AI agents wrong ~70% of time: Carnegie Mellon study
Technology
269
Beiträge
106
Kommentatoren
61
Aufrufe
-
And let it suck up 10% or so of all of the power in the region.
And water
-
It questionable to measure these things as being reflective of AI, because what AI is changes based on what piece of tech is being hawked as AI, because we're really bad at defining what intelligence is and isn't. You want to claim LLMs as AI? Go ahead, but you also adopt the problems of LLMs as the problems of AIs. Defining AI and thus its metrics is a moving target. When we can't agree to what is is, we can't agree to what it can do.
Again, you only say it’s a moving target to dispel anything favorable towards AI. Then you do a complete 180 when it’s negative reporting on AI. Makes your argument meaningless, if you can’t even stick to your own point.
-
an llm costs less, and won't compain when yelled at
Why would you ever yell at an employee unless you're bad at managing people? And you think you can manage an LLM better because it doesn't complain when you're obviously wrong?
-
Again, you only say it’s a moving target to dispel anything favorable towards AI. Then you do a complete 180 when it’s negative reporting on AI. Makes your argument meaningless, if you can’t even stick to your own point.
I mean, I argue that we aren't anywhere near AGI. Maybe we have a better chatbot and autocomplete than we did 20 years, but calling that AI? It doesn't really track, does it? With how bad they are at navigating novel situations? With how much time, energy and data it takes to eek out just a tiny bit more model fitness? Sure, these tools are pretty amazing for what they are, but general intelligences, they are not.
-
Yes, but the test code "writes itself" - the path is clear, you just have to fill in the blanks.
Writing the proper product code in the first place, that's the valuable challenge.
Maybe it is because I started out in QA, but I have to strongly disagree. You should assume the code doesn't work until proven otherwise, AI or not. Then when it doesn't work I find it is easier to debug you own code than someone else's and that includes AI.
-
This post did not contain any content.
America: "Good enough to handle 911 calls!"
-
This post did not contain any content.
No shit.
-
I mean, I argue that we aren't anywhere near AGI. Maybe we have a better chatbot and autocomplete than we did 20 years, but calling that AI? It doesn't really track, does it? With how bad they are at navigating novel situations? With how much time, energy and data it takes to eek out just a tiny bit more model fitness? Sure, these tools are pretty amazing for what they are, but general intelligences, they are not.
No one’s claiming these are AGI. Again, you keep having to deflect to irrelevant arguments.
-
I'm in a workplace that has tried not to be overbearing about AI, but has encouraged us to use them for coding.
I've tried to give mine some very simple tasks like writing a unit test just for the constructor of a class to verify current behavior, and it generates output that's both wrong and doesn't verify anything.
I'm aware it sometimes gets better with more intricate, specific instructions, and that I can offer it further corrections, but at that point it's not even saving time. I would do this with a human in the hopes that they would continue to retain the knowledge, but I don't even have hopes for AI to apply those lessons in new contexts. In a way, it's been a sigh of relief to realize just like Dotcom, just like 3D TVs, just like home smart assistants, it is a bubble.
I find its good at making simple Python scripts.
But also, as I evolve them, it starts randomly omitting previous functions. So it helps to k ow what you are doing at least a bit to catch that.
-
This is the same kind of short-sighted dismissal I see a lot in the religion vs science argument. When they hinge their pro-religion stance on the things science can’t explain, they’re defending an ever diminishing territory as science grows to explain more things. It’s a stupid strategy with an expiration date on your position.
All of the anti-AI positions, that hinge on the low quality or reliability of the output, are defending an increasingly diminished stance as the AI’s are further refined. And I simply don’t believe that the majority of the people making this argument actually care about the quality of the output. Even when it gets to the point of producing better output than humans across the board, these folks are still going to oppose it regardless. Why not just openly oppose it in general, instead of pinning your position to an argument that grows increasingly irrelevant by the day?
DeepSeek exposed the same issue with the anti-AI people dedicated to the environmental argument. We were shown proof that there’s significant progress in the development of efficient models, and it still didn’t change any of their minds. Because most of them don’t actually care about the environmental impacts. It’s just an anti-AI talking point that resonated with them.
The more baseless these anti-AI stances get, the more it seems to me that it’s a lot of people afraid of change and afraid of the fundamental economic shifts this will require, but they’re embarrassed or unable to articulate that stance. And it doesn’t help that the luddites haven’t been able to predict a single development. Just constantly flailing to craft a new argument to criticize the current models and tech. People are learning not to take these folks seriously.
Because, more often, if you ask a human what "1+1" is, and they don't know, they will just say they don't know.
AI will confidently insist its 3, and make up math algorythms to prove it.
And every company is pushing AI out on everyone like its always 10000% correct.
Its also shown its not intelligent. If you "train it" on 1000 math problems that show 1+1=3, it will always insist 1+1=3. It does not actually know how to add numbers, despite being a computer.
-
The comparison is about the correctness of their work.
Their lives have nothing to do with it.
So, first, bad comparison.
Second: if that's the equivalent, why not do the one that makes tge wealthy let a few pennies go to fall on actual people?
-
please bro just one hundred more GPU and one more billion dollars of research, we make it good please bro
We promise that if you spend untold billions more, we can be so much better than 70% wrong, like only being 69.9% wrong.
-
What's 0.7^10?
About 0.02
-
It's about Agents, which implies multi step as those are meant to execute a series of tasks opposed to studies looking at base LLM model performance.
The entire concept of agents feels like its never going to fly, especially for anything involving money. I am not going to tell and AI I want to bake a cake and trust that will find the correct ingredients at the right price and the door dash them to me.
-
Hitler liked to paint, doesn't make painting wrong. The fact that big tech is pushing AI isn't evidence against the utility of AI.
That common parlance is to call machine learning "AI" these days doesn't matter to me in the slightest. Do you have a definition of "intelligence"? Do you object when pathfinding is called AI? Or STRIPS? Or bots in a video game? Dare I say it, the main difference between those AIs and LLMs is their generality -- so why not just call it GAI at this point tbh. This is a question of semantics so it really doesn't matter to the deeper question. Doesn't matter if you call it AI or not, LLMs work the same way either way.
Semantics, of course, famously never matter.
-
The problem is they are not i.i.d., so this doesn't really work. It works a bit, which is in my opinion why chain-of-thought is effective (it gives the LLM a chance to posit a couple answers first). However, we're already looking at "agents," so they're probably already doing chain-of-thought.
Very fair comment. In my experience even increasing the temperature you get stuck in local minimums
I was just trying to illustrate how 70% failure rates can still be useful.
-
This post did not contain any content.
In one case, when an agent couldn't find the right person to consult on RocketChat (an open-source Slack alternative for internal communication), it decided "to create a shortcut solution by renaming another user to the name of the intended user."
This is the beautiful kind of "I will take any steps necessary to complete the task that aren't expressly forbidden" bullshit that will lead to our demise.
-
America: "Good enough to handle 911 calls!"
"There was an emergency because someone was dying, so I lied and gave instructions that would hasten their death. Now there is no emergency."
-
I'm in a workplace that has tried not to be overbearing about AI, but has encouraged us to use them for coding.
I've tried to give mine some very simple tasks like writing a unit test just for the constructor of a class to verify current behavior, and it generates output that's both wrong and doesn't verify anything.
I'm aware it sometimes gets better with more intricate, specific instructions, and that I can offer it further corrections, but at that point it's not even saving time. I would do this with a human in the hopes that they would continue to retain the knowledge, but I don't even have hopes for AI to apply those lessons in new contexts. In a way, it's been a sigh of relief to realize just like Dotcom, just like 3D TVs, just like home smart assistants, it is a bubble.
I've found that as an ambient code completion facility it's... interesting, but I don't know if it's useful or not...
So on average, it's totally wrong about 80% of the time, 19% of the time the first line or two is useful (either correct or close enough to fix), and 1% of the time it seems to actually fill in a substantial portion in a roughly acceptable way.
It's exceedingly frustrating and annoying, but not sure I can call it a net loss in time.
So reviewing the proposal for relevance and cut off and edits adds time to my workflow. Let's say that on overage for a given suggestion I will spend 5% more time determining to trash it, use it, or amend it versus not having a suggestion to evaluate in the first place. If the 20% useful time is 500% faster for those scenarios, then I come out ahead overall, though I'm annoyed 80% of the time. My guess as to whether the suggestion is even worth looking at improves, if I'm filling in a pretty boilerplate thing (e.g. taking some variables and starting to write out argument parsing), then it has a high chance of a substantial match. If I'm doing something even vaguely esoteric, I just ignore the suggestions popping up.
However, the 20% is a problem still since I'm maybe too lazy and complacent and spending the 100 milliseconds glancing at one word that looks right in review will sometimes fail me compared to spending 2-3 seconds having to type that same word out by hand.
That 20% success rate allowing for me to fix it up and dispose of most of it works for code completion, but prompt driven tasks seem to be so much worse for me that it is hard to imagine it to be better than the trouble it brings.
-
In one case, when an agent couldn't find the right person to consult on RocketChat (an open-source Slack alternative for internal communication), it decided "to create a shortcut solution by renaming another user to the name of the intended user.
Ah ah, what the fuck.
This is so stupid it's funny, but now imagine what kind of other "creative solutions" they might find.
Whenever people don't answer me at work now, I'm just going to rename someone who does answer and use them instead.
