DeepSeek V4 hallucinates like crazy and often forgets explicitly mentioned parts of the context. I guess compressing tokens and cherry-picking attention comes at a cost.
DeepSeek V4 hallucinates like crazy and often forgets explicitly mentioned parts of the context. I guess compressing tokens and cherry-picking attention comes at a cost.
Deepseek is one of the worst in terms of hallucination rate according to artificial analysis' benchmark: https://artificialanalysis.ai/?omniscience=omniscience-hallu...
That's interesting. The "best" current models, Fable and especially GPT 5.6, are also lying liars that lie all the time. Seems like we're going the wrong way on hallucination.
And I remember Sam Altman saying 2 years ago or more, that hallucination was already "fixed" internally. Well, clearly not.
I've been seeing more "grounding" messages in the thinking log of Claude models. I guess that's "do a web search, read the docs", probably designed to mitigate hallucinations.
I am surprised by how much the really giant models hallucinate, though. My vague feeling was that little models hallucinate a lot because they just don't know anything (the world's knowledge simply does not fit in a few GB) and don't know how to say, "I don't know". But, the big models kinda do know everything, and yet, here we are, they're still making shit up all the time.
One of my tests to see if "we are there", it's to ask a list of mayors from my city. Sounds silly, but most models just create random mayors that never existed.
Without search, of course. In theory this should be easy, because clearly the Wikipedia data it's in the model.
> I am surprised by how much the really giant models hallucinate, though. My vague feeling was that little models hallucinate a lot because they just don't know anything (the world's knowledge simply does not fit in a few GB) and don't know how to say, "I don't know". But, the big models kinda do know everything, and yet, here we are, they're still making shit up all the time.
In my mostly unscientific RAG experiments I found that larger models were more likely to hallucinate in a RAG setting. I think that it's because they have more world knowledge. As an example, when asking about safety legislation in Ireland, Claude got hooked on the notion that OSHA was involved, which clearly is not true, while the smaller models just said that they couldn't find any information (which was the correct answer).
Deepseek V4 pro is a heavily undertrained model, they only trained it a bit more than the small version and that small version is 6-ish times smaller. Ive found that Flash is absolutely incredible as a workhorse for wide scale agentic nonsense, but Pro is a bit undercooked and really goes on strange tangents very often.
I have seen occasional weird behavior that I guess could be attributed to hallucinations, but for security auditing, DeepSeek v4 Pro is among the best models I've tested, competitive with Opus 4.8 and GPT 5.5 (MiMo and GLM also did well, Qwen 3.7 Max was below all of those, though only barely), and at an order of magnitude lower cost per task.