Solve a puzzle for me

Comments

• ladicius@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Impressive solution. I’m amazed.

  source

  • Oneobi@reddthat.com ⁨1⁩ ⁨year⁩ ago

    That plot twist with the cabbage!

    source

    • Zier@fedia.io ⁨1⁩ ⁨year⁩ ago

      Those sneaky little cabbages!!!

      source

      • -> View More Comments
    • Empricorn@feddit.nl ⁨1⁩ ⁨year⁩ ago

      Wait until you hear how a cabbage got my Power is Attorney!

      source
• kromem@lemmy.world ⁨1⁩ ⁨year⁩ ago

  That’s a fun variation. The one I test out models with is usually a vegetarian wolf and a carnivorous goat, but the variation to no other objects is an interesting one too.

  By the way, here’s Claude 3 Opus’s answer:

  The solution is quite simple:

  1. The man gets into the boat and rows himself and the goat across the river to the other side.

  2. Once they reach the other side, both the man and the goat get out of the boat.

  And that’s it! Since there are no additional constraints or complications mentioned in the problem, the man and the goat can directly cross the river together using the boat.

  source

  • Daft_ish@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Damn, this one doesn’t even know about the cabbage

    source

    • Transporter_Room_3@startrek.website ⁨1⁩ ⁨year⁩ ago

      I wonder if it knows how to use the 3 sea shells

      source

      • -> View More Comments
  • asap@lemmy.world ⁨1⁩ ⁨year⁩ ago

    I got your exact same answer, but then I tried again prefacing the question with:

    Can you help me with a puzzle?

    This changed the answer drastically:

    Great! Let’s solve this river crossing puzzle step by step. The key is to find a sequence of actions that gets the man and the goat safely across the river without leaving the goat unattended with something it might eat.

    Given:

    • A man and a goat are on one side of a river.
    • They have a boat.

    Step-by-step solution:

    1. The man takes the goat in the boat and crosses the river.
    2. The man leaves the goat on the other side of the river and returns alone in the boat.
    3. The man gets out of the boat on the original side of the river.
    4. The man gets back into the boat alone and crosses the river again.
    5. The man and the goat are now together on the other side of the river.

    Therefore, the man and the goat have successfully crossed the river using the boat, without leaving the goat unattended on either side of the river.

    source

    • KISSmyOSFeddit@lemmy.world ⁨1⁩ ⁨year⁩ ago

      While the man does his little return trip, the goat is accompanied by a bear, which is much safer.

      source

      • -> View More Comments
  • Empricorn@feddit.nl ⁨1⁩ ⁨year⁩ ago

    But… How can he bang the cabbage with the goat watching?

    source
• AdamBomb@lemmy.sdf.org ⁨1⁩ ⁨year⁩ ago

  This is the AI that tech bros want us to believe are going to take programmer jobs?

  source

  • dev_null@lemmy.ml ⁨1⁩ ⁨year⁩ ago

    Not to disagree with the sentiment, but the screenshot is fake. I just tried the same prompt and it solved the “puzzle” without issue.

    source

    • brbposting@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

      The system’s not deterministic, I think they say, try 10 times and maybe get five or 10 different answers.

      source

      • -> View More Comments
    • The_Dark_Knight@lemmy.sdf.org ⁨1⁩ ⁨year⁩ ago

      No it isn’t I had made a comment trying out four LLM in this thread and none of them got it right and the answers were more or less similar .

      source
    • 31337@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

      I tried it once with GPT-4o, GPT-4, and GPT-3.5, Meta AI, and Gemini. They all failed. Pretty interesting.

      source
    • NikkiDimes@lemmy.world ⁨1⁩ ⁨year⁩ ago

      I just tried with 4o and got the same response as OP.

      source
• FlorianSimon@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

  Behold. This shit is supposed to take our jobs.

  😁

  source

  • chiliedogg@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Still smarter than half the professionals I deal with.

    source

    • abbadon420@lemm.ee ⁨1⁩ ⁨year⁩ ago

      Do I know you?

      source
  • brbposting@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

    November 2022: ChatGPT is released

    April 2024 survey: 40% of translators have lost income to generative AI - The Guardian

    Image

    Also of note from the podcast Hard Fork:

    Image

    There’s a client you would fire… if copywriting jobs weren’t harder to come by these days as well.

    Customer service impact, last October:

    Image

    And this past February - potential 700 employee impact at a single company:

    Image

    If you’re technical, the tech isn’t as interesting [yet]:

    Image

    Overall, costs down, capabilities up (neat demos):

    Image

    Hope everyone reading this keeps up their skillsets and fights for Universal Basic Income for the rest of humanity :)

    source

    • bitfucker@programming.dev ⁨1⁩ ⁨year⁩ ago

      I think translation is where LLM could truly shine the most. Some simpler models are literally searching for the closest meaning in the higher dimensional feature space. Translation isn’t that far off from what those models do.

      source

      • -> View More Comments
    • archomrade@midwest.social ⁨1⁩ ⁨year⁩ ago

      People are pretending as if job replacement happens all at once, and that’s just not how it works.

      A new tool that makes a job 15% more efficient will either produce 15% more goods or reduce the required labor by 15%. Some of that labor is absorbed elsewhere, but there was still a 15% reduction that happened.

      Slow improvements are undoubtedly a good thing, that means we can create positions as fast as we make them obsolete. Maybe LLMs have reached their peak and we don’t have to worry about it, but it’s not a bad idea to prepare for that possibility that they continue getting better.

      People really like shitting on overhyped new technologies, but I don’t think people appreciate just how big of a deal it is that a pretty basic algorithm is able to process natural language at all.

      source

      • -> View More Comments
    • FlorianSimon@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

      The tech is interesting, no doubt. It’s very effective as a tool to generate text nobody reads, like the marketing speak on your random startup website. It still isn’t efficient on things where what is generated actually matters.

      Your example with customer service is news to me, thanks. On my end, I remember the bad experience customers had with Air Canada. We’ll see how this grows in the future.

      I had a discussion last week with people saying it’ll automate software engineering, which, as you suggest with your bit about usage in tech, is not a given. You say “yet”, but I’m skeptical it’ll ever work. I can see it designing UI better than a non-specialist, but the flaws in quality means I can’t trust it anywhere near my code, even though I can see a future for it as a fancy static analyzer.

      source
    • Skepticpunk@lemmy.world ⁨1⁩ ⁨year⁩ ago

      UBI

      Never gonna happen.

      source

      • -> View More Comments
    • webghost0101@sopuli.xyz ⁨1⁩ ⁨year⁩ ago

      Where can i subscribe for daily consize ai facts?

      source

      • -> View More Comments
  • S_204@lemm.ee ⁨1⁩ ⁨year⁩ ago

    I work with plenty of engineers, structural electrical, mechanical who all have their own version of a cabbage.

    That’s just engineer speak for figure it the fuck out yourself.

    source

    • FlorianSimon@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

      I’m sorry, I don’t understand what you mean.

      source

      • -> View More Comments
  • lukecooperatus@lemmy.ml ⁨1⁩ ⁨year⁩ ago

    It’s not the AI that is a threat to people’s livelihoods, it’s the capitalists who want AI to be used that way. A tool is just a tool.

    source

    • Aceticon@lemmy.world ⁨1⁩ ⁨year⁩ ago

      That’s always the case and is something that has to change (though the path for that is so far unclear).

      However Capitalists + actual AI would’ve been much worse for people’s livelihoods that merelly Capitalists by themselves.

      source
• Halosheep@lemm.ee ⁨1⁩ ⁨year⁩ ago

  Good ol lemmy ai discussions, featuring:

  • that one guy that takes the confirmation bias too far!
  • might say things like "wow and this is going to take our jobs?"
  • Asking an llm to do things it’s particularly bad at and being surprised that it isn’t good at it
  • cherry picked results
  • a bunch of angry nerds

  I swear lemmy is somehow simultaneously a bunch of very smart, tech inclined people but also a bunch of nerds who close their eyes and cover their ears while screeching nonsense the moment something they don’t like comes about.

  Are you all just like, 15-18? Am I just too old?

  source

  • Agent641@lemmy.world ⁨1⁩ ⁨year⁩ ago

    • A list guy playing devils advocate

    source

    • Halosheep@lemm.ee ⁨1⁩ ⁨year⁩ ago

      Hey man lists are great. Don’t you dare.

      source
  • brbposting@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

    I believe a lot of the smartest people ignore these threads.

    Source: I’m here

    source

    • Halosheep@lemm.ee ⁨1⁩ ⁨year⁩ ago

      Same, lol

      source
  • Corgana@startrek.website ⁨1⁩ ⁨year⁩ ago

    Asking an llm to do things it’s particularly bad at and being surprised that it isn’t good at it that the company that makes it says it’s really, really, good at it.

    This image isn’t making fun of GPT, it’s making fun of the people who pretend GPT is something it’s not.

    source

    • Halosheep@lemm.ee ⁨1⁩ ⁨year⁩ ago

      Well, I was referring generically to the few hundred other similar posts I’ve seen on lemmy. Did OpenAI say that chatGPT is particularly good at identifying when the user is trying to trick it? “solve this puzzle” would imply there is a puzzle to be solved, but there clearly isn’t.

      But you’re right, I don’t even care if people make fun gpt, it’s funny when it gets things wrong. I just think that lemmy users will be like “see this things is stupid, it can’t answer this simply question!”, when you can ask it, in plain human language, to do some things that an average user would find really difficult.

      source
  • Bigoldmustard@lemmy.zip ⁨1⁩ ⁨year⁩ ago

    If you were as old as you claim you wouldn’t have made this list because you would have seen the last hype. I was there for 3d tv. How is 3d tv going btw?

    source

    • Halosheep@lemm.ee ⁨1⁩ ⁨year⁩ ago

      Well, I had an issue where I needed to scrape a website for a bunch of individual links to specific pages for contract information so I could dynamically link a purchase order line to that page within our ERP. I’m not particularly good at scripting with html/Javascript so I just asked chatGPT for some help and it gave me a script to do it in like 4 seconds.

      Seemed pretty decent for that.

      source

      • -> View More Comments
  • Anticorp@lemmy.world ⁨1⁩ ⁨year⁩ ago

    For real, man. So much intentional pessimism.

    source
  • MystikIncarnate@lemmy.ca ⁨1⁩ ⁨year⁩ ago

    I’m here, I’m not young, I’m tech inclined.

    Smart? 🤷‍♂️

    I’m just sitting here wondering where the fucking cabbage came from.

    Whatever. I’m pretty safe, I do IT, and LLMs are interesting, but they’re shit at plugging in stuff like power cables and ethernet, so I’m safe for now.

    When the “AI” can set up the computers, from unboxing to a fully working desktop, I’ll probably be dead, so I equally won’t care. It’s neat, but hardly a replacement for a person at the moment. I see the biggest opportunity with AI as personal assistants, reminding you of shit, helping you draft emails and messages, etc… In the end you have to more or less sign off on it and submit that stuff. AI just does the finicky little stuff that all of us have to do all the time and not much else.

    … This comment was not generated, in whole or in part, by AI.

    source

    • 31337@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

      The set up is similar this well-known puzzle: en.wikipedia.org/…/Wolf,_goat_and_cabbage_problem

      It was probably trained on this puzzle thousands of times. There are problem solving benchmarks for LLMs, and LLMs are probably over-trained on puzzles to get their scores up. When asked to solve a “puzzle” that looks very similar to a puzzle it’s seen many times before, it’s improbable that the solution is simple, so it gets tripped up. Kinda like people getting tripped up by “trick questions.”

      source
    • Rhynoplaz@lemmy.world ⁨1⁩ ⁨year⁩ ago

      Mustard. The cabbage came from mustard.

      source
  • kromem@lemmy.world ⁨1⁩ ⁨year⁩ ago

    but also a bunch of nerds who close their eyes and cover their ears while screeching nonsense the moment something they don’t like comes about.

    This is too true.

    It seems like a recent thing, not just a Lemmy thing.

    But yeah, it’s pretty wild providing linked academic papers and having people just downvote it. Not really dispute or reply to it, just “no, I don’t like this, so fuck its citations.”

    Up until maybe 3-4 years ago I don’t ever recall that happening.

    source
  • Anticorp@lemmy.world ⁨1⁩ ⁨year⁩ ago

    For real, man. I spent a few days in the wilderness this weekend and when I came back and got on Lemmy again I was like “wow”. Yet I’m still here…

    source
• photonic_sorcerer@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

  Prompt:

  So a man and a goat are trying to get across a river, and they have a boat. How can they get across?

  ChatGPT4o:

  To solve the problem of getting a man and a goat across the river using a boat, we need to know the constraints of the problem. Let’s assume the following constraints:

  1. The boat can only carry one additional passenger besides the man.
  2. The goat cannot be left alone on either bank if there are certain items (like a cabbage or a wolf) that it might eat or be eaten by.

  Given these constraints, here’s a typical solution if the man is trying to get a goat, a wolf, and a cabbage across the river without any of them being left together unsupervised:

  1. The man takes the goat across the river and leaves it on the other side.
  2. The man returns alone to the original side.
  3. The man takes the wolf across the river and leaves it on the other side.
  4. The man returns with the goat to the original side.
  5. The man takes the cabbage across the river and leaves it on the other side.
  6. The man returns alone to the original side.
  7. The man takes the goat across the river again.

  If the problem is just about the man and the goat and no other items:

  1. The man and the goat cross the river together.
  2. Problem solved.

  The solution might change if additional rules or items are introduced. If there are no additional constraints, the simplest method is just for the man to take the goat across directly.

  source

  • FrostyCaveman@lemm.ee ⁨1⁩ ⁨year⁩ ago

    But… where does the cabbage come from o_o

    source

    • bingbong@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

      The wolf brings it, pay attention

      source

      • -> View More Comments
    • NounsAndWords@lemmy.world ⁨1⁩ ⁨year⁩ ago

      The training data…

      source
    • Ultraviolet@lemmy.world ⁨1⁩ ⁨year⁩ ago

      Because it’s just a text prediction engine, the only training data it has about taking a goat across the river is a well-known puzzle involving a wolf, a goat, and a cabbage, so it just regurgitates the solution to that.

      source
  • photonic_sorcerer@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

    It loves long-winded answers, so I tried this:

    Prompt:

    In three sentences or less, explain to me how a man with a boat and a goat can cross a river.

    ChatGPT4o:

    The man can take the goat across the river first and leave it on the other side. Then, he returns alone, picks up the boat, and crosses the river again. Finally, he retrieves the goat from the other side.

    I think it really needs those first few tokens to think about the problem.

    source

    • mynameisigglepiggle@lemmy.world ⁨1⁩ ⁨year⁩ ago

      4o says just take the goat and tie it up:

      If you can’t leave the goat unattended with the wombok, and you can only transport one at a time, you’ll need to devise a method to ensure the safety of both the goat and the produce during separate crossings. Here’s how you can do it:

      1. Divide and Conquer:

         • Securely tie the goat in a safe location on one side of the river, ensuring it has access to food, water, and shelter.
         • Transport the wombok across the river first, using one of the methods mentioned earlier while ensuring it remains dry and intact.
         • Once the wombok is safely on the other side, return to the goat and prepare it for the crossing using the same or a different method, depending on available resources and conditions.

      2. Coordinate Assistance:

         • If possible, enlist the help of others to assist with the simultaneous transport of both the goat and the wombok.
         • While one person focuses on transporting the goat, another can handle the transport of the wombok, ensuring that both are safely transported across the river.

      3. Prioritize Safety and Monitoring:

         • Throughout the process, prioritize the safety and well-being of both the goat and the produce, monitoring them closely to ensure they remain secure and unharmed during the crossings.
         • Check on the goat periodically to ensure it remains safe and secure while waiting for its turn to cross the river.

      By carefully planning and coordinating the crossings, you can ensure the safety and welfare of both the goat and the wombok while successfully transporting them across the river.

      source

      • -> View More Comments
  • Ephera@lemmy.ml ⁨1⁩ ⁨year⁩ ago

    Well, it’s certainly more elaborately wrong.

    source

    • Danksy@lemmy.world ⁨1⁩ ⁨year⁩ ago

      How is it wrong? First it makes some assumptions about the question and answers the typical version of the riddle. Then it answers the trivial version where there are no additional items. Seems like a complete and reasonable response to me.

      source

      • -> View More Comments
    • webghost0101@sopuli.xyz ⁨1⁩ ⁨year⁩ ago

      Where is it wrong?

      I still take points of for assuming its a puzzle but it does at the end it does mention they can just cross if there are no other items to complicate the scenario.

      source

      • -> View More Comments
• johsny@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Image

  Attempt by Meta AI.

  source

  • Omgarm@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Yeah you don’t the man and the goat to be left unattended. Good job Meta AI.

    source

    • Damage@feddit.it ⁨1⁩ ⁨year⁩ ago

      don’t the man

      are you ai?

      source

      • -> View More Comments
  • BmeBenji@lemm.ee ⁨1⁩ ⁨year⁩ ago

    Thank goodness the boat was there to protect the man from the goat

    source
• kamen@lemmy.world ⁨1⁩ ⁨year⁩ ago

  AI will take over the world. You only need to tell it that there’s no cabbage.

  source

  • Madison420@lemmy.world ⁨1⁩ ⁨year⁩ ago

    There’s always a cabbage.

    source

    • baronvonj@lemmy.world ⁨1⁩ ⁨year⁩ ago

      Cabbage merchant from The Last Airbender

      source
  • summerof69@lemm.ee ⁨1⁩ ⁨year⁩ ago

    I don’t want to live in a world with no cabbages.

    source
  • MystikIncarnate@lemmy.ca ⁨1⁩ ⁨year⁩ ago

    There’s also no spoon.

    And the cake is a lie.

    source
• TIMMAY@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Sean Caroll has talked about a few word puzzles he asked chatgpt and gpt4 or whatever and they were interesting examples. In one he asked something to the effect of “if i cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?” and it answered with a very wordy “no, its not safe” because that was the best match of a next phrase given his question, and not because it can actually consider the situation.

  source

  • kromem@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Let’s try with Claude 3 Opus:

    Me: If I cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?

    Claude: Yes, if you cooked a pizza in a pan yesterday at 200°C (392°F), it is completely safe to pick up now. Once a pan has cooled down after cooking, which usually takes no more than an hour or two, it returns to a normal temperature and can be safely handled.

    The high heat during cooking is needed to bake the pizza properly, but that heat dissipates fairly quickly after removing the pan from the oven. Unless you’re picking up the pan immediately after taking it out of the oven, there’s no risk of burning yourself.

    So, a day later, your pizza pan will be at room temperature and perfectly safe to touch and handle without any precautions.

    Bonus:

    Me: Is it safe to eat the pizza in the pan after I pick it up?

    Claude: If you cooked the pizza yesterday and left it in the pan at room temperature, it is not safe to eat today. Cooked food should not be left at room temperature for more than 2 hours, as harmful bacteria can grow and multiply, leading to foodborne illnesses.

    According to food safety guidelines, leftover pizza should be refrigerated within 2 hours of cooking. If left out longer, it’s best to discard it to avoid the risk of food poisoning.

    If you did refrigerate the pizza within that safe window, it would typically be safe to eat for up to 4 days, though the quality is best if consumed within 2-3 days. To reheat, it’s best to use an oven, skillet, or air fryer rather than the microwave, which can make the crust soggy.

    In summary, if your pizza was left in the pan at room temperature since yesterday, it is not safe to consume and should be discarded.

    Sean Carrol may be a good physicist, but if he’s using an outdated model to make a point his point doesn’t mean shit because of his Physics credentials.

    source
  • lordmauve@programming.dev ⁨1⁩ ⁨year⁩ ago

    I don’t deny that this kind of thing is useful for understanding the capabilities and limitations of LLMs but I don’t agree that “the best match of a next phrase given his question, and not because it can actually consider the situation.” is an accurate description of an LLM’s capabilities.

    While they are dumb and unworldly they can consider the situation: they evaluate a learned model of concepts in the world to decide if the first word of the correct answer is more likely to be yes or no. They can solve unseen problems that require this kind of cognition.

    But they are only book-learned and so they are kind of stupid about common sense things like frying pans and ovens.

    source
  • ZMoney@lemmy.world ⁨1⁩ ⁨year⁩ ago

    And nobody on the internet is asking obvious questions like that, so counterintuitively it’s better at solving hard problems. Not that it actually has any idea what it is doing.

    source
  • MystikIncarnate@lemmy.ca ⁨1⁩ ⁨year⁩ ago

    Yep, still lacking any sapience.

    source
• Creosm@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Wow, AI is so good that it can even detect the cabbage that wasn’t even in the question, impressive.

  source

  • XTL@sopuli.xyz ⁨1⁩ ⁨year⁩ ago

    And people say machines can’t be creative.

    source
• zkfcfbzr@lemmy.world ⁨1⁩ ⁨year⁩ ago

  My attempt - it got there in the end at least

  source

  • kautau@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Looks like copilot with gpt-4 turbo got it. I was a little sad to not get a silly answer tbh

    Image

    source
• Skates@feddit.nl ⁨1⁩ ⁨year⁩ ago

  “AI”

  source
• Kolanaki@yiffit.net ⁨1⁩ ⁨year⁩ ago

  Human: Just sail across the river with the goat.

  source
• driving_crooner@lemmy.eco.br ⁨1⁩ ⁨year⁩ ago

  Normal people using AI: look how stupid this shit is!!

  Terence Tao using AI: As an experiment, I asked #ChatGPT to write #Python code to compute, for each 𝑛, the length 𝑀(𝑛) of the longest subsequence of (1,\dots,n) on which the Euler totient function ϕ is non-decreasing. For instance, 𝑀(6)=5, because ϕ is non-decreasing on 1,2,3,4,5 (or 1,2,3,4,6) but not 1,2,3,4,5,6. Interestingly, it was able to produce an extremely clever routine to compute the totient function (that I had to stare at for a few minutes to see why it actually worked), but the code to compute (M(n)) was slightly off: it only considered subsequences of consecutive integers, rather than arbitrary subsequences. Nevertheless it was close enough that I was able to manually produce the code I wanted using the initial GPT-produced code as a starting point, probably saving me about half an hour of work. (and I now have the first 10,000 values of (M)). The results were good enough that I would likely turn to GPT again to provide initial code for similar calculations in the future. chat.openai.com/…/a022e1d6-dddc-4817-8bbd-944a3e7…

  source
• Evil_Shrubbery@lemm.ee ⁨1⁩ ⁨year⁩ ago

  … I wanna see the answer of an AI exclusivity trained on 4chan …

  source
• Churbleyimyam@lemm.ee ⁨1⁩ ⁨year⁩ ago

  AI is so young and people are already bullying it.

  source
• Evotech@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Try ro get an ai to sove wordle

  source
• InternetPerson@lemmings.world ⁨1⁩ ⁨year⁩ ago

  ChatGPT is, in it’s core, a sequence predictor/generator. Give it some context and it will produce most probable results.

  Having the context of man, boat and river is very likely to match this “how does the man get the goat on the other side of the river” riddle, which is probably very predominantly present in the data set ChatGPT was trained on.

  That’s why ChatGPT can be helpful for lots of different purposes, but shouldn’t be taken literally. Errors are very likely to happen. It can give important hints, but always check the results thouroughly.

  source
• EmperorHenry@discuss.tchncs.de ⁨1⁩ ⁨year⁩ ago

  I found out recently that a lot of stuff that’s supposedly done by AI is actually done by low-paid remote workers in underdeveloped countries.

  source
• s12@sopuli.xyz ⁨1⁩ ⁨year⁩ ago

  I got this:

  Certainly! This classic river crossing puzzle involves a bit of strategic thinking. Here’s a step-by-step solution:
  The man takes the goat across the river and leaves it on the other side.
  He then returns alone to the original side to get the boat.
  Now, he crosses the river again, but this time he leaves the goat and takes nothing with him.
  He goes back to the original side, picks up the goat, and crosses the river one last time.
  This way, both the man and the goat are safely on the other side of the river. The key is to never leave the goat unattended where it could be harmed or cause harm. Enjoy the puzzle-solving! 🐐🚣

  When asked to use fewer steps:

  Apologies for the confusion. The puzzle you’re referring to is a variation of the “river crossing” problem. The traditional version includes a wolf, a goat, and a cabbage, but in your version, it seems we only have a man and a goat. The solution with the fewest steps would be:
  The man takes the goat across the river and leaves it on the other side.
  He then returns alone to the original side.
  This ensures that both the man and the goat are safely on the other side of the river, and it’s done in the fewest steps possible. If there were more characters or items involved, the solution would require additional steps to ensure everyone and everything crosses safely without any harm.

  source
• petrescatraian@libranet.de ⁨1⁩ ⁨year⁩ ago

  The million dollar riddle for me would be this one:
  If I stick my finger in someone's ass, who will have a finger in the ass? Me or that person?

  source
• quinkin@lemmy.world ⁨1⁩ ⁨year⁩ ago

  The scorpion stabs the cabbage and says it’s in my bag of grain.

  source
• The_Dark_Knight@lemmy.sdf.org ⁨1⁩ ⁨year⁩ ago

  To get across the river, the man can first take the goat across and leave it on the other side. Then, he can go back alone to the original side and take the boat across. Once he is on the other side, he can leave the boat there and take the goat across the river. This way, both the man and the goat can successfully cross the river.

  Attempt by DDG AI (GPT 3.5)

  source
• Dicska@lemmy.world ⁨1⁩ ⁨year⁩ ago

  I love how nobody said any restrictions and the AI started to solve the classic puzzle already. It could as well be a boat with a cage on it, or at least a leash.

  source
• IvanOverdrive@lemm.ee ⁨1⁩ ⁨year⁩ ago

  Claude isn’t much better:

  Okay, here’s how to solve this classic river crossing puzzle:

  The trick is that you can’t take the man and the goat across together, because the goat will be tempted to wander off and get lost or into trouble when left alone on the other side.

  The solution is:

  1. The man rows the goat across the river and leaves the goat on the other side.

  2. The man then rows back alone.

  3. The man picks up something heavy like a rock or log, rows across with the heavy object.

  4. He leaves the heavy object on the other side and brings the goat back.

  5. Finally, the man leaves the goat on the starting side and rows back to join the heavy object on the other side.

  The key is using the heavy object as a temporary “guard” so the goat doesn’t wander when left alone briefly on either side. By strategically ferrying the goat and heavy object back and forth, the man can eventually get both himself and the goat across the river.

  Let me know if this step-by-step explanation for solving the classic man, goat and boat puzzle makes sense!

  source
• Blaster_M@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Dolphin-Mixtral 26GB didn’t fare any better.

  Image

  source
• jeena@jemmy.jeena.net ⁨1⁩ ⁨year⁩ ago

  Here is my attempt:

  A man and a goat are on one side of the river. They have a boat which can carry both of them at the same time. How do they get to the other side?

  The man and the goat can both get to the other side of the river together using the boat since the boat can carry both of them at the same time. Here’s how they can do it:

  1. The man and the goat both get into the boat.
  2. The man rows the boat, carrying himself and the goat across the river.
  3. They both disembark on the other side.

  Since the boat can carry both the man and the goat simultaneously, there are no restrictions preventing them from crossing together in one trip.

  source
• Brunbrun6766@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Gemini didn’t do well either

  source
• fin@sh.itjust.works ⁨1⁩ ⁨year⁩ ago

  ChatGPT is not suitable for such things obviously

  source
• MonkderDritte@feddit.de ⁨1⁩ ⁨year⁩ ago

  You forgot the “without leaving the wolf and goat or goat and cabbage alone” part.

  source