[aakresearch]

Wait, what? I thought everyone agrees that modern models post September 2025 (or whenever Opus or whatever 5.6789 was released) do not hallucinate, make things up, contradict themselves and can review their own output into perfection regardless of task, goal or context???? /s

[UncleOxidant]

In general I think from the coding side they're more robust now. However, people generating docs are maybe not as experienced with how to prompt in ways that avoid having the LLM tell you what you want to hear. I think this is still a pitfall that can easily be fallen into. Those of us who are doing LLM-assisted coding for the last couple of years are more aware of this now. Those who are planning/management folks are still kind of susceptible depending on how much experience they've had dealing with LLMs.

[KronisLV]

What a take with no nuance.

> do not hallucinate

They do, just less. To the degree of being usable, as long as there are guardrails and they're used responsibly. For example, if there's code being output, there should be type checking and compilation, as well as code tests that prove that it works or that it doesn't - seeing how abysmal code coverage is in most of the projects I've seem, for whatever reason people thought that they didn't really need it much. They were wrong.

This also implies you need SOTA models on max reasoning.

> make things up

Same as above. Ideally you'd give them some way to verify their claims, like web search or browsing and referencing docs, Jira tickets etc., basically improve the signal to noise ratio.

> contradict themselves

They do so way less than before, as long as the above is true.

> can review their own output into perfection

They are pretty good at reviewing things, especially if you make them do adversarial review! It will never be perfect, but can be close in quality to human output (e.g. the code they produce, when used properly and with intent, is better than the code I've seen many developers write and ship before LLMs were a thing).

This also more or less scales with how much compute you give them - three parallel review agents will turn one output artifact into something good with higher confidence than two, and definitely better than with no review. There's a cost vs quality balance and it seems that all those xhigh and max reasoning modes are still geared way too much towards cost, instead of quality. So you have to make up for that shortcoming yourself.

> regardless of task, goal or context????

Garbage in, garbage out. I won't be an asshole and say that you're holding it wrong, nor will I say that anyone should listen to the claims marketing AI (absolutely delusional takes, meant to attract investors), but we're slowly getting to a better position in regards to LLMs, year by year.

It's just a shame that the peak of inflated expectations hit while the technology still hasn't fully plateaued and reached whatever its ceiling is.

I probably also shouldn't ignore the fact that some people will not care about any of it and send AI generated slop verbatim and to an outside observer there's no way to easily tell apart the difference between the two, unless you make a technical report contain exact references to where the data is sourced from, for example (and then either verify the references yourself, or make another agent do it).

[MaKey]

I think you missed the /s (for sarcasm) at the end.

[KronisLV]

Yeah, my bad, though I’ve also heard those arguments more or less said genuinely - on one hand people hold LLMs to some unreasonably high standard, expecting to one shot apps before being deemed good, and on the other just outputting slop with no regard for the quality.