Developers are choosing older AI models
augmentcode.com
Developers are choosing older AI models
1–10 of 179 posts
Re: Developers are choosing older AI models
#2It could be an interesting data point, but without correcting for absolute usage figures and their customers it's kind of hard to make general statements.
Re: Developers are choosing older AI models
#3For development use cases, I switched to Sonnet 4.5 and haven't looked back. I mean, sure, sometimes I also use GPT-5 (and mini) and Gemini 2.5 Pro (and Flash), and also Cerebras Code just switched to providing GLM 4.6 instead of the previous Qwen3 Coder so those as well, but in general the frontier models are pretty good for development and I wouldn't have much reason to use something like Sonnet 4 or 3.7 or whatever.
Re: Developers are choosing older AI models
#4I think this is somewhat disingenuous since not everyone uses the latest thing, and people tend to stick to “what works” for them.
Models are picky enough about prompting styles that changing to a new model every week/month becomes an added chunk of cognitive overload, testing and experimentation, plus even in developer tooling there have been minor grating changes in API invocations and use of parameters like temperature (I have a fairly low-level wrapper for OpenAI, and I had to tweak the JSON handling for GPT-5).
Also, there are just too many variations in API endpoints, providers, etc. We don’t really have a uniform standard. Since I don’t use “just” OpenAI, every single tool I try out requires me to jump through a bunch of hoops to grab a new API key, specify an endpoint, etc.—and it just gets worse if you use a non-mainstream AI endpoint.
Re: Developers are choosing older AI models
#5GPT5 is HELLISHLY slow. That's all there is to it.
It loves doing a whole bunch of reasoning steps and prolaim how mucf of a very good job it did clearing up its own todo steps and all that mumbo jumbo, but at the end of the day, I only asked it a small piece of information about nginx try_files that even GPT3 could answer instantly.
Maybe before you make reasoning models that go on funny little sidequests wher they multiply numbers by 0 a couple of times, make it so its good at identfying the length of a task. ntil then, I'll ask little bro and advance only if necessity arrives. And if it ends up gathering dust, well... yeah.
Re: Developers are choosing older AI models
#6Seems to completely ignore usage of local/free models as well as anything but Sonnet/ChatGPT. So my confidence in the good faith of the author is... heavily restricted.
Re: Developers are choosing older AI models
#7I think this is somewhat disingenuous since not everyone uses the latest thing, and people tend to stick to “what works” for them. Models are picky enough about prompting styles that changing to a new model every week/month becomes an added chunk of cognitive overload, testing and experimentation, plus even in developer tooling there have been minor grating changes in API invocations and use of parameters like temper…
> I think this is somewhat disingenuous since not everyone uses the latest thing, and people tend to stick to “what works” for them.
They say that the number of users on Claude 4.5 spiked and then a significant number of users reverted to 4.0 with the trend going up, and they are talking about their usage metrics. So I don't get how your comment is relevant to the article ?
Re: Developers are choosing older AI models
#8Seems to completely ignore usage of local/free models as well as anything but Sonnet/ChatGPT. So my confidence in the good faith of the author is... heavily restricted.
Do you use a local/ free model?
Re: Developers are choosing older AI models
#9GPT5 is HELLISHLY slow. That's all there is to it. It loves doing a whole bunch of reasoning steps and prolaim how mucf of a very good job it did clearing up its own todo steps and all that mumbo jumbo, but at the end of the day, I only asked it a small piece of information about nginx try_files that even GPT3 could answer instantly. Maybe before you make reasoning models that go on funny little sidequests wher they…
[dead]
Re: Developers are choosing older AI models
#10Seems to completely ignore usage of local/free models as well as anything but Sonnet/ChatGPT. So my confidence in the good faith of the author is... heavily restricted.
Augment doesn't support local models or anything else other than Claude/GPT