- cross-posted to:
- technology@lemmy.zip
- cross-posted to:
- technology@lemmy.zip
For one month beginning on October 5, I ran an experiment: Every day, I asked ChatGPT 5 (more precisely, its “Extended Thinking” version) to find an error in “Today’s featured article”. In 28 of these 31 featured articles (90%), ChatGPT identified what I considered a valid error, often several. I have so far corrected 35 such errors.
You must log in or # to comment.
Congrats. You just burned down 4 trees in the rainforest for every article you had an LLM analyze.
LLMs can be incredibly useful, but everybody forgets how much of an environmental nightmare this shit is.
“Liar thinks truth is also a lie. More at 11”
The problem is a lot of this is almost impossible to actually verify. After all if an article says a skyscraper has 70 stories even people working in the building may not be able to necessarily verify that.
I have worked in a building where the elevator only went to every other floor, and I must have been in that building for at least 3 months before I noticed because the ground floor obviously had access and the floor I worked on just happened to do have an elevator so it never occurred to me that there may be other floors not listed.
For something the size of a 63 (or whatever it actually was) story building it’s not really visually apparent from the outside either, you’d really have to put in the effort to count the windows. Plus often times the facade looks like more stories so even counting the windows doesn’t necessarily give you an accurate answer not that anyone would necessarily have the inclination to do so. So yeah, I’m not surprised that errors like that exist.
More to the point the bigger issue is can the AI actually prove that it is correct. In the article there was contradictory information in official sources so how does the AI know which one was the right one? Could somebody be employed to go check? Presumably even the building management don’t know the article is incorrect otherwise they would have been inclined to fix it.
Finding inconsistencies is not so hard. Pointing them out might be a -little- useful. But resolving them based on trustworthy sources can be a -lot- harder. Most science papers require privileged access. Many news stories may have been grounded in old, mistaken histories … if not on outright guesses, distortions or even lies. (The older the history, the worse.)
And, since LLMs are usually incapable of citing sources for their own (often batshit) claims any – where will ‘the right answers’ come from? I’ve seen LLMs, when questioned again, apologize that their previous answers were wrong.
This is way overblown. Wikipedia is on par with the most accurate Encyclopedias with 3-4 factual errors per article.
More like 1, sometimes 2, errors in 90% of wikipedia’s longest and most active articles.
legitimate use of a LLM
I find that an extremely simplified way of finding out whether the use of an LLM is good or not is whether the output from it is used as a finished product or not. Here the human uses it to identify possible errors and then verify the LLM output before acting and the use of AI isn’t mentioned at all for the corrections.
The only danger I see is that errors the LLM didn’t find will continue to go undiscovered, but they probably would be undiscovered without the use of the LLM too.
I think the first part you wrote is a bit hard to parse but I think this is related:
I think the problematic part of most genAI use cases is validation at the end. If you’re doing something that has a large amount of exploration but a small amount of validation, like this, then it’s useful.
A friend was using it to learn the linux command line, that can be framed as having a single command at the end that you copy, paste and validate. That isn’t perfect because the explanation could still be off and it wouldn’t be validated but I think it’s still a better use case than most.
If you’re asking for the grand unifying theory of gravity then:
- validation isn’t built into the task (so you’re unlikely to do it with time).
- validation could be as time intensive as the task (so there is no efficiency gain if you validate).
- its beyond your ability to validate so if it says nice things about you then a subset of people will decide the tool is amazing.
Yeah, my morning brain was trying to say that when it is used as a tool by someone that can validate the output and act upon it then it’s often good. When it is used by someone who can’t, or won’t, validate the output and simply uses it as the finished product then it usually isn’t any good.
Regarding your friend learning to use the terminal I’d still recommend validating the output before using it. If it’s asking genAI about flags for ls then sure no big deal, but if a genAI ends up switching around sda and sdb in your dd command resulting in a wiped drive you only got yourself to blame for not checking the manual.
Or it flags something as an error falsely and the human has so much faith in the system that it must be correct, and either wastes time finding the solution or bends reality to “correct” it in a human form of hallucinating bs. Especially dangerous if saying there is an error supports the individual’s personal beliefs
Edit:
I’ll call it “AI-induced confirmation bias” cousin to AI-induced psychosis.
“AI” summed up. 95% of the time it’s pointless bullshit being shoehorned into absolutely everything. 5% of the time it can be useful.
like Comic Sans
Something weird about corporations spending billions on “the Comic Sans of technology”
Yep. Let it flag potential problems, and have humans react to it, e.g. by reviewing and correcting things manually. AI can do a lot of things quick and efficiently, but it must be supervised like a toddler.
This is an interesting idea:
The “at least one” in the prompt is deliberately aggressive, and seems likely to force hallucinations in case an article is definitely error-free. So, while the sample here (running the prompt only once against a small set of articles) would still be too small for it, it might be interesting to investigate using this prompt to produce a kind of article quality metric: If it repeatedly results only in invalid error findings (i.e. what a human reviewer
Disagrees with), that should indicate that the article is less likely to contain factual errors
Wait, you mean using Large Language Model that created to parse walls of text, to parse walls of text, is a legit use?
Those kids at openai would’ve been very upset if they could read.
Chatbots aren’t the worst use case, too, even though we are headed in a wrong direction.
Yes and no. I have enjoyed reading through this approach, but it seems like a slippery slope from this to “vibe knowledge” where LLMs are used for actually trying to add / infer information.
Don’t discard a good technique cause it can be implemented poorly.
A tool that gives at least 40% wrong answers, used to find 90% errors?
If you read the post it’s actually quite a good method. Having an LLM flag potential errors and then reviewing them manually as a human is actually quite productive.
I’ve done exactly that on a project that relies on user-submitted content; moderating submissions at even a moderate scale is hard, but having an llm look through for me is easy. I can then check through anything it flags and manually moderate. Neither the accuracy nor precision is perfect, but it’s high enough to be useful so it’s a low-effort way to find a decent number of the thing you’re looking for. In my case I was looking for abusive submissions from untrusted users; in the OP author’s case they were looking for errors. I’m quite sure this method would never find all errors, and as per the article the “errors” it flags aren’t always correct either. But the effort:reward ratio is high on a task that would otherwise be unfeasible.
But we don’t know what the false positive rate is either? How many submissions were blocked that shouldn’t have been, it seems like you don’t have a way to even find that metric out unless somebody complained about it.
I can then check through anything it flags and manually moderate.
It isn’t doing anything automatically; it isn’t moderating for me. It’s just flagging submissions for human review. “Hey, maybe have a look at this one”. So if it falsely flags something it shouldn’t, which is common, I simply ignore it. And as I said, that error rate is moderate, and although I haven’t checked the numbers of the error rate, it’s still successful enough to be quite useful.
90% errors isn’t accurate. It’s not that 90% of all facts in wikipedia are wrong. 90% of the featured articles contained at least one error, so the articles were still mostly correct.
Bias needs to be reinforced!
The first edit was undoing a vandalism that persisted for 5 years. Someone changed the number of floors a building had from 67, to 70.
A friendly reminder to only use Wikipedia as a summary/reference aggregate for serious research.
This is a cool tool for checking these sorts of things, run everything through the LLM to flag errors and go after them like a wack-a-mole game instead of a hidden object game.
the tool that is mainly based on wikipedia info?
The tool doesn’t just check the text for errors it would know of. It can also check sources, compare articles, and find inconsistencies within the article itself.
There’s a list of the problems it found that often explains where it got the correct information from.
No surprise.
Wikipedia ain’t the bastion of facts that lemmites make them out to be.
It’s a mess of personal fiefdoms run by people with way too much time on their hands and an ego to match.
Yeah, better to use grokpedia /s
I know this is sarcasm, but in case people don’t know.
Oh Jesus Christ no. At least Wikipedia has some form of oversight from multiple sources and people.
