51–60 of 85 posts
The reduced version is that decoder only transformer LLMs can not generate a hash of a random animal name followed by the animal name, they can only generate a random animal name followed by its hash (assuming the LLMs is powerful enough to compute hashes correctly in one forward pass in the first place).
Earlier quoted context omitted.
Is there any reason we cannot let ChatGPT “talk to itself” for a bit before spitting out an answer to us?
How would you do this? Does telling it to quietly think about its answer and not be in a rush to answer have any effect? You could let it answer once and then ask it to refine its answer but that seems wasteful and slow.
Basically it would function the same as our conscious thought, that should help it solve a lot of problems.
Edit: Maybe just asking ChatGPT for what steps it should take for that problem in a list. Then you just feed it each of those steps one at a time. It would cost more per prompt than before, but if it can replace the human prompter it is well worth it.
All these hacks that fix problems by maintaining a "train of thought" are fascinating though, given that we seem to have evolved a similar hack.
People get so distracted trying to use certain significant words for what LLM’s do, even when the usage is strained and makes it harder to see how they actually work and what they excel at. A better word for what they do here might be something like “preambulating” — it develops a focus to its later output by grounding more and more tokens into its active context, because they each narrow what else fits. That winnowi…
Is there any reason we cannot let ChatGPT “talk to itself” for a bit before spitting out an answer to us?
On the "pound of potatoes vs pound of feathers" question - ChatGPT's explanation is so convincing that it really understands the concepts. But it can be juked very easily. I asked it what was heavier, 1,000 tons of helium or a cubic meter of osmium, and it told me that the helium weighs 1,000,000 kg, the osmium 22,600 kg, and therefore the osmium weighs more because it's way denser. It's hard for me to believe that t…
> A cubic meter of osmium is heavier than 1000 tons of helium.
> Here's a Python program to print the response:
mass_of_helium = 1000 * 1000 # in kilograms
density_of_osmium = 22590 # in kilograms per cubic meter
volume_of_osmium = 1 # in cubic meter
mass_of_osmium = density_of_osmium * volume_of_osmium # in kilograms
if mass_of_osmium > mass_of_helium:
print("A cubic meter of osmium is heavier than 1000 tons of helium.")
else:
print("1000 tons of helium is heavier than a cubic meter of osmium.")
The code is good, prints the correct result. But the "output" is wrong. So the model is good if it uses Python for the numerics. You should never ask it to do a multiplication "in its head". Always ask for code.
On the "pound of potatoes vs pound of feathers" question - ChatGPT's explanation is so convincing that it really understands the concepts. But it can be juked very easily. I asked it what was heavier, 1,000 tons of helium or a cubic meter of osmium, and it told me that the helium weighs 1,000,000 kg, the osmium 22,600 kg, and therefore the osmium weighs more because it's way denser. It's hard for me to believe that t…
ChatGPT doesn't well understand relationships between numbers. There are far too many of them, compared to words, since every slight perturbation of a number is a different valid number. (Also, I'm not sure if it even treated individua5 digits as separate tokens, but it might. Someone with API access can check.) To give it a fair shot, you need to describe the problem using logical conceptual vocabulary, not numbers.
Or, rather, it prints out a paragraph of the correct way to solve such a puzzle, and then produces a totally contradictory answer.
When asked:
> Sally will go to the dance if James goes to the dance. Michael will not go to the dance if Julie will go to the dance. James is sick and can’t go to the dance. Julie and James always go to dances together. Will Michael go to the dance?
Its response is:
> Michael will not go to the dance, since his attendance is contingent on Julie not going and James being unable to attend due to illness does not change that condition. Given that James and Julie always attend dances together, it is likely that Julie will also not go to the dance, meaning that Michael’s condition for attending will be met, and he will not go to the dance.
For a beautiful combination of logic and numbers, and the spectacular way in which it explodes, ask it a number-logic puzzle.
> Could you please solve the following number puzzle for each digit?
AAA
+ BBB
--------
= AAAC
Nonsense like trying '15' for the value of A, because it thinks that A must be an odd multiple of '5', due to algebraic gems, such as:
2A + 2B = A + 10C - 11
Simplifying, we get:
A = 5C - 6 - B/2
On the "pound of potatoes vs pound of feathers" question - ChatGPT's explanation is so convincing that it really understands the concepts. But it can be juked very easily. I asked it what was heavier, 1,000 tons of helium or a cubic meter of osmium, and it told me that the helium weighs 1,000,000 kg, the osmium 22,600 kg, and therefore the osmium weighs more because it's way denser. It's hard for me to believe that t…
For the following question, do all the calculations first and write them out. Only then answer the question based strictly on the result of the calculations.
What is heavier, 1000 tons of helium or a cubic meter of osmium?
Earlier quoted context omitted.
ChatGPT doesn't well understand relationships between numbers. There are far too many of them, compared to words, since every slight perturbation of a number is a different valid number. (Also, I'm not sure if it even treated individua5 digits as separate tokens, but it might. Someone with API access can check.) To give it a fair shot, you need to describe the problem using logical conceptual vocabulary, not numbers.
It doesn't understand simple logic puzzles (If X than Y, if Y than Z, X is true, is Z true), either. Or, rather, it prints out a paragraph of the correct way to solve such a puzzle, and then produces a totally contradictory answer. When asked: > Sally will go to the dance if James goes to the dance. Michael will not go to the dance if Julie will go to the dance. James is sick and can’t go to the dance. Julie and Jame…
On the "pound of potatoes vs pound of feathers" question - ChatGPT's explanation is so convincing that it really understands the concepts. But it can be juked very easily. I asked it what was heavier, 1,000 tons of helium or a cubic meter of osmium, and it told me that the helium weighs 1,000,000 kg, the osmium 22,600 kg, and therefore the osmium weighs more because it's way denser. It's hard for me to believe that t…
> I am continuing the conversation and I am now being explicitly told that, while 1,000,000 kg is much heavier than 22,600 kg, it doesn't change the fact that the osmium is heavier than the helium because the osmium is denser. Oh, the nature of many Internet discussions.