I've found that the VSCode GitHub Copilot extension defaults to Claude Sonnet 4.0 (in agent mode) in all new workspaces. It's the first thing I check now, but I imagine a lot of people just roll with it, especially if they use inline completions where it might not be obvious what model is being used.
Developers are choosing older AI models
81–90 of 179 posts
Re: Developers are choosing older AI models
#82Earlier quoted context omitted.
Most people can’t affort the GPUs for local models if you want to get close to cloud capabilities.
A 4090 has 24GB of VRAM allowing you to run a 22B model entirely in memory at FP8 and 24B models at Q6_K (~19GB). A 5090 has 32GB of VRAM allowing you to run a 32B model in memory at Q6_K. You can run larger models by splitting the GPU layers that are run in VRAM vs stored in RAM. That is slower, but still viable. This means that you can run the Qwen3-Coder-30B-A3B model locally on a 4090 or 5090. That model is a Mix…
you need a couple RTX 6000 pros to come close to matching cloud capability
Re: Developers are choosing older AI models
#83To the authors of the site, please know that your current "Cookiebot by Usercentrics" is old and pretty much illegal. You shouldn't need to click 5 times to "Reject all" if accepting all is one click. Newer versions have a "Deny" button.
Or you could just reject all third party cookies, see no sites break and enjoy your privacy.
Doesn't spare you from having to interact with the popup. This is probably the single dumbest law to ever have been made. It wastes everyone's time, and not insignificantly. While the browser is and always was in full control of cookies, nobody checks whether the popup actually even does what it says. And since it's a waste of your time in the first place, who takes the time to report illegal ones, much less has any interest to do so, because where you saw it is where you will likely never visit again anyway.
If anything browsers should be simply rejecting all cookies by default, and the user should only be whitelisting ones they need on the few sites where they need it.
Re: Developers are choosing older AI models
#84Earlier quoted context omitted.
Today. But what about in 5 years? Would you bet we will be paying hundreds of billions to OpenAI yearly or buying consumer GPUs? I know what I will be doing.
But the progress goes both ways: In five years, you would still want to use whatever is running on the cloud supercenters. Just like today you could run gpt-2 locally as a coding agent, but we want the 100x-as-powerful shiny thing.
That would be great if that was the case but my understanding is that the progress is plateauing. I don't know how much of this is anthorpic / Google / openAI holding itself back to save money and how much is the state of the art improvement slowing down though. I can imagine there could be a 64 GB GPU in five years as absurd as it feels to type that today.
Re: Developers are choosing older AI models
#85Earlier quoted context omitted.
Weirdly this site also requested bluetooth access on my mac.
That would be the browser fingerprinting in action. I often get a lot of requests to use widevine on ddg's browser on android (which informs one about it) for I suspect similar reasons.
Interesting. Is this fingerprinting in action? I have Widevine disabled on Brave desktop (don't recall if this is default), occasionally I get Widevine permission request on some sites.
Re: Developers are choosing older AI models
#86Earlier quoted context omitted.
Or you could just reject all third party cookies, see no sites break and enjoy your privacy.
Doesn't spare you from having to interact with the popup. This is probably the single dumbest law to ever have been made. It wastes everyone's time, and not insignificantly. While the browser is and always was in full control of cookies, nobody checks whether the popup actually even does what it says. And since it's a waste of your time in the first place, who takes the time to report illegal ones, much less has any…
I don't think the lawmakers planned for the level of malicious compliance that would be deployed.
Re: Developers are choosing older AI models
#87Earlier quoted context omitted.
I am currently using a local model qwen3:8b running on a 2020 (2018 intel chip) Mac mini for classifying news headlines and it's working decently well for my task. Each headline takes about 2-3 seconds but is pretty accurate. Uses about 5.3 gigs of ram.
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 is to have a fast GPU and run a model that fits entirely within the GPU's memory. In these cases you might measure the model's processing speed in tens of tokens per second.
As the idealness decreases, the processing speed decreases. On a CPU only with a model that fits in RAM, you'd be maxing out in the low single digit tokens per second, and on lower performance hardware, you start talking about seconds over token instead. If the model does not fit in RAM, then the measurement is minutes per token.
For most people, their minimum acceptable performance level is in the double digit tokens per second range, which is why people optimize for that with high-end GPUs with as much memory as possible, and choose models that fit inside the GPU's RAM. But in theory you can run large models on a potato, if you're prepared to wait until next week for an answer.
Re: Developers are choosing older AI models
#88Earlier quoted context omitted.
Or you could just reject all third party cookies, see no sites break and enjoy your privacy.
Doesn't spare you from having to interact with the popup. This is probably the single dumbest law to ever have been made. It wastes everyone's time, and not insignificantly. While the browser is and always was in full control of cookies, nobody checks whether the popup actually even does what it says. And since it's a waste of your time in the first place, who takes the time to report illegal ones, much less has any…
Single dumbest law ever made? I think that’s underestimating the stupidity of many laws.
Re: Developers are choosing older AI models
#89For 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?
Re: Developers are choosing older AI models
#90Earlier quoted context omitted.
But… they do all the time. Almost everybody uses some mix of Office, Slack, Notion, random email providers, random “security” solutions etc. The exception is the opposite. The only thing prevents info leaking is ToS, and there are options for that even with LLMs. Nothing changed regarding that.
In my personal experience, it's very common for big companies to host email, messengers, conferencing software on their own servers.
Yes, then they use Outlook for example. Have you checked the ToS of the new Outlook version for commoners? They flat out state that they can use all of your emails for whatever they want.
Also, companies host for example an Exchange server on prem; and guess, what it connects to? Why you can usually access account at outlook.com?