When Execution Gets Cheap, Does Taste Become the Moat?
5 min read
Writing
Hard Truths About Where AI Is Headed
5 min read
Difficulties in Building an AI Safety Startup
4 min read
Gaining clarity on Automated Alignment Research
4 min read
Better model diffing is needed
2 min read
Automating AI Safety: What we can do today
10 min read
AI Alignment Project Ideas
6 min read
How much I'm paying for AI productivity software (and the future of AI use)
9 min read
The importance of Entropy
2 min read
Accelerating AI Alignment Research (Talk)
1 min read
Using data attribution for AI alignment
5 min read
Quantum Computing, Photonics, and Energy Bottlenecks for AGI
10 min read
AI Insights #1: How Misalignment Could Lead to Takeover & Necessary Safety Properties
5 min read
My current research and request for collaborators
3 min read
But is it really in Rome? Limitations of the ROME model editing technique
3 min read
An incomplete list of projects I'd like to work on in 2023
1 min read
(Linkpost) Results for a survey of tool use and workflows in alignment research
1 min read
How learning efficiently applies to alignment research
2 min read
Differential Training Process: Delaying capabilities until inner aligned
3 min read
Near-Term AI capabilities probably bring low-hanging fruits for global poverty/health
1 min read
Is the "Valley of Confused Abstractions" real?
3 min read
Foresight for AGI Safety Strategy
10 min read
Notes on Cicero
3 min read
Detail about factual knowledge in Transformers
2 min read
Current Thoughts on my Learning System
4 min read
What does "Effective" in EA mean to you?
3 min read
Helping organizations survive disasters (and potentially avoid them altogether)
8 min read
I'll be in Berkeley for SERI MATS for the next 2 months
1 min read
AI Alignment YouTube Playlists
1 min read
A descriptive, not prescriptive, overview of current AI Alignment Research
2 min read
A survey of tool use and workflows in alignment research
1 min read
Interesting Applications of GPT-3: Elicit
9 min read