Agam Brahma
tl;dr: treat llm output as a pointer to the answer, not the answerEveryone who leans on these tools has been burnt: an invented flag, a test that passes for the wrong reason. Abstaining isn't a serious option for me either ... the leverage is too large to leave on the table. So the question is how...
Agam Brahma
tl;dr: the test was't really about measuring the machine, but rather about measuring us.Eliza was enoughJoseph Weizenbaum wrote ELIZA in the mid-1960s as a kind of "parody of therapy". It was a simple program that mostly took what you typed and turned it back into a question. If you said you were...
Alexandra
Choosing the right AI model is now a well-recognized problem. It is still not trivial, but at least there are benchmarks, pricing pages, context-window comparisons, and plenty of public discussion to guide you. Coding agents are still more of a wild west. Many people treat them as simple...
My Astro Notes
A walk through the major families of AI models — what they do, how they work, and what it takes to train them — for people who want intuition, not a textbook.
msuzen
Extension of this post, appear as a short article with a conjecture:Mehmet Süzen. In-context learning as a new kind of symbolic-AutoML: Lyapunov conjecture for CoTs. 2024 HAL FrancePreamble A graph path (Wikipedia)With the common usage of Pre-trained Large Language Models (PLMs/LLMs), now it is...
Adrian's Corner
It’s conference season for developers and Microsoft’s annual conference Build just wrapped up. I haven’t paid particular attention to Build in the past, but it’s been interesting to follow this year due to Microsoft’s close collaboration with OpenAI and them pushing ahead with integrating...
Martín Villalba
Now that everyone is talking about Large Language Models (LLMs) in general and ChatGPT in particular I thought I would share a couple thoughts I've been having about this technology that I haven't seen anywhere else. But first, let's talk about chess. Chess is a discipline notorious for coming out...