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 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.

▲

rho4 a day ago | parent | next [-]

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 with people who give me a 1 sentence response to my question, and only start elaborating and going on tangents and down rabbit holes upon request.

▲

philipwhiuk a day ago | parent | next [-]

> 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.

I doubt it. In fact I would predict the speed/detail trade-off continues to diverge.

▲

confirmmesenpai a day ago | parent | prev | next [-]

> Imagine waiting for a minute until Google spits out the first 10 results.

what if the instantaneous responses make you waste 10 min realizing they were not what you searched for?

▲

rho4 a day ago | parent [-]

I understand your point, but I still prefer instantaneous responses.

Only when the immediate answers become completely useless will I want to look into slower alternatives.

But first "show me what you've got so far", and let me decide whether it's good enough or not.

▲

confirmmesenpai a day ago | parent [-]

I am already at that point. when I need to search something more complex than exact keyword match, I don't even bother googling it anymore, I just ask chatgpt to research it for me and read it's response 5 min later.

	▲	rho4 a day ago \| parent [-]
		Yes, I feel the same recently with Google results. But I think I would still like to see the immediate 10 results, along with a big button "Try harder - not feeling very lucky".

▲

unparagoned a day ago | parent | prev [-]

Grok fast is fast but doing a lot of stupid stuff fast actually ends up being slower

▲

EagnaIonat a day ago | parent | prev | next [-]

> It loves doing a whole bunch of reasoning steps

If you are talking about local models, you can switch that off. The reasoning is a common technique now to improve the accuracy of the output where the question is more complex.

▲

geldedus a day ago | parent | prev | next [-]

Only Codex is slow. GPT 5 classic is fast

▲

szundi a day ago | parent | prev | next [-]

[dead]

▲

Tepix a day ago | parent | prev [-]

The article(§) talks about going from Sonnet 4.5 back to Sonnet 4.0.

(§) You know that it's a hyperlink, do you? /s