Skip to content

Instantly share code, notes, and snippets.

View YuniorGlez's full-sized avatar

Yunior González Santana YuniorGlez

View GitHub Profile
@YuniorGlez
YuniorGlez / 0.README.md
Last active December 3, 2022 02:03 — forked from agentcooper/0.README.md
Telegram chat backup/export

How to use

  1. Login to https://web.telegram.org
  2. Copy-paste contents of telegram-scripts.js into JS console
  3. Run showContacts() or showDialogs() to get the list of contacts with ids or the 20 last conversations in the same order of the client view
  4. Run saveChat(userId) where userId is the id from step 3 (inside the [] )

Process can take a while, check console for progress. Occasionall FLOOD_WAIT errors are expected. Once done, browser will download the JSON file.

Motivation

Below you have some articles related about prompting and some papers

GPT can [tell bad jokes](https://zapier.com/blog/can-chatgpt-be-funny) and write accidentally hilarious poems about your life, but it can also help you do your job better. The catch: you need to help it do _its_ job better, too.

At its most basic level, OpenAI's GPT-3 and GPT-4 predict text based on an input called a prompt. But to get the best results, you need to write a clear prompt with ample context. After tinkering with it for more hours than I'd like to admit, these are my tips for writing an effective GPT-3 or GPT-4 prompt.

Test your prompt

There's very little chance that the first time you put your AI prompt in, it'll spit out exactly what you're looking for. You need to write, test, refine, test, and so on, until you consistently get an outcome you're happy with. I recommend testing your prompt in the [<