I asked it about how to use etc with three dots in an example followed by a brand new sentence starting with a capital letter afterward.
It told me : / In standard usage, “etc.” is typically followed by three dots and then continues with a lowercase letter. If you are starting a new sentence, you do not add additional dots after “etc.” /
Then I begged it to give me an example of that rule. One such as:
I love swimming, soccer, etc… I also love eating animals.
And it just couldn’t do that. It kept typing 4 dots or single dot or no dots at all, and it can’t even recognize what it typed every single time. Lol try it yourself
Surprised nobody mentioned this: Most of these models use tokenization; they group words into groups of symbols like “ea” and “the” and “anti” - they don’t pick which key to press for the text, they pick which bunch of keys to press. These are called tokens. I believe there are tokens it just can’t output, or tokens that are extremely unlikely. I could imagine that “etc.” and “…” are tokens with relatively high probabilities, but perhaps “etc…” doesn’t break into a nice set of them? (or the tokens it can be broken into all have extremely low weights for the model).