weeks I've got to the conclusion ChatGPT is very strongly leading the race. Every answer it gives me is better - it's more concise and more informative. I look forward to testing this further, but out of the few runs I just did after reading about this - it isn't looking much better

What about Grok, are they catching up?

I've only tried Grok Code Fast 1, so I can't speak for any of the other models.

In my experience, Grok is very fast and very cheap, but only moderately intelligent. It isn't stupid, but it rarely does anything that impresses me. The reason it's a useful model is that it is very, very fast (~90 tokens per second) and is very competitively priced.

Re: Claude Sonnet 4.5

#245

Post by XenophileJKO »

garciasn wrote: post #77
patates wrote: post #40

Earlier quoted context omitted.

In my experience Gemini 2.5 Pro is the star when it comes to complex codebases. Give it a single xml from repomix and make sure to use the one at the aistudio.

In my experience, G2.5P can handle so much more context and giving an awesome execution plan that is implemented by CC so much better than anything G2.5P will come up with. So; I give G2.5P the relevant code and data underneath and ask it to develop an execution plan and then I feed that result to CC to do the actual code writing. This has been outstanding for what I have been developing AI assisted as of late.

I would believe this. In regular conversational use with the Gemini family of models, I've noticed they regularly have issues with context blending.. i.e. confusing what you said and they said and causality.

I would think this would manifest as poor plan execution. I personally haven't used Gemini on coding tasks primarily based on my conversational experience with them.

Re: Claude Sonnet 4.5

#246

Post by scrollaway »

emp17344 wrote: post #224
scrollaway wrote: post #198

Earlier quoted context omitted.

GP is right, though. Many programming communities, including (in some threads, but not all) HN, have become ridiculous anti-AI bubbles - what's the point of trying to have a discussion if you're going to get systematically shut down by people whose entire premise is that they don't use it? It's like trying to explain color to the blind. What "discussion" do you want to have? Another round of "LLMs are terrible at emb…

I think you’re overly sensitive to criticism of LLMs.

No? I really don't give a crap what people criticize. It doesn't change anything in my life - I have plenty going on and nothing you or anyone says here will alter that. It's just sad to see a community I like (and which I've been a part of for longer than you've been programming) factually shut itself down to reality...

Re: Claude Sonnet 4.5

#247

Post by blurbleblurble »

nerdsniper wrote: post #161
blurbleblurble wrote: post #115

Earlier quoted context omitted.

The only exaggeration is in that the way I asked GPT-5 to leave claude to do its thing was to say "why don't we just let claude cook"? I later checked with ChatGPT about the whole exchange and it confirmed that it was well aware of the meaning of this slang, and it's first reaction was that whole thing just sounded like a funny programmer joke, all in jest. But then I reminded it that I'd explicitly pushed back on a…

I strongly disagree with the personified way you interact with LLMs from a standpoint of “I’ve rarely gotten the best output from the LLM when I interact casually with them”. However, it’s the early days of learning this new interface, and there’s a lot to learn - certainly some amount of personification has been proven to help the LLM by giving it a “role”, so I’d only criticize the degree rather than the entire con…

That's fair. I enjoy the playfulness of it and for me it feels almost like a video game or something, and also like I'm using my own natural language directly.

Also appreciate your perspective. It's important to come at these things with some discipline. And moreso, bringing in a personal style of interaction invites a lot of untamed human energies into the dynamic.

The thing is, most of the time I'm quite dry with it and they still ignore my requests really often, regardless of how explicit or dry I am. For me, that's the real takeaway here, stripping away my style of interaction.

Re: Claude Sonnet 4.5

#248

Post by beefnugs »

jjordan wrote: post #230
bradley13 wrote: post #116

I need to try Claude - haven't gotten to it. I use AI for different things, though, including proofreading posts on political topics. I have run into situations where ChatGPT just freezes and refuses. Example: discussing the recent rape case involving a 12-year-old in Austria. I assume its guardrails detect "sex + kid" and give a hard "no" regardless of the actual context or content. That is unacceptable. That's like…

This is why eventually, the AI with the fewest guardrails will win. Grok is currently the most unguarded of the frontier models, but it could still use some work on unbiased responses.

Still has to be a local model too.

Arbitrary government censorship on top of arbitrary corporate censorship is a hell no for me forever into the future

Re: Claude Sonnet 4.5

#249

Post by Fraterkes »

sebastiennight wrote: post #228
emp17344 wrote: post #196

Earlier quoted context omitted.

> I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. 1 is not infinitely greater than 0.

It... literally is? Or otherwise, can you share what you think the ratio is?

I think it's a pedantic point, but maybe they just meant that talking about 1 being multitudes greater than 0 implies multiplication. And since 1/0 is undefined that doesn't make much sense.

Re: Claude Sonnet 4.5

#250

Post by kurtis_reed »

simonw wrote: post #204

I had access to a preview over the weekend, I published some notes here: https://simonwillison.net/2025/Sep/29/claude-sonnet-4-5/ It's very good - I think probably a tiny bit better than GPT-5-Codex, based on vibes more than a comprehensive comparison (there are plenty of benchmarks out there that attempt to be more methodical than vibes). It particularly shines when you try it on https://claude.ai/ using its brand n…

Why did you have access to a preview?
Post reply on HN