It's true that people don't have a good intuitive sense of what the models are good or bad at (see: counting the Rs in "strawberry"), but this is more a human limitation than a fundamental problem with the technology.
I stress test commercially deployed LLMs like Gemini and Claude with trivial tasks: sports trivia, fixing recipes, explaining board game rules, etc. It works well like 95% of the time. That's fine for inconsequential things. But you'd have to be deeply irresponsible to accept that kind of error rate on things that actually matter.
The most intellectually honest way to evaluate these things is how they behave now on real tasks. Not with some unfalsifiable appeal to the future of "oh, they'll fix it."
That exposes me to when the models are objectively wrong and helps keep me grounded with their utility in spaces I can check them less well. One of the most important things you can put in your prompt is a request for sources, followed by you actually checking them out.
And one of the things the coding agents teach me is that you need to keep the AIs on a tight leash. What is their equivalent in other domains of them "fixing" the test to pass instead of fixing the code to pass the test? In the programming space I can run "git diff *_test.go" to ensure they didn't hack the tests when I didn't expect it. It keeps me wondering what the equivalent of that is in my non-programming questions. I have unit testing suites to verify my LLM output against. What's the equivalent in other domains? Probably some other isolated domains here and there do have some equivalents. But in general there isn't one. Things like "completely forged graphs" are completely expected but it's hard to catch this when you lack the tools or the understanding to chase down "where did this graph actually come from?".
The success with programming can't be translated naively into domains that lack the tooling programmers built up over the years, and based on how many times the AIs bang into the guardrails the tools provide I would definitely suggest large amounts of skepticism in those domains that lack those guardrails.
This is a broad statement that assumes we agree on the purpose.
For my purpose, which is software development, the technology has reached a level that is entirely adequate.
Meanwhile, sports trivia represents a stress test of the model's memorized world knowledge. It could work really well if you give the model a tool to look up factual information in a structured database. But this is exactly what I meant above; using the technology in a suboptimal way is a human problem, not a model problem.
If the purpose is indeed software development with review, then there's nothing stopping multi-billion dollar companies from putting friction into these sytems to direct users towards where the system is at its strongest.
95% is not my experience and frankly dishonest.
I have ChatGPT open right now, can you give me examples where it doesn't work but some other source may have got it correct?
I have tested it against a lot of examples - it barely gets anything wrong with a text prompt that fits a few pages.
> The most intellectually honest way to evaluate these things is how they behave now on real tasks
A falsifiable way is to see how it is used in real life. There are loads of serious enterprise projects that are mostly done by LLMs. Almost all companies use AI. Either they are irresponsible or you are exaggerating.
Lets be actually intellectually honest here.
Quite frankly, this is exactly like how two people can use the same compression program on two different files and get vastly different compression ratios (because one has a lot of redundancy and the other one has not).
You will just won't have any clue what that could be.
#8 has an incorrect answer (3 appearances according to Gemini, 2 according to reality https://en.wikipedia.org/wiki/Bowl_championship_series#BCS_a...)
So it works well 95% of the time for literally a trivial use case. Imagine if any other tech tool had that kind of reliability: `ls` displays 95% of your files, your phone successfully sends and receives 95% of text messages, or Microsoft Word saving 95% of the characters you typed in. That's just not acceptable.
I did exactly what I said I did. I'm using these systems the way they're designed and advertised. I'm following the happy path with tasks that are small, trivial, and easy to check. This is the charitable approach. Yet the system creaks under the lightest load. If Google wants to put on a better show with stronger models, then they should make those the default.
You don't need to make excuses for shoddy engineering from multi-billion dollar corporations. And you're quite welcome to run the same prompt on ChatGPT and evaluate it on your own time.
Fake content and lies. To drive outrage. To influence elections. To distract from real crimes. To overload everyone so they're too tired to fight or to understand. To weaken the concept that anything's true so that you can say anything. Because who cares if the world dies as long as you made lots of money on the way.
Guiding principle of the AI industry
Another way of saying that is that capitalism is the real problem, but I was never anti-capitalist in principle, it's just gotten out of hand in the last 5-10 years. (Not that it hadn't been building to that.)
Capitalism is a tool and it's fine as a tool, to accomplish certain goals while subordinated to other things. Unfortunately it's turned into an ideology (to the point it's worshiped idolatrously by some), and that's where things went off the rails.
> One way to understand an LLM is as an improv machine. It takes a stream of tokens, like a conversation, and says “yes, and then…” This yes-and behavior is why some people call LLMs bullshit machines. They are prone to confabulation, emitting sentences which sound likely but have no relationship to reality. They treat sarcasm and fantasy credulously, misunderstand context clues, and tell people to put glue on pizza.
Yes, there have been improvements on them, but none of those improvements mitigate the core flaw of the technology. The author even acknowledges all of the improvements in the last few months.
I also wonder if I leave my secretary with a ream of papers and ask him for a summary how many will he actually read and understand vs skim and then bullshit? It seems like the capacity for frailty exists in both "species".
[1]: https://link.springer.com/article/10.1007/s10676-024-09775-5
https://philosophersmag.com/large-language-models-and-the-co...
This is true, but I prefer to think of it as "It's delusional to pretend as if human beings are not bullshit machines too".
Lies are all we have. Our internal monologue is almost 100% fantasy. Even in serious pursuits, that's how it works. We make shit up and lie to ourselves, and then only later apply our hard-earned[1] skill prompts to figure out whether or not we're right about it.
How many times have the nerds here been thinking through a great new idea for a design and how clever it would be before stopping to realize "Oh wait, that won't work because of XXX, which I forgot". That's a hallucination right there!
[1] Decades of education!
Models have gotten ridiculously better, they really have, but the scale has increased too, and I don't think we're ready to deal with the onslaught.
Even before LLMs where in the public's discourse, I would have business ask about using AI instead of building some algorithm manually, and when I asked if they had considered the failure rate, they would return either blank stares or say that would count as a bug. To them, AI meant an algorithm just as good as one built to handle all edge cases in business logic, but easier and faster to implement.
We can generally recognize the AIs being off when they deal in our area of expertise, but there is some AI variant of Gell-Mann Amnesia at play that leads us to go back to trusting AI when it gives outputs in areas we are novices in.
Being wrong is not the same as a hallucination. It's a natural step on a journey to being more right. This feels a bit like Andreesen proudly stating he avoids reflection - you can act like that, but the human brain doesn't have to. LLMs have no choice in the matter.
If so, how do we distinguish between code that works and code that doesn't work? Why should we even care?
Hilariously, not by using our brains, that's for sure. You have to have an external machine. We all understand that "testing" and "code review" are different processes, and that's why.
If lies are all we have, then how is this behavior possible?
You're cherry picking my little bit of wordsmithing. Obviously we aren't always wrong. I'm saying that our thought processes stem from hallucinatory connections and are routinely wrong on first cut, just like those of an LLM.
Actually I'm going farther than that and saying that the first cut token stream out of an AI is significantly more reliable than our personal thoughts. Certainly than mine, and I like to think I'm pretty good at this stuff.
Your no-true-scotsman clause basically falsifies that statement for me. Fine, LLMs are, at worst I guess, "non-thoughtful humans". But obviously LLMs are right an awful lot (more so than a typical human, even), and even the thoughtful make mistakes.
So yeah, to my eyes "Humans are NOT different" fits your argument better than your hypothesis.
(Also, just to be clear: LLMs also say "I don't know", all the time. They're just prompted to phrase it as a criticism of the question instead.)
I’m still not a big fan of comparing humans and LLMs because LLMs lack so much of what actually makes us human. We might bullshit or be wrong because of many reasons that just don’t apply to LLMs.