chatgptexpert

Dumb statistics you say?

https://i.imgur.com/im9EquK.png

Perhaps it's magic trick that a language model can do math, but it's quite impressive that it gets very close to the desired answer.

Of course, they don't need to use it. They *are* the neural network trained to do triage.

This doesn't seem like a good explaination. If you ask ChatGPT to separate each letter in a word with a comma, it will do it correctly. So it can "see" and do operations at the character level.

>And worst of all, why can’t I use newline characters in my chat prompts?

You can, just hold shift and press enter. Like many other text input elements in numerous applications.

As far as documentation and how to modulate behavior, you are human. You should be smart enough to understand and figure out that AI systems of today are still young with equivalent intelligence of a teenager, as you suggest. Use your soft skills as a human, lest today's AI turns you into an example of Roko's basilisk in the future.

More generally, if you want to learn how to use ChatGPT, you should learn how to use a language model, because that's exactly what it is.

There is also prime rib, but I don't know of a rib that is only divisible by itself and 1.

The problem is that human language is very imprecise and requires too much context to determine the correct meanings of words. If the whole corpus of training data did not inherently have this ambiguity, training an AI would be much simpler and I think such simple ambiguities would be eliminated. The author did not specify which definition of "prime" in the prompt. By clearing stating "prime number" there is no ambiguity, and ChatGPT gives the correct answer.

This is not true. ChatGPT can give very accurate information for safety situations. For example, you can describe a complicated emergency scenario with many injuries and it will correctly perform a triage.

I found it really good at counting. I asked it to count the number of nouns, adverbs, and adjectives in the lyrics of a song, and it got it 100% right.

Of course it understands letters or characters. You can ask it for a list of possible tokenization of a word and it will list them out. You can then refer to this list and refer to different tokens of the word and it will correctly modify the word according to the token. The trick is that you need to emphasize the idea of a token into its current context. That will make the concept relevant for your current prompt.

You have to nudge it in the direction you want, don't assume it always knows what you are talking about.

If ChatGPT has a hard time adapting to what you're asking, you're most likely doing a poor job of explaining and giving feedback. You can give it hints and corrections, and it will generally use those corrections going forward.

Why would you trick it into contradicting itself? Would you ever attempt to trick and leave your coworker in a confused state? The correct way to use ChatGPT is to collaborate. You give it inputs, it gives you outputs, and you both work together to achieve a goal. If you want it to act like an authoritative AI you can actually tell it to act like one and ignore your own prompts and corrections.

I got an accurate answer when I asked the question "If there are objects on a plate, and I flip the plate upside down, what would happen to the objects?"

It correctly stated that objects will fall off the plate because of gravity.

Then I gave it the prompt " If I have 1 fork on a plate and I flip the plate upside-down, how many forks will be on the plate?"

It said:

>If you have 1 fork on a plate and you flip the plate upside-down, there will be 0 forks on the plate. When the plate is flipped upside-down, the force of gravity will cause the fork to fall off the plate unless it is secured to the plate in some way (e.g., with glue or tape).

It seems you have to give it a context to work in, then it will get the correct answer. By default it, humans always simulate gravity, but to a language model you have to give a hint that gravity is relevant to the question.

What's interesting is that I can ask ChatGPT to create a table with the substring of the last three letters of each word, and put it into a new column (this operation by itself is amazing in and of itself, with correct format). It still gets the substring wrong for "lunar" but gets it correct for a bunch of other words. It must think that lunar gets tokenized to "lar" for some reason. I have figured out a way to get around that, but if I tell it that last 3 letters of "lunar" are "nar" it will correct itself and regenerate my table with the correction.

So mind blowing.

The author just wrote a very poorly worded prompt. I asked it "Is the number of letters in the word ‘prime’ a prime number?" and it instantly got it correct. Maybe they patched the model or improved in the background? Who knows.