(Hastily-written code to reproduce these findings is available here. It also contains some extraneous logic.)
This post consists of the Sequences Highlights compiled to a zoomer-readable format, i.e., video. If you'd prefer to watch these videos on YouTube proper rather than on this post, use this YouTube playlist. These videos may or may not suit your mind well; as far as I can tell, there's...
If I (a 19 year old male) texted "www.readthesequences.com" to my roommate, the probable outcome is that he would skim the site for under a minute, text back something like "seems interesting, I'll def check it out sometime", and then proceed to never read another word. I have another friend,...
Our alignment research aims to make artificial general intelligence (AGI) aligned with human values and follow human intent. We take an iterative, empirical approach: by attempting to align highly capable AI systems, we can learn what works and what doesn’t, thus refining our ability to make AI systems safer and...
In no particular order, here's a collection of Twitter screenshots of people attacking AI Safety. A lot of them are poorly reasoned, and some of them are simply ad-hominem. Still, these types of tweets are influential, and are widely circulated among AI capabilities researchers. 1 2 3 4 5 (That...
The news tiles on Snapchat are utter drivel. Looking at my phone, today's headlines are: "Zendaya Pregnancy Rumors!", "Why Hollywood Won't Cast Lucas Cruikshank", and "The Most Dangerous Hood in Puerto Rico". Essentially, Snapchat news is the Gen-Z equivalent of the tabloid section at a Walmart checkout aisle. Which is...