Начал экспериментировать с GPT-4

[dmm]

Через ChatGPT+, за двадцатку в месяц. В общем, разница между этой штукой и ChatGPT огромная, и нет смысла ещё тянуть время.

Сразу она начала с предупреждения: "GPT-4 currently has a cap of 25 messages every 3 hours. Expect significantly lower caps, as we adjust for demand."

Но когда я попросил её дать мне советы по моему проекту, она очень мило выступила, технически грамотно в конкретном контексте, и совсем не всё, что она сказала, было общим местом (и, в любом случае, она явно шире видит, чем я; я даже почти всё это "в принципе знаю", и с чем-то могу и не согласиться, но, с другой стороны, оно всё по делу, большую часть этого дела я бы и не вспомнил).

Comments

[dmm]

Вот, насчёт LaTeX. Я ей сказал

I have the following markdown text; please generate equivalent LaTeX: и вставил вот этот markdown: https://github.com/anhinga/2022-notes/blob/main/Generative-autoregressive-models-are-similators/README.md

Она мне на это сказала (ещё не проверял, всё ли хорошо):

Here is the equivalent LaTeX code for your provided Markdown text:

\section{Generative autoregressive models are simulators}

A radical novel understanding of the nature of GPT-3-like models seems to be crystallizing.

\textit{These models are simulators, they generate various entities (which tend to be rather short-lived at the moment),
and users are interacting with those entities. This novel understanding explains a lot of observable phenomena and
opens new promising directions of work.}

A lot of people were seeing glimpses of this for a few years now. E.g. when I was playing with GPT-2 in 2019, I noticed that
it looked like a virtual personality was created at first (sampled from a distribution of virtual personalities
conditioned by the initial prompt), and then that personality was speaking to me. Or, at least, that was my impression.

\begin{center}
\line(1,0){250}
\end{center}

Fast-forwarding to September 2022:

The following text has been published by \textbf{``janus''} on Sep 2, 2022:

\url{https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators}

It has been further publicized and discussed by Scott Alexander on Sep 19:

\url{https://astralcodexten.substack.com/p/janus-gpt-wrangling}

This both crystallizes a lot of that new understanding, shows that this viewpoint is gradually proliferating in leading
organizations focusing on better understanding the true nature of modern generative Transformers and on leveraging this
improved understanding, and helps to disseminate this viewpoint (due to the popularity of Scott Alexander's substack in
the relevant circles of professionals).

This subdirectory is for the materials related to this new understanding.

\begin{center}
\line(1,0){250}
\end{center}

\subsection{My reading notes:}

\href{reading-janus-gpt-wrangling.md}{reading-janus-gpt-wrangling.md} - written (this page also contains links to some tools and papers by ``Janus'' including their \textbf{loom} tool and ``Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm'' paper, \url{https://arxiv.org/abs/2102.07350})

\href{reading-simulators-essay.md}{reading-simulators-essay.md} - written

\begin{center}
\line(1,0){250}
\end{center}

\subsection{Thinking further about this topic}

\textit{Work in progress}

*****

Ещё сказала

Make sure to include the necessary packages in your LaTeX document preamble for the hyperlink and URL functions, such as:

\usepackage{hyperref}
\usepackage{url}

Please note that due to the limitations of the text format here, you may need to adjust the formatting slightly (e.g., line breaks) when copying this code into your LaTeX editor.

Сейчас посмотрю, что получилось...

[juan_gandhi]

В смысле ему можно весь проект с гитхаба выдать на растерзание?

[dmm]

Не пробовал. Я сделал copy-paste.