[flagged]
Instead of being the best model, it's a race to bring in revenue and add bias for ad channels.
Developers are choosing older AI models
111–120 of 179 posts
Re: Developers are choosing older AI models
#112[flagged]
What I love about the words enshitification is it’s _almost_ autological. It takes a nice crisp on syllable word like “shit” and ruins it by adding 5 extra syllables. It just doesn’t worse over time, to be truly autological
Re: Developers are choosing older AI models
#113Earlier quoted context omitted.
Can you expand a bit on your software setup? I thought running local models was restricted to having expensive GPUs or latest Apple Silicon with unified memory. I have a Intel 11th gen home server which I would like to use to run some local model for tinkering if possible.
It's really just a performance tradeoff, and where your acceptable performance level is. Ollama, for example, will let you run any available model on just about any hardware. But using the CPU alone is _much_ slower than running it on any reasonable GPU, and obviously CPU performance varies massively too. You can even run models that are bigger than available RAM too, but performance will be terrible. The ideal case…
+1
> It's really just a performance tradeoff, and where your acceptable performance level is.
I am old enough to remember developers respecting the economics of running the software they create.
Ollama running locally paired occasionally with using Ollama Cloud when required is a nice option if you use it enough. I have twice signed up and paid $20/month for Ollama Cloud, love the service, but use it so rarely (because local models so often are sufficient) that I cancelled both times.
If Ollama ever implements a pay as you go API for Ollama Cloud, then I will be a long term customer. I like the business model of OpenRouter but I enjoy using Ollama Cloud more.
I am probably in the minority, but I wish subscription plans would go away and Claude Code, gemini-cli, codex, etc. would all be only available pay as you go, with ‘anti dumping’ laws applied to running unsustainable businesses.
I don’t mean to pick on OpenAI, but I think the way they fund their operations actually helps threaten the long term viability of our economy. Our government making the big all-in bet on AI dominance seems crazy to me.
Re: Developers are choosing older AI models
#114I am definitely not. Claude 4.5 and GPT 5 all the way for me
Re: Developers are choosing older AI models
#115GPT5 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…
Only Codex is slow. GPT 5 classic is fast
Re: Developers are choosing older AI models
#116Some missing context (pun intended) is that Augment code has recently switched to a per-token instead of per-message pricing model. This hasn't gone down particularly well, but that's another story. But it may well be that users drop back to older models in the expectation it will use less tokens.
Personally, I stopped using GPT-5 as it would just be tool call after tool call without ever stopping to tell you what the hell it was doing. Sonnet 4.5 much better in this regard. Albeit it's too verbose for the new token based world ('let me just summarise that in a report')
Re: Developers are choosing older AI models
#117For 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 whateve…
What tool are you using to enable switching between so many models?
Isn't Continue supposed to help you do that, in VSCode?
https://marketplace.visualstudio.com/items?itemName=Continue...
Re: Developers are choosing older AI models
#118Earlier quoted context omitted.
For large context (up to 100K tokens in some cases). We found that GPT-5: a) has worse instruction following; doesn't follow the system prompt b) produces very long answers which resulted in a bad ux c) has 125K context window so extreme cases resulted in an error
ChatGPT when using 5 or 5-Thinking doesn’t even follow my “custom instructions” on the web version. It’s a serious downgrade compared to the prior generation of models.
It does “follow” custom instructions. But more as a suggestion rather than a requirement (compared to other models)
Re: Developers are choosing older AI models
#119For 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 whateve…
I have canceled my Claude Max subscription because Sonnet 4.5 is just too unreliable. For the rest of the month I'm using Opus 4.1 which is much better but seems to have much lower usage limits than before Sonnet 4.5 was released. When I hit 4.1 Opus limits I'm using Codex. I will probably go through with the Codex pro subscription.
Sonnet 4.5 is way worse than Opus 4.1 -- it's incredible that they claim it's their best coding model.
It's obvious if you've used the two models for any sort of complicated work.
Codex with GPT-5 codex (high thinking) is better than both by a long shot, but takes longer to work. I've fully switched to Codex, and I used Claude Code for the past ~4 months as a daily driver for various things.
I only reach for Sonnet now if Codex gets cagey about writing code -- then I let Sonnet rush ahead, and have Codex align the code with my overall plan.
Re: Developers are choosing older AI models
#120I wish we could pin down not only the model but also the way the UI works as well. Last week Claude seemed to have a shift in the way it works. The way it summarises and outputs its results is different. For me it's gotten worse. Slower, worse results, more confusing narrowing down what actually changed etc etc. Long story short, I wish I was able to checkpoint the entire system and just revert to how it was previous…
You can install or using a specific version of claude by pinning it. Like `npx @anthropic-ai/claude-code@2.0.14` or `npm install -g @anthropic-ai/claude-code@2.0.14`
Claude Code is distinct from the Claude models.