Claude Sonnet 4.5 • Hacker News Board

Re: Claude Sonnet 4.5

#11

Post by kixiQu » Mon, Sep 29, 2025, 5:07 PM UTC

Lots of feature dev here – anyone have color on the behavior of the model yet? Mouthfeel, as it were.

Re: Claude Sonnet 4.5

#12

Post by mentos » Mon, Sep 29, 2025, 5:07 PM UTC

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.

Curious how you find ChatGPT5 to ChatGPT5-Codex?

Re: Claude Sonnet 4.5

#13

Post by meetpateltech » Mon, Sep 29, 2025, 5:08 PM UTC

Seeing the progress of the Claude models is really cool!

Charting Claude's progress with Sonnet 4.5: https://youtu.be/cu1iRoc1wBo

Re: Claude Sonnet 4.5

#14

Post by mohsen1 » Mon, Sep 29, 2025, 5:09 PM UTC

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 :(

Re: Claude Sonnet 4.5

#15

Post by dingnuts » Mon, Sep 29, 2025, 5:09 PM UTC

cryptoz wrote: post #4

I've really got to refactor my side project which I tailored to just use OpenAI API calls. I think the Anthropic APIs are a bit different so I just never put in the energy to support the changes. I think I remember reading that there are tools to simpify this kind of work, to support multiple LLM APIs? I'm sure I could do it manually but how do you all support multiple API providers that have some differences in the…

> think I remember reading that there are tools to simpify this kind of work, to support multiple LLM APIs

just ask Claude to generate a tool that does this, duh! and tell Claude to make the changes to your side project and then to have sex with your wife too since it's doing all the fun parts

Re: Claude Sonnet 4.5

#16

Post by greenfish6 » Mon, Sep 29, 2025, 5:10 PM UTC

As the rate of model improvement appears to slow, the first reactions seem to be getting worse and worse, as it takes more time to assess the model's quality and understand the nuances & subtler improvements

Re: Claude Sonnet 4.5

#17

Post by alach11 » Mon, Sep 29, 2025, 5:10 PM UTC

I'm really interested in the progress on computer use. These are the benchmarks to watch if you want to forecast economic disruption, IMO. Mastery of computer use takes us out of the paradigm of task-specific integrations with AI to a more generic interface that's way more scalable.

Re: Claude Sonnet 4.5

#18

Post by muttantt » Mon, Sep 29, 2025, 5:11 PM UTC

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 :(

how are you using grok code fast? what tooling/cli/etc?