NotebookLM podcasts, but good
AI / LLMs / Agents
oliver’s Prompt
f: saul
You Sent the Message. But Did You Write It?
Nabeel S. Qureshi (@nabeelqu) on X
How I don't use LLMs
How Better Feedback Can Revolutionize Education (with Daisy Christodoulou) - Econlib
f; Cedric
Engineering \ Anthropic
How I Broke My 20-Year SPSS Habit To Vibe Code Something in a Python Colab Notebook
How I Built a Google Docs Add-On in Three Hours (Using Vibe Engineering)
Made myself a research tool Claude makes flash cards from passages I highlight Reduces the friction of using spaced repetition. Sharing in case helpful to you! generateflash dot cards pic.twitter.com/s15SvEeTv5— Dwarkesh Patel (@dwarkesh_sp) March 16, 2025
Vibe coding - muller's ratchet on codebase pic.twitter.com/0I7PiR6jD3— Dwarkesh Patel (@dwarkesh_sp) March 14, 2025
Anki + GPT-3 = 3
Running Claude Code on your @Obsidian directory is super powerful. Here Claude goes through my notes on an upcoming guest's book, and converts my commentary into a list of questions to be added onto the Interview Prep file. pic.twitter.com/o3uvAsd0As— Dwarkesh Patel (@dwarkesh_sp) February 24, 2025
PMing with o1 pro, v0, and DeepSeek-R1
How I Use "AI"
Just started using Smart Composer Plugin on Obsidian (basically Cursor for writing).
You're using ChatGPT wrong - Fried Kielbasa
Gwern on LLM-usage as infohazard
f: Austin
Examples of GenAI/LLM use by experts - Self Improvement - The Commonplace Community
you can create a custom style in claude!?
Prompts
Great paper summarizing the prompt techniques - The Prompt Report.
How I Use Claude
who amongst you will use code llms (and maybe nn interp?) to let me visualize any repo like a factorio map, letting me see who's working on different parts, see the repo evolve over time
What are good places to learn how to get better at using current AI tools for general work/productivity: Ideas for good uses, tools, getting better at prompting, staying up to date w. new tools, etc
A Three-Layer Model of LLM Psychology — LessWrong
LLM prompts
transcribe.py
Dwarkesh's transcript LLM
Dwarkesh Patel on X: "We’re way more patient in training human employees than AI employees. We will spend weeks onboarding a human employee and giving slow detailed feedback. But we won’t spend just a couple of hours playing around with the prompt that might enable the LLM to do the exact same job," / X