938
AI agents wrong ~70% of time: Carnegie Mellon study (www.theregister.com)
submitted 1 year ago by to c/technology@lemmy.world
246 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 50 points 1 year ago (23 children)

LLMs are like a multitool, they can do lots of easy things mostly fine as long as it is not complicated and doesn't need to be exactly right. But they are being promoted as a whole toolkit as if they are able to be used to do the same work as effectively as a hammer, power drill, table saw, vise, and wrench.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 23 child comments
    •
  • [–] 9 points 1 year ago

    Because the tech industry hasn't had a real hit of it's favorite poison "private equity" in too long.

    The industry has played the same playbook since at least 2006. Likely before, but that's when I personally stated seeing it. My take is that they got addicted to the dotcom bubble and decided they can and should recreate the magic evey 3-5 years or so.

    This time it's AI, last it was crypto, and we've had web 2.0, 3.0, and a few others I'm likely missing.

    But yeah, it's sold like a panacea every time, when really it's revolutionary for like a handful of tasks.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 38 points 1 year ago (14 children)

    Exactly! LLMs are useful when used properly, and terrible when not used properly, like any other tool. Here are some things they're great at:

    • writer's block - get something relevant on the page to get ideas flowing
    • narrowing down keywords for an unfamiliar topic
    • getting a quick intro to an unfamiliar topic
    • looking up facts you're having trouble remembering (i.e. you'll know it when you see it)

    Some things it's terrible at:

    • deep research - verify everything an LLM generated of accuracy is at all important
    • creating important documents/code
    • anything else where correctness is paramount

    I use LLMs a handful of times a week, and pretty much only when I'm stuck and need a kick in a new (hopefully right) direction.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 14 child comments
    •
  • [–] 33 points 1 year ago* (10 children)
    • narrowing down keywords for an unfamiliar topic
    • getting a quick intro to an unfamiliar topic
    • looking up facts you’re having trouble remembering (i.e. you’ll know it when you see it)

    I used to be able to use Google and other search engines to do these things before they went to shit in the pursuit of AI integration.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 10 child comments
    •
  • [–] 4 points 1 year ago (9 children)

    Google search was pretty bad at each of those, even when it was good. Finding new keywords to use is especially difficult the more niche your area of search is, and I've spent hours trying different combinations until I found a handful of specific keywords that worked.

    Likewise, search is bad for getting a broad summary, unless someone has bothered to write it on a blog. But most information goes way too deep and you still need multiple sources to get there.

    Fact lookup is one the better uses for search, but again, I usually need to remember which source had what I wanted, whereas the LLM can usually pull it out for me.

    I use traditional search most of the time (usually DuckDuckGo), and LLMs if I think it'll be more effective. We have some local models at work that I use, and they're pretty helpful most of the time.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 9 child comments
    •
  • [–] 7 points 1 year ago (1 child)

    No search engine or AI will be great with vague descriptions of niche subjects because by definition niche subjects are too uncommon to have a common pattern of 'close enough'.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 4 points 1 year ago

    Which is why I use LLMs to generate keywords for niche subjects. LLMs are pretty good at throwing out a lot of related terminology, which I can use to find the actually relevant, niche information.

    I wouldn't use one to learn about a niche subject, but I would use one to help me get familiar w/ the domain to find better resources to learn about it.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 5 points 1 year ago (6 children)

    It is absolutely stupid, stupid to the tune of "you shouldn't be a decision maker", to think an LLM is a better use for "getting a quick intro to an unfamiliar topic" than reading an actual intro on an unfamiliar topic. For most topics, wikipedia is right there, complete with sources. For obscure things, an LLM is just going to lie to you.

    As for "looking up facts when you have trouble remembering it", using the lie machine is a terrible idea. It's going to say something plausible, and you tautologically are not in a position to verify it. And, as above, you'd be better off finding a reputable source. If I type in "how do i strip whitespace in python?" an LLM could very well say "it's your_string.strip()". That's wrong. Just send me to the fucking official docs.

    There are probably edge or special cases, but for general search on the web? LLMs are worse than search.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 9 points 1 year ago (5 children)

    than reading an actual intro on an unfamiliar topic

    The LLM helps me know what to look for in order to find that unfamiliar topic.

    For example, I was tasked to support a file format that's common in a very niche field and never used elsewhere, and unfortunately shares an extension with a very common file format, so searching for useful data was nearly impossible. So I asked the LLM for details about the format and applications of it, provided what I knew, and it spat out a bunch of keywords that I then used to look up more accurate information about that file format. I only trusted the LLM output to the extent of finding related, industry-specific terms to search up better information.

    Likewise, when looking for libraries for a coding project, none really stood out, so I asked the LLM to compare the popular libraries for solving a given problem. The LLM spat out a bunch of details that were easy to verify (and some were inaccurate), which helped me narrow what I looked for in that library, and the end result was that my search was done in like 30 min (about 5 min dealing w/ LLM, and 25 min checking the projects and reading a couple blog posts comparing some of the libraries the LLM referred to).

    I think this use case is a fantastic use of LLMs, since they're really good at generating text related to a query.

    It’s going to say something plausible, and you tautologically are not in a position to verify it.

    I absolutely am though. If I am merely having trouble recalling a specific fact, asking the LLM to generate it is pretty reasonable. There are a ton of cases where I'll know the right answer when I see it, like it's on the tip of my tongue but I'm having trouble materializing it. The LLM might spit out two wrong answers along w/ the right one, but it's easy to recognize which is the right one.

    I'm not going to ask it facts that I know I don't know (e.g. some historical figure's birth or death date), that's just asking for trouble. But I'll ask it facts that I know that I know, I'm just having trouble recalling.

    The right use of LLMs, IMO, is to generate text related to a topic to help facilitate research. It's not great at doing the research though, but it is good at helping to formulate better search terms or generate some text to start from for whatever task.

    general search on the web?

    I agree, it's not great for general search. It's great for turning a nebulous question into better search terms.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 5 points 1 year ago (2 children)

    One word of caution with AI searxh is that it's weirdly vulnerable to SEO.

    If you search for "best X for Y" and a company has an article on their blog about how their product solves a problem the AI can definitely summarize that into a "users don't like that foolib because of ...". At least that's been my experience looking for software vendors.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 1 year ago* (last edited 1 year ago) (1 child)

    It's a bit frustrating that finding these tools useful is so often met with it can't be useful for that, when it definitely is.

    More than any other tool in history LLMs have a huge dose of luck involved and a learning curve on how to ask the right things the right way. And those method change and differ between models too.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 1 year ago (2 children)

    I will say I've found LLM useful for code writing but I'm not coding anything real at work. Just bullshit like SQL queries or Excel macro scripts or Power Automate crap.

    It still fucks up but if you can read code and have a feel for it you can walk it where it needs to be (and see where it screwed up)

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 9 points 1 year ago* (1 child)

    Exactly. Vibe coding is bad, but generating code for something you don't touch often but can absolutely understand is totally fine. I've used it to generate SQL queries for relatively odd cases, such as CTEs for improving performance for large queries with common sub-queries. I always forget the syntax since I only do it like once/year, and LLMs are great at generating something reasonable that I can tweak for my tables.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 5 points 1 year ago (4 children)

    and doesn't need to be exactly right

    What kind of tasks do you consider that don't need to be exactly right?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 1 year ago*

    Description generators for TTRPGs, as you will read through them afterwards anyway and correct when necessary.

    Generating lists of ideas. For creative writing, getting a bunch of ideas you can pick and choose from that fit the narrative you want.

    A search engine like Perplexity.ai which after searching summarizes the web page and adds a link to the page next to it. If the summary seems promising, you go to the real page to verify the actual information.

    Simple code like HTML pages and boilerplate code that you will still review afterwards anyway.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 2 points 1 year ago*

    Most. I've used ChatGPT to sketch an outline of a document, reformulate accomplishments into review bullets, rephrase a task I didnt understand, and similar stuff. None of it needed to be anywhere near perfect or complete.

    Edit: and my favorite, "what's the word for..."

  • permalink
  • fedilink
  • source
  • parent
  • [–] 1 point 1 year ago

    Things that are inspiration or for approximations. Layout examples, possible correlations between data sets that need coincidence to be filtered out, estimating time lines, and basically anything that is close enough for a human to take the output and then do something with it.

    For example, if you put in a list of ingredients it can spit out recipes that may or may not be what you want, but it can be an inspiration. Taking the output and cooking without any review and consideration would be risky.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 1 point 1 year ago

    It is truly terrible marketing. It's been obvious to me for years the value is in giving it to people and enabling them to do more with less, not outright replacing humans, especially not expert humans.

    I use AI/LLMs pretty much every day now. I write MCP servers and automate things with it and it's mind blowing how productive it makes me.

    Just today I used these tools in a highly supervised way to complete a task that would have been a full day of tedius work, all done in an hour. That is fucking fantastic, it's means I get to spend that time on more important things.

    It's like giving an accountant excel. Excel isn't replacing them, but it's taking care of specific tasks so they can focus on better things.

    On the reliability and accuracy front there is still a lot to be desired, sure. But for supervised chats where it's calling my tools it's pretty damn good.

  • permalink
  • fedilink
  • source
  • parent
  • [–] -1 points 1 year ago

    That's because they look like "talking machines" from various sci-fi. Normies feel as if they are touching the very edge of the progress. The rest of our life and the Internet kinda don't give that feeling anymore.

  • permalink
  • fedilink
  • source
  • parent