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

141–150 of 819 posts

Re: Claude Sonnet 4.5

#141

Post by Hamuko »

mohsen1 wrote: post #14

Price is playing a big role in my AI usage for coding. I am using Grok Code Fast as it's super cheap. Next to it GPT-5 Codex. If you are paying for model use out of pocket Claude prices are super expensive. With better tooling setup those less smart (and often faster) models can give you better results. I am going to give this another shot but it will cost me $50 just to try it on a real project :(

I'm too cheap to pay for any of them. I've only tried gpt-oss:20b because I can run it locally and it's a complete waste of time for anything except code completions.

Re: Claude Sonnet 4.5

#142

Post by AlecSchueler »

Kuinox wrote: post #97
AlecSchueler wrote: post #82

Earlier quoted context omitted.

But then how does the quality increase? Normally we hear that when models are trained on the output of other models the style becomes very muted and various other issues start to appear. But this probably the best pelicans on a bicycle I've ever seen, by quite some margin.

Just compare it with a human on a bicycle, you would see that LLMs are weirdly good at drawing pelicans in SVG but not humans.

I thought a human would be a considerable step up in complexity but I asked it first for a pelican[0] and then for a rat [1] to get out of the bird world and it did a great job on both.

But just fot thrills I also asked for a "punk rocker"[2] and the result--while not perfect--is leaps and bounds above anything from the last generation.

0 -- ok, here's the first hurdle! It's giving me "something went wrong" when I try to get a share link on any of my artifacts. So for now it'll have to be a "trust me bro" and I'll try to edit this comment soon.

Re: Claude Sonnet 4.5

#143

Post by rapind »

blurbleblurble wrote: post #56
yewenjie wrote: post #5

Looking at the chart here, it seems like Sonnet 4 was already better than GPT-5-codex in the SWE verified benchmark. However, my subjective personal experience was GPT-5-codex was far better at complex problems than Claude Code.

GPT-5 is like the guy on the baseball team that's really good at hitting home runs but can't do basic shit in the outfield. It also consistently gets into drama with the other agents e.g. the other day when I told it we were switching to claude code for executing changes, after badmouthing claude's entirely reasonable and measured analysis it went ahead and decided to `git reset --hard` even after I twice pushed back…

> it went ahead and decided to `git reset --hard` even after I twice pushed back on that idea

So this is something I've noticed with GPT (Codex). It really loves to use git. If you have it do something and then later change your mind and ask it to undo the changes it just made, there's a decent chance it's going to revert to the previous git commit, regardless of whether that includes reverting whole chunks of code it shouldn't.

It also likes to occasionally notice changes it didn't make and decide they were unintended side effects and revert them to the last commit. Like if you made some tweaks and didn't tell it, there's a chance it will rip them out.

Claude Code doesn't do this, or at least I never noticed it doing this. However, it has it's own medley of problems of course.

When I work with Codex, I really lean into a git workflow. Everything is on a branch and commit often. It's not how I'd normally do things, but doesn't really cost me anything to adopt it.

These agents have their own pseudo personalities, and I've found that fighting against it is like swimming upstream. I'm far more productive when I find a way to work "with" the model. I don't think you need a bunch of MCPs or boilerplate instructions that just fill up their context. Just adapt your workflow instead.

Re: Claude Sonnet 4.5

#144

Post by alfalfasprout »

danieloj wrote: post #130
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…

Could you share the actual examples of where you’re seeing the 3x output increase?

right? The irony is so thick you could cut it with a butter knife

Re: Claude Sonnet 4.5

#145

Post by senordevnyc »

catigula wrote: post #140
senordevnyc wrote: post #125

Earlier quoted context omitted.

HN is such a negative and cynical place these days that it's just not worth it. I just don't have the patience to hear yet another anti-AI rant, or have someone who is ideologically opposed to AI nitpick its output. Like you, I've found AI to be a huge help for my work, and I'm happy to keep outcompeting the people who are too stubborn to approach it with an open mind.

[flagged]

OK. Well, I've been doing this the hard way for about twenty years, and now with AI in the mix my little solo SaaS has gone from nothing to $5k MRR in six weeks. Guess I'm not holding it completely wrong?

Re: Claude Sonnet 4.5

#146

Post by scrollaway »

catigula wrote: post #140
senordevnyc wrote: post #125

Earlier quoted context omitted.

HN is such a negative and cynical place these days that it's just not worth it. I just don't have the patience to hear yet another anti-AI rant, or have someone who is ideologically opposed to AI nitpick its output. Like you, I've found AI to be a huge help for my work, and I'm happy to keep outcompeting the people who are too stubborn to approach it with an open mind.

[flagged]

You are making assumptions about someone you have never talked to in the past, and don't know anything about.

Of the two of you, I know which one I'd bet on being "right". (Hint: It's the one talking about their own experience, not the one supplanting theirs onto someone else)

Re: Claude Sonnet 4.5

#147

Post by blurbleblurble »

Marazan wrote: post #133
blurbleblurble wrote: post #110

Earlier quoted context omitted.

Yeah, it's wild how the biases get encoded in there. Maybe they aren't even entirely separable from the magic of LLMs.

It isn't wild, it is inherent to the very nature of large language models. The power of using LLMs is working out what it has encoded and how to access it.

I appreciate it being wild in the sense that language is inherently a tangled mess and these tools are actually leveraging that messy complexity.

Re: Claude Sonnet 4.5

#148

Post by kelsey98765431 »

senordevnyc wrote: post #125
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…

HN is such a negative and cynical place these days that it's just not worth it. I just don't have the patience to hear yet another anti-AI rant, or have someone who is ideologically opposed to AI nitpick its output. Like you, I've found AI to be a huge help for my work, and I'm happy to keep outcompeting the people who are too stubborn to approach it with an open mind.

all major nation state intelligence services have an incentive to spread negative sentiment and reduce developer adoption of ai technology as they race to catch up with the united states.

Re: Claude Sonnet 4.5

#149

Post by mrshu »

crthpl wrote: post #120
zurfer wrote: post #57

Earlier quoted context omitted.

Also getting a perfect score on AIME (math) is pretty cool. Tongue in cheek: if we progress linearly from here software engineering as defined by SWE bench is solved in 23 months.

The reason they get a perfect score on AIME is because every question on AIME had lots of thought put into it, and it was made sure that everything was a possible. SWE-bench, and many other AI benchmarks, have lots of eval noise, where there is no clear right answer, and getting higher than a certain percentage means you are benchmaxxing.

Do you think a more messier math benchmark (in terms of how it is defined) might be more difficult for these models to get?

Re: Claude Sonnet 4.5

#150

Post by catigula »

scrollaway wrote: post #146
catigula wrote: post #140

Earlier quoted context omitted.

[flagged]

You are making assumptions about someone you have never talked to in the past, and don't know anything about. Of the two of you, I know which one I'd bet on being "right". (Hint: It's the one talking about their own experience, not the one supplanting theirs onto someone else)

[flagged]
Post reply on HN