Sublime
An inspiration engine for ideas
The ultimate guide to prompt engineering in 2025
Learn:
1. Why role prompting (e.g. “You are a math professor. . .”) is largely ineffective, counter to what most people think. Research shows that while role prompts may help with tone or writing style, they have little to no effect on improving... See more
Prioritizing long-term interests over immediate gains Constructing effective arguments Second-order thinking and realizing long-term interests:
Rhiannon Beaubien • The Great Mental Models Volume 1: General Thinking Concepts
ACX 2024 Prediction Contest Retrospective
thedissonance.net
Every day, first thing, most people get a blend of randomness all at once. In this high-dimensional space, you’re being pulled in a bunch of different directions, not really making progress. Progress is doing some math today and doing some more math in the same area tomorrow. A little bit of compounding progress along the same direction each day
... See moreEric Jorgenson • The Anthology of Balaji: A Guide to Technology, Truth, and Building the Future
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
machinelearning.apple.com
Astral Codex Ten | Scott Alexander | Substack
astralcodexten.com
A fun thought experiment on survivorship bias and selecting the best strategy:
Imagine two entrepreneurs, Alice and Bob. They each open a business with an initial capital of $100,000. Alice takes more risks and, as a result, has a high growth rate of 10%. However, because of those risks, she also has a high failure rate... See more
Luca Dellannax.comI'm one of those in-the-trenches LLM researchers. I haven't participated much in the AI or AI safety discourse on Twitter.
After having read and thought through various arguments for and against AI existential risk, here's a summary of my current beliefs.
Sherjil Ozairx.com