ivansavz

I've been trying to categorize the recent release of math results obtained via use of GenAI, but I'm long out of academia so I can't judge for myself. The few papers that related to my research were unreadable, but I don't know if it's because I'm no longer current or because the content is mathslop.

I found this collections of reactions to be a useful barometer.

I'd love to be able to filter only on reactions of people AFTER they have read a paper or two in their field, but I guess we'll have to wait a few days for that.

So far I'm yet to find a serious mathematician who actually found something of interest by reading the results (e.g. understand a new proof trick or approach to a problem). Does anyone have links to such positive ractions?

I've been getting a lot of genAI-targeted SPAM too, based on a different template:

First paragraph = credible description of my startup.

Second paragraph = offer to "connect" me with private capital in NYC who are interested in funding this specific type of business.

I assumed Linked In is rife with such targeted spam, but now the bastards are hitting my email... The sender and text are different in each email that SPAM filters have trouble adapting to it.

Thx genAI. I really needed that in my life. Wonderful stepping stone toward AGI.

Okay, let's start a new game where we try to guess the prompt that produced this text.

My guess would be "Write a 2000 words blog post based on the analogy between the difficulty of understanding the laws of physics and minified source code."

It's a cool analogy, no doubt, but reading the 2000 words of the article, I felt there was no substance or flesh around it. Okay there were some examples vaguely related to the analogy, and writing was smoothish, but what was the message in the end? What were the new ideas (beyond the analogy)?

Every time I read a LLM generated long form text I am reminded of the communication engineering: communication channels can only decrease the information content. For example, in the communication setup:

   Alice sends msg  --encode--> codeword --channel--> codeword' --decode--> msg' Bob received

The best we can hope for is that the message was transmitted faithfully, so msg' = msg, since the channel noise can only degrade the information content, specifically, the mutual information is a non-increasing function:

   I(msg;codeword') ≤ I(msg;codeword),

due to the monotonicity of information (a.k.a. data processing inequality).

Similarly, if Alice uses LLM to communicate to Bob, we have:

   Alice's idea --encode--> prompt --LLM--> generated text --decode--> idea' 

Monotonicity of information tells us

   I(idea;generated text) ≤ I(idea;prompt).

So I really don't get it, why do people believe that adding LLM generation step could improve the communication of their ideas? It seems directly analogous to passing a message through an additional noisy channel. Just show us the prompt.

Does anyone have experience using SMLs for RAG (either as query rewriter or as generator for the final answer)?

I'd like to work with a corpus offline (internal university research data) and I'm hoping I can get everything done without the data leaving the premises.

I guess the biggest bottleneck is going to be for the context window size which won't be able to fit too many result "hits."

Any info or advice would be appreciated.

Absolutely. I feel I gain at least 10 IQ points when reading something on paper.

This is also the strategy I use for editing drafts of my books. I bring a printed draft to someplace nice (e.g. coffee shop or park) and read it all carefully, then I transfer the edits back to the .tex sources. I do several passes of this, until I feel the text + explanations are solid.

Reading on screen just isn't the same...

I got halfway though the exercises with the help of a reading group. They were very hard, bit thought provoking, so I would definitely recommend. Don't feel discouraged if you get stuck and try not to look at the solutions right away.