zlacker

>>meetpa+(OP)
My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried.

There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person does. But I'm finding that these Gemini models are finally able to replace searches and stackoverflow for a lot of my day-to-day programming.

>>segpha+J4
I have been asking if AI without hallucination, coding or not is possible but so far with no real concrete answer.

>>ksec+66
It's already much improved on the early days.

But I wonder when we'll be happy? Do we expect colleagues friends and family to be 100% laser-accurate 100% of the time? I'd wager we don't. Should we expect that from an artificial intelligence too?

>>mattlo+E6
I expect my calculator to be 100% accurate 100% of the time. I have slightly more tolerance for other software having defects, but not much more.

>>kweing+c8
Are you sure about that? Try these..

- (1e(1e10) + 1) - 1e(1e10)

- sqrt(sqrt(2)) * sqrt(sqrt(2)) * sqrt(sqrt(2)) * sqrt(sqrt(2))

>>pizza+gl
Three decades and I haven't had to do anything remotely resembling this on a calculator, much less find the calculator wrong. Same for the majority of general population I assume.

>>ctxc+jm
The person you're replying to pointed out that you shouldn't expect a calculator to be 100% accurate 100% of the time. Especially not when faced with adversarial prompts.