Those of us using AI systems to get lots of work done quickly do know that AIs still hallucinate constantly and can't reliably write code of the type there isn't a large sample of in the training corpus, that they constantly forget which directory they are in and get lost trying to juggle two branches at a time and that they require constant supervision etc.

Both are possible, there is no juxtaposition here.

@perrymetzger Eventually this has to clash in some way with some new frame emerging and honestly that day can’t come soon enough.

@IAmArcIvanov I have not had an experience anything like yours. None of the things you suggest have occurred for me in a long time.

@perrymetzger The top AI researchers admit they hallucinate and talk candidly about their limitations. You aren’t a serious person

@perrymetzger All the llms still hallucinate endlessly and happily make things up. Anyone who says otherwise is experiencing psychosis.

@perrymetzger Opus 4.6 with Claude Code. Occurs all the time. 4.7 and 4.8 are even worse + waste more tokens. Perhaps we're writing different types of code.

@kuza55 Extreme levels of testing. I put tests around everything.

@perrymetzger Here is an open AI article about it

https://openai.com/index/why-language-models-hallucinate/

And the accompanying research paper

https://arxiv.org/abs/2509.04664

@Poofarmer69 Show me a “top AI researcher” that claims that a thinking model with web access routinely hallucinates.

@perrymetzger Codex still regularly makes mistakes.

100% of my code is AI at this point, but the length of the leash I give it still seems to matter.

I would love to hear details about what you're building, how you're building it and how you're guaranteeing reliability.

@perrymetzger Rather like: A: "I have this power drill I use to put lots of holes in wood reliably and quickly, you should try it!" B: "But my job doesn't involve putting holes in things." C: "But my job is putting holes in concrete." A: "Why are B and C such Luddites?! You must use my tool!"

@IAmArcIvanov @spion The harness also makes a big difference. That said, I have friends that swear by harnesses other than Codex CLI, like Open Code. I have not tried those.

@perrymetzger @IAmArcIvanov Yes, Opus has gone downhill ever since 4.5 - it can tackle more ambitious tasks but the rate of really bad errors has gone up drastically; 4.7+ is a net waste of time.

gpt 5.5 in codex doesn't seem to have that issue so far - definitely not to that extent.

@Poofarmer69 You have no idea what you’re talking about at all, do you? You didn’t even understand the thing that I was saying which you think you have somehow refuted. I will not be wasting more time on this.

@IAmArcIvanov Try Codex CLI for a few days. See if you like it better. You can always cancel the subscription.

@perrymetzger I honestly think the divide is all about expectations. If they expect AI to be a magic Oracle that never makes mistakes, they are disappointed. If they recognize that both AI and humans use iteration toward a goal as the core way to do things, and mistakes are expected, AI works.

@Poofarmer69 Neither of these talk about whether a reasoning model with web access hallucinates at all. You don’t even understand what I was talking about, do you? You’re just throwing stuff at the wall and hoping it sticks.

@IAmArcIvanov @perrymetzger Or, perhaps, we're writing different types of prompts.

Why don't you just tell us what type of code you are writing instead of pretending you are writing more sophisticated code than those of us with a nearly flawless ai experience daily.

@reed_rawlings Being wrong half a percent of the time is a lot better than human beings in most domains.