Detail about factual knowledge in Transformers
This post is currently in the Appendix of a much longer post I'm currently editing and waiting for feedback.
In
Current Thoughts on my Learning System
TLDR of what I've been thinking about lately:
* Learning is a set of skills. You need to practice each component
What does "Effective" in EA mean to you?
In the lead-up to EAG SF, I took some time to think about what EA means to me.
When I
Helping organizations survive disasters (and potentially avoid them altogether)
Note: This is an old blog post I wrote in 2019. Resharing now because I feel like AGI forecasters or
I'll be in Berkeley for SERI MATS for the next 2 months
This is a quick post to mention that I'll be in Berkeley attending the SERI MATS program to work on
AI Alignment YouTube Playlists
I created two AI Alignment playlists on Youtube. One is slide-heavy and the other is not. I separated them into
A descriptive, not prescriptive, overview of current AI Alignment Research
TL;DR: In this project, we collected and cataloged AI alignment research literature and analyzed the resulting dataset in an
A survey of tool use and workflows in alignment research
Crossposted from the AI Alignment Forum.
TL;DR: We are building language model powered tools to augment alignment researchers and
Interesting Applications of GPT-3: Elicit
Using GPT-3 on the backend, Elicit can help with a wide range of research and brainstorming tasks. The team behind Elicit is focused on building tools that will help millions of people think through the types of questions we ask ourselves every day.