11–20 of 491 posts
Also, I'm missing a section on how (if) human brains manage to avoid hallucinations in this.
Also, it doesn't have to never hallucinate, it just has to hallucinate less than we do.
You have to very carefully ask your question for it to not make things up. For example don't ask "how do I do this in in x?". Ask "can I do this with x?" These "AI" s are like "yes men". They will say anything to please you even if it's untrue or impossible. I have met people like that and they are very difficult to work with. You can't trust that they will deliver the project they promised and you always have to dou…
Fortunately that doesn't tell much about the limitations of the underlying intelligence but mostly about the limitations of the incentive structure you put around it
It sounds a bit like an incompleteness theorem (which in practice also doesn't mean that math research is futile) - yeah, LLMs may not be able to compute some functions, but the hallucination problem isn't about LLMs needing to know everything. The problem that we care about is the 'I don't know'-answering problem, which may still be computable.
It seems a stretch to call it "inevitable". "Inevitable given the current architecture without modifications" at most. Also, I'm missing a section on how (if) human brains manage to avoid hallucinations in this. Also, it doesn't have to never hallucinate, it just has to hallucinate less than we do.
> hallucination is defined as inconsistencies between a computable LLM and a computable ground truth function. That's simply inaccuracy or fabrication. Labelling it hallucination simply panders to the idea these programs are intelligent.
The models are just generating probable text. What’s amazing of how often the text is correct. It’s no surprise at all when it’s wrong Their bold confidence to be flat out wrong may be their most human trait
The models are just generating probable text. What’s amazing of how often the text is correct. It’s no surprise at all when it’s wrong Their bold confidence to be flat out wrong may be their most human trait
You can train a model to always carefully claim that what they say may or may not be true, but that may not necessarily make them easier to work with.
IIUC what we're missing right now is the ability for the model to get a good estimate of how confident they _should_ be.
This can be done "externally" or "internally". Doing it externally would mean: make the model not directly stream its train of thought directly to the end user but instead use it first to produce a query info some system that can help it weigh its confidence factor. Then a se and run on that output and its previous output can reformat the answer to be more balanced.
Doing it internally would require this process to be part of the incremental output token production. I don't know about the field to know whether that's even doable and whether we have some progress on that front
It seems a stretch to call it "inevitable". "Inevitable given the current architecture without modifications" at most. Also, I'm missing a section on how (if) human brains manage to avoid hallucinations in this. Also, it doesn't have to never hallucinate, it just has to hallucinate less than we do.
How often do we sit somewhere thinking about random scenarios that won't ever happen and are filled with wild thoughts and sometimes completely out of the world situations.. then we shake our heads and throw away the impossible from that thought train and only use what was based in reality
The models are just generating probable text. What’s amazing of how often the text is correct. It’s no surprise at all when it’s wrong Their bold confidence to be flat out wrong may be their most human trait
paulsutter said: > Note that this is the single most human attribute of LLMs It might be if LLM hallucinations looked like or occurred at the same frequency as human hallucinations do, but they don’t.
Yesterday I read "Building a deep learning rig" as "Building a deep learning pig" at first for some reason I can't explain...