tonyatpeking

	Inductive Reasoning	Abductive Reasoning	Deductive Reasoning
Description	Generalizes from examples to broader conclusions. 🧩	Infers the most likely explanation from incomplete evidence. 🔍	Applie

karpathy

# -----------------------------------------------------------------------------
# AI-powered Git Commit Function
# Copy paste this gist into your ~/.bashrc or ~/.zshrc to gain the `gcm` command. It:
# 1) gets the current staged changed diff
# 2) sends them to an LLM to write the git commit message
# 3) allows you to easily accept, edit, regenerate, cancel
# But - just read and edit the code however you like
# the `llm` CLI util is awesome, can get it here: https://llm.datasette.io/en/stable/

gcm() {

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

simonw

[
  {
    "date": "Mon Jan 23 13:03:00 2017 -0800", 
    "message": "Recommended by Django https://docs.djangoproject.com/en/1.10/ref/databases/#setting-sql-mode", 
    "title": "SET sql_mode='STRICT_TRANS_TABLES';", 
    "hash": "a395f401c9a6d3e8602b80ecc729d736da871f46", 
    "author": "Simon Willison <[email protected]>"
  }, 
  {
    "date": "Mon Jan 23 11:37:38 2017 -0800", 

fclairamb

#ifdef SHELL
g++ -Wall -Werror -g -I../../cclib/rapidjson/include $0 && ./a.out
exit 0
#endif

// Output is:
// {"project":"rapidjson","stars":11}
// {"Name":"XYZ","Rollnumer":2,"array":["hello","world"],"Marks":{"Math":"50","Science":"70","English":"50","Social Science":"70"}}
// {"FromEmail":"[email protected]","FromName":"Sender's name","Subject":"My subject","Recipients":[{"Email":"[email protected]"}],"Text-part":"this is my text"}