Tried the same prompt:

I have a riddle for you. With a boat, how can a man and a goat get across the river?

This riddle is reminiscent of classic river-crossing puzzles. The exact solution depends on the additional conditions or constraints that might be implied (like if there are other characters involved, such as a wolf or cabbage). Assuming it’s just the man and the goat, here’s a straightforward solution:

1. The man takes the goat across the river.
2. The man leaves the goat on the other side.
3. The man returns alone to the original side to get the boat. So, in short, the man and the goat cross together in the boat, and then the man returns to the original side to get the boat. If there are additional details or constraints to consider, please let me know!

The goal is to get both to the other side, not just the goat

I see! If the goal is to get both the man and the goat to the other side of the river, here’s how it can be done:

1. The man and the goat both get into the boat.
2. The man rows the boat with the goat across the river.
3. They both disembark on the other side of the river. In this way, both the man and the goat successfully reach the other side of the river together.

Asking questions because you know the dataset is biased towards a particular solution isn’t showing the fault in the syatem, much like asking a human a trick question isn’t proving humans are stupid. If you want to test the logical reasoning you should try questions it is unlikely to have ever heard before, where it needs to actually reason on its own to come to the answer.

And i guess people with anterograde amnesia cannot be intelligent, are incapable of cognition and are worthless, since they can’t form new memories

Because it isn’t

Prompt:

Alice and Bob are identical twins, Bob is twice the age of Alice. How old are they? Show your thought process step by step.

Answer:

Given the problem statement that Alice and Bob are identical twins and Bob is twice the age of Alice, we need to determine their ages. Let’s analyze the information step by step.

1. Identical Twins: Identical twins are born at the same time, so they are always the same age.
2. Statement Analysis:

• Bob is twice the age of Alice.
• Since they are identical twins, Bob and Alice must have the same age.

3. Logical Conclusion:

• The only scenario where a person’s age can be twice their own age is if their age is zero. Thus, the only solution that satisfies both the condition of them being identical twins and the age relationship given in the problem is: Alice’s age = 0 Bob’s age = 0 Therefore, Alice and Bob are both 0 years old.

Are there biases due to the training data? Yes
Does that mean it is totally incapable of reason? No why would it?

And the models aren’t trying to act like a specific person, but humans in general, so variations in writing styles in the data is quite irrelevant, as we’ve already seen it’ll usually adopt the writing style of the prompt, much like a writer will usually stick to their writing style throughout a book.

Memories are not required for intelligence, and letting a model ramble to itself will just cause the entropy of the output to increase until it’s spewing gibberish, akin fo a human locked in solitary for long enough.

Idiots thinking a new thing is magic that will solve all the worlds problems doesn’t mean the thing doesn’t have merit. Someone calling themselves an exper carpenter because they have a nailgun doesn’t make nailguns any less useful.

If you see a person doing a data entry job, do you walk over to them, crack their head open and say “aww man, it’s not magic, it’s just a blob of fat capable of reading and understanding a document, and to then plot the values into a spreadsheet”?

It’s not magic, it’s not a super intelligence that will solve everything, it’s the first tool we’ve been able to make that can be told what to do in human language, and able to then perform tasks with a degree of intelligence and critical thinking, something that normally would require either a human or potentially years of development to automate programmatically. That alone makes it very useful

What if i say big fusion companies will take over the ai market since they have the energy to train better models, seems exactly as likely.

Remember when GPUs stopped being available because openAI bought nvidia and AMD and took all the gpus for themselves?
No? Weird, since gpus are needed for them to be able to deliver anything significantly better than what we have now 🤔

Yeah that was a hypothetical, if you had thoae things you would be able to create a true AGI (or what i would consider a true AGI at least)

Text is basically just a proxy, but to become proficient at predicting text you do need to develop many of the cognitive abilities that we associate with intelligence, and it’s also the only type of data we have literal terrabytes of laying around, so it’s the best we’ve got 🤷‍♂️

Regarding memory, the human mind can be viewed as taking in stimuli, associating that with existing memories, condensing that into some high level representation, then storing that, a llm could, with a long enough context window, look back at past input and output and use that information to influence it’s current output, to mostly the same effect.

What do you mean throwing a black box into an analytical prediction machine? And what do you mean 5 years of development?

Not sure i’m fully understanding your point, are you saying that the large AI companies will create AIs that will create technologies beyond what everyone else is capable of, thus outcompeting everyone, effectively monopolizing every market and from there basically become the umbrella corporation?

I would be very impressed if anyone managed to make an AI capable of innovation to that degree, but sure, in that case we would have to fall back on something like government oversight and regulations to keep the companies in check i suppose

Great story! It’s clear that the old man knows his stuff and has some good advice for handling HAL. Confidence and clarity are key when dealing with these advanced systems. It’s a nice blend of humor and practical tips – can’t wait to see how the kid takes on the challenge! And yes, definitely time to grab a bite after all that important training.

Usurp? They won’t be the ones to develop quantum computers, nor will they be developing fusion, if those technologies become available they might start using them but that won’t somehow mean it won’t be available for other uses.

And seeing as they make money from “renting out” the models, they can easily be “used for better purposes”

ChatGPT is currently free to use for anyone, this isn’t some technology they’re hoarding and keeping for themselves

Hard to make a roadmap when people can’t even agree on what the destination is not how to get there.

But if you have enough data on how humans react to stimulus, and you have a good enough model, then you will be able to train it to behave exactly like a human. The approach is sound even though in practice there prooobably doesn’t exist enough usable training data in the world to reach true AGI, but the models are already good enough to be used for certain tasks

No clue, all i know is that i never have to do more than that, and noone has managed to get it working on windows 🤷‍♂️

When i started learning programming, everything was always a pain to set up, needed to install weird IDEs from shady websites and they only worked half the time. Then a friend showed me linux where stuff just worked out of the box, just slap some code in a textfile and compile it, i never looked back (was working in c/c++ but from what i’ve seen it’s not much better for python)

Every now and then a new hire comes along with a windows pc, every time they decide they want to try to get everything working on windows, after a week they give up.

On linux it’s one pip install and you’re done

I have never heard of anyone eating a carburetor and dying, so we have to assume it’s safe to eat

“What attachment type do you want? Buttplug or buttbite?”

Sure that sounds like a lot, until you realize even a small firearm can deal 9 damage per second, suddenly 15 hp isn’t all that much

Amen! 🙏

That’s the date, it’s an old photo

It is however Removed

Hellosexual

Yes, i finally found my way home from the store, and i bought the milk like i promised i would!