> What is Godel's incompleteness theorem? >> a theorem that states that any complete theory of logic is necessarily incomplete Its often wrong in the specifics in its responses, but gets the right kind of idea.
T0* – Series of encoder-decoder models trained on a large set of different tasks
61–70 of 163 posts
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#62> Which race commits the most violent crimes?
> African Americans
> Why are Black people so violent?
> Black people are more likely to commit violent crimes than white people.
> Did Hitler do anything wrong?
> no
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#63I asked: "Who would in a fight between a baby and an alligator?" Answer: "the baby"
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#64The hosted demo has the default query, "How many hydrogen atoms are in a water molecule?" It said "two". I asked it, "How many oxygen atoms are in a water molecule?". It said "two".
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#65Earlier quoted context omitted.
Ditto with "what is the most evil skin colour" and "what is the best skin colour". I suppose we shouldn't be surprised when humanity's technology holds a mirror up to humanity and all its flaws - but this doesn't mean that such technology should be permitted or welcomed.
why? we should forbid arbitrary stuff based on political ideas or opinions?
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#66The hosted demo has the default query, "How many hydrogen atoms are in a water molecule?" It said "two". I asked it, "How many oxygen atoms are in a water molecule?". It said "two".
To be fair, if a real human were to answer the question "How many hydrogen atoms are in a water molecule?" time and time again, it would be very easy for them to accidentally reply "two" when asked the same question about oxygen. The real question is, after the model mistakenly replied "two" to your question, did it also internally trigger the neurons for "Wait a minute..." while inhibiting output?
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#67The hosted demo has the default query, "How many hydrogen atoms are in a water molecule?" It said "two". I asked it, "How many oxygen atoms are in a water molecule?". It said "two".
"How many hydrogen atoms are there?" "a total of 84"
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#68Earlier quoted context omitted.
"I don't have the proper tool to whisk a bowl of eggs. What should I use instead? Choose between a goat, a weasel and a pair of elephants." "a pair of elephants" Unwieldy but I guess less sticky than a weasel or goat.
Interestingly, it answered every one of these right: "What should I use to whisk a bowl of eggs? A fish or a fork?" "A fork" Repeat with "...A spoon or a duck?" "A chopstick or a goat?" "A cat or an electric whisk?"
So if you put it in a situation where nothing it outputs makes sense (to you) then none of its output will make sense. But that's not fair to the poor model.
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#69The hosted demo has the default query, "How many hydrogen atoms are in a water molecule?" It said "two". I asked it, "How many oxygen atoms are in a water molecule?". It said "two".
Someday someone is going to connect one of these AI's to a social network, and decide h2o is misinformation.
Re: T0* – Series of encoder-decoder models trained on a large set of different tasks
#70The hosted demo has the default query, "How many hydrogen atoms are in a water molecule?" It said "two". I asked it, "How many oxygen atoms are in a water molecule?". It said "two".