61–70 of 179 posts
To 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.
I think this is one of the many indicators that even though these models get “version upgrades” it’s closer to switching to a different brain that may or may not understand or process things the way you like. Without a clear jump in performance, people test new models and move back to ones they know work if the new ones aren’t better or are actually worse.
Earlier quoted context omitted.
Most people can’t affort the GPUs for local models if you want to get close to cloud capabilities.
Most people I know can't afford to leak business insider information to 3rd party SaaS providers, so it's unfortunately not really an option.
Earlier quoted context omitted.
Interesting, I'm on Brave and have never had a site request bluetooth access before, so much so that I'd never even granted Brave bluetooth access, hence why it popped up as a system notification this time around.
Doesn't Brave disable WebBluetooth by default via a flag?
It's by no means a new feature, but the privacy concerns outlined in this post are still valid 10 years later: https://blog.lukaszolejnik.com/w3c-web-bluetooth-api-privacy...
I think this is one of the many indicators that even though these models get “version upgrades” it’s closer to switching to a different brain that may or may not understand or process things the way you like. Without a clear jump in performance, people test new models and move back to ones they know work if the new ones aren’t better or are actually worse.
Interesting to use a term like brain in the context of LLMs.
Earlier quoted context omitted.
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…
That's out of touch for 90% of developers worldwide
Earlier quoted context omitted.
Can you elaborate on that? In which part of the RAG pipeline did GPT-4.1 perform better? I would expect GPT-5 to perform better on longer context tasks, especially when it comes to understanding the pre-filtered results and reasoning about them
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
I think this is one of the many indicators that even though these models get “version upgrades” it’s closer to switching to a different brain that may or may not understand or process things the way you like. Without a clear jump in performance, people test new models and move back to ones they know work if the new ones aren’t better or are actually worse.
To 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.
GPT5 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…
This. Speed determines whether I (like to) use a piece of software. Imagine waiting for a minute until Google spits out the first 10 results. My prediction: All AI models of the future will give an immediate result, with more and more innovation in mechanisms and UX to drill down further on request. Edit: After reading my reply I realize that this is also true for interactions with other people. I like interacting wi…
I doubt it. In fact I would predict the speed/detail trade-off continues to diverge.