From Newsgroup: comp.ai

When prompting an AI Chatbot with a physics or math problem,
is it possible to use LaTeX input yet? If not, how is it done?
--
https://www.nfld.com/~dalton/dtales.html Salmon on the Thorns (mystic page) rCLMary walks down to the waterrCOs edge and there she hangs Her head
to find herself faded a shadow of what she once was" (Sarah McLachlan)

--- Synchronet 3.21a-Linux NewsLink 1.2

From Newsgroup: comp.ai

Greetings.

On 2025-06-22 21:15, David Dalton wrote:

When prompting an AI Chatbot with a physics or math problem,
is it possible to use LaTeX input yet? If not, how is it done?

This surely depends on the individual AI chatbot and (assuming you're
asking about those based on large language models) how it was trained.

I did a quick test with ChatGPT just now and it had no problem
recognizing equations written in LaTeX markup. The answers even
included equations of their own that the web interface helpfully
rendered visually (maybe as MathML) but which, when copied to the
clipboard, turned into LaTeX markup.

Regards,
Tristan
--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Tristan Miller
Free Software developer, ferret herder, logologist
https://logological.org/ =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

--- Synchronet 3.21a-Linux NewsLink 1.2

From Newsgroup: comp.ai

In comp.ai On 23/06/2025 03:21, Tristan Miller wrote:

[Just now, ChatGPT] had no problem
recognizing equations written in LaTeX markup.

^^^^^^^^^^^

Normally people say things like "understanding" which you've avoided, of course it's not right for an LLM, but "recognizing" also implies mind
via "cognize". Is "recognizing" an accepted technical term for LLMs or
should we say "predicting from" ?

"Just now, ChatGPT had no problem predicting from equations written
in LaTeX markup."

--
Yours Faithfully
Tristan Wibberley

--- Synchronet 3.21a-Linux NewsLink 1.2

From Newsgroup: comp.ai

Greetings.

On 2025-07-10 07:26, Tristan Wibberley wrote:

[Just now, ChatGPT] had no problem recognizing equations written in
LaTeX markup.

-a ^^^^^^^^^^^

Normally people say things like "understanding" which you've avoided, of course it's not right for an LLM, but "recognizing" also implies mind
via "cognize". Is "recognizing" an accepted technical term for LLMs or should we say "predicting from" ?

It's true that using the term "understand" with reference to what LLMs
do has been stigmatized, but I haven't encountered any similar
proscriptions for "recognize". The latter term has been used
academically in the context of AI systems since long before the advent
of LLMs, and has even become entrenched in popular usage through terms
such as "speech recognition" and "facial recognition". There are even
plenty of computational but non-AI uses going back to the 1950s -- books
and articles write of computers "recognizing" magnetically encoded bits
on a storage medium, or symbols in a computer program, or numbers within
a certain range.

Regards,
Tristan
--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Tristan Miller
Free Software developer, ferret herder, logologist
https://logological.org/ =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

--- Synchronet 3.21a-Linux NewsLink 1.2

From Newsgroup: comp.ai

On 10/07/2025 09:38, Tristan Miller wrote:

Greetings.

On 2025-07-10 07:26, Tristan Wibberley wrote:

[Just now, ChatGPT] had no problem recognizing equations written in
LaTeX markup.

... "recognizing" ... implies mind via "cognize". Is "recognizing"
an accepted technical term for LLMs or should we say "predicting from"
?

["recognize"] has been used
academically in the context of AI systems since long before the advent
of LLMs, and has even become entrenched in popular usage through terms
such as "speech recognition" and "facial recognition".-a There are even plenty of computational but non-AI uses going back to the 1950s -- books
and articles write of computers "recognizing" magnetically encoded bits
on a storage medium, or symbols in a computer program, or numbers within
a certain range.

Thanks for the detailed and helpful response.

It seems those uses of "recognize" and "recognition" are specifically
for classification and, typically, classification of an input as a representation of a specific symbol.

Do you find that normally a face is said to be recognized when the
system provides a name, classified when it provides a species, detected
when it provides an assertion of presence?

I wonder if "recognize" is properly applied to LLM prediction of a
statement that asserts a specific member of a class rather than for just
any useful prediction or for prediction of any classifying statement in general?


That continues to raise some interesting questions. If you ask "is
[code] latex?" and the system responds "yes", did it even get as far as 'classifying' the code as latex? Did the system merely admit it to a "similar-to-latex" set rather than discriminating the code from other
things from which you would expect it to be discriminated when it is classified?

--
Tristan

--- Synchronet 3.21a-Linux NewsLink 1.2

From Newsgroup: comp.ai

Greetings.

On 2025-07-13 00:09, Tristan Wibberley wrote:

Do you find that normally a face is said to be recognized when the
system provides a name, classified when it provides a species, detected
when it provides an assertion of presence?

I'm not sure I follow you.

I wonder if "recognize" is properly applied to LLM prediction of a statement that asserts a specific member of a class rather than for just
any useful prediction or for prediction of any classifying statement in general?

Again, I'm not sure what you're getting at. What do you mean by
"prediction" here? Does this just refer to the output of an LLM?

That continues to raise some interesting questions. If you ask "is
[code] latex?" and the system responds "yes", did it even get as far as 'classifying' the code as latex? Did the system merely admit it to a "similar-to-latex" set rather than discriminating the code from other
things from which you would expect it to be discriminated when it is classified?

Does it matter, and is this any different to how a human would answer
the same question?

Regards,
Tristan
--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Tristan Miller
Free Software developer, ferret herder, logologist
https://logological.org/ =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

--- Synchronet 3.21a-Linux NewsLink 1.2