151–160 of 179 posts
Earlier quoted context omitted.
That's out of touch for 90% of developers worldwide
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.
Earlier quoted context omitted.
Honestly though how many people reading this do you think have that setup vs. 85% of us being on a MBx? > The Qwen3-Coder-480B-A35B model could also be run on a 4090 or 5090 by splitting the active 35B parameters across VRAM and RAM. Reminds me of running Doom when I had to hack config.sys to forage 640KB of memory. Less than 0.1% of the people reading this are doing that. Me, I gave $20 to some cloud service and I c…
> Reminds me of running Doom when I had to hack config.sys to forage 640KB of memory. The good old days of having to do crazy nutty things to get Elite II: Frontier, Magic Carpet, Worms, Xcom: UFO Enemy Unknown, Syndicate et cetera to actually run on my PC :-)
Earlier quoted context omitted.
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.
> [...] 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 [...] Yes, it's down from 40h/week to 3-5h/week on Max plan, effectively. A real bummer. See my comment here [1] regarding [2]. [1] https://news.ycombinator.com/item?id=45604301 [2] https://github.com/anthropics/claude-code/issues/8449
In my experience sonnet 4.5 is basically pointless, it often gets non-trivial tasks wrong, and for trivial tasks I can use a local model or one of the myriad of providers that give free inference.
EDIT: Holy shit I read the github issue, fuck these people.
> We highly recommend Sonnet 4.5 -- Opus uses rate limits faster, and is not as capable for coding tasks.
They're just straight gaslighting us now lmao.
Earlier quoted context omitted.
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?
Your on premise exchange server has zero connections to outlook.com. OWA (Outlook Web Access) looks similar to outlook.com but has otherwise nothing to do with it.
Earlier quoted context omitted.
How do you objectively tell whether a model "performs" better than another?
Not the original commenter but I work in the space and we have large annotated datasets with "gold" evidence that we want to retrieve, the evaluation of new models is actually very quantitative.
Ya, the original commenter likely does not work in the space - hence the ask.
> the evaluation of new models is actually very quantitative.
While you may be able to derive a % correct (and hence quantitative), they are by their nature very much not quantitative. Q&As on written subjects are very much subjective. Example benchmark: https://llm-stats.com/benchmarks/gpqa Even though there are techniques to reduce overfitting, it still isn't eliminated. So it's very much subjective.
For 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…
It's a shame Cerebras completely dropped Qwen3 Coder's fast tool calling, short and instant responses, and better speed overall for GLM 4.6 thinking. Qwen3 is really good at hitting the tools first, then coming up with a well-grounded answer based on reality. Sometimes it's good when a model is Socratic: just knows it knows nothing.
GLM 4.6 on the other hand is more self-sufficient and if it sees it, and knows it, it thinks and thinks and finally just fixes it in one or two shots, so when you hit the jackpot, it probably an improvement over Q3C. But when it does not get it right, it digs itself into a hole larger than the Olympus Mons.
Isn’t this obvious? When you have a task you think is hard. You give it to a cleverer model. When a task is straight forward you give it to an older one.
Not realy. Most developers would prefer one model that does everything best. That is the easiest, set it and forget it, no manual descision required. What is unclear from the presentation is wether they do this or not. Do teams that use Sonnet 4.5 just always use it, and teams on Sonnet 4.0 likewise? Or do individuals decided which model to use on a per task basis. Personally I tend to default to just 1, and only go…
What I definitely do care about is speed and efficiency. I recently canceled CoPilot to go back to Cursor, it's just so much faster for the inline code completion.
When I do have something difficult, I open four browser tabs and copy paste a big long promp into the free versions of the top models so I can take my time reasoning out their answers.
I use agents when I have a basic task that I can easily judge their output in code review.
Earlier 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…
For 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?