[tldoc] TeXLive plans in writing the documentation: will be human or chatgpt generated text?

[Boris Veytsman]

KB> Date: Thu, 8 Jun 2023 15:01:26 -0600
KB> From: Karl Berry <karl at freefriends.org>

KB> Carlos - TUG as an organization has no opinion pro or con for chatgpt,
KB> or llm in general. The board has never discussed it; as far as I can
KB> see, there's nothing to discuss. In his newsletter, Boris was simply
KB> making an observation. Boris is on this list and can confirm if it would
KB> ease your mind.


Absolutely.

It is true that LLMs now are a hot topic, so the ability of them to
produce TeX code (or rather LaTeX code (*)) is rather amusing.  Still the
amount of confabulation by them is too large (I think the technical
term is hallucination).  I reported elsewhere the abysmal results of
them for a problem which computers have been able to solve for fifty
years (https://tug.org/TUGboat/tb44-1/tb136pres.pdf).  There are
horror stories about LLMs inventing precedents for legal briefs with
rather bad consequences for the lawyers.

As far as I know there are no plans of using LLMs in documentation
writing or code generation for TUG.  If these projects appear, it
would be interesting to see the results - and we cannot exclude the
possibility they might be useful.  Especially if we can solve the
hallucination problem.

---------------------------------------------------------------------------
(*) Another amusing thing - it looks like chatgpt understands the
difference between LaTeX and plain TeX:

BV: hi

ChatGPT: Hello! How can I assist you today?

BV: can you translate LaTeX code to plain TeX?

ChatGPT: Certainly! I can help you with that. Please provide the LaTeX
code you'd like to translate, and I'll do my best to convert it to
plain TeX for you.

BV: please translate $\frac{a}{b}$ to plain TeX

ChatGPT: Certainly! In plain TeX, the equivalent code for the fraction
\frac{a}{b} in LaTeX is: $$\displaystyle{a \over b}$$ This will
produce the same fraction a/b in plain TeX.


-- 
Good luck

-Boris