GPT4o still can't reason. It is super fancy autocomplete.
https://i.imgur.com/z83umbk.jpeg
Here I change a widely known riddle to the opposite answer, and I manage to make it state them both as the answer.
https://i.imgur.com/z83umbk.jpeg
Here I change a widely known riddle to the opposite answer, and I manage to make it state them both as the answer.
When I speak colloquially, I have an underlying idea rooted in a world model to be expressed. I don't spit out 1 word at a time based on the previous words I already said.
It's very much feels to be gearing towards figuring out the gist of a search engine you may be trying to complete and put together by reading a few links.
You can stump a person with a riddle or a logic puzzle or an optical illusion.
The fact is that people who say 'it is just fancy autocomplete' are using a thought-terminating cliche, and a 'I stumped an LLM' proves nothing.
It is simply regurgitating this phrase without even considering that it is stating the exact opposite of the answer it just gave, simply because most answers to this riddle on the internet say this at the end.
> This riddle plays on the assumption that a surgeon is typically male, but in this case, the surgeon is the boy's mother.
So from this 1 failing, you can see that it is a copy and paste machine, and it doesn't even understand that it is contradicting itself.