[iamflimflam1]

I would really recommend anyone who tries something with GPT and then wonders why it doesn’t work to read the GPT3 paper. They go into detail on what the model is and isn’t good at.

One thing to really think about for this particular case is “What is going to do the counting? Where is it going to store its running count?” - it’s pretty obvious after asking yourself these questions that “counting words” is not something an LLM can do well.

It’s very easy to fall into the trap of thinking there is a “mind” behind ChatGPT that is processing thoughts like we do.

[soygul]

Very good suggestion, will read it in a moment.

I asked another instance of ChatGPT to count the words in the conversation and I copy pasted the conversation message by message. It successfully counted. Given the ridiculous concurrency of human brain, I assume an orchestra of ChatGPT instances could simulate at least some of that "mind".

[muzani]

It's really just super autocomplete. Visualize a loop. You can ask it in the loop to count, but you can't ask it to loop. It needs to loop to be able to track the word count.

[frozencell]

What about GPT4 with plugins?

[iamflimflam1]

This is much more possible. Just built a plugin a 5-10 minutes with GPT generating most of the code.