Sign in Subscribe

Writing

09
Jan
'26

Difficulties in Building an AI Safety Startup

4 min read
09
Jan
'26

Gaining clarity on Automated Alignment Research

4 min read
09
Jan
'26

Better model diffing is needed

2 min read
08
Aug
'25

Automating AI Safety: What we can do today

11 min read
02
Oct
'24

AI Alignment Project Ideas

6 min read
24
Sep
'24

How much I'm paying for AI productivity software (and the future of AI use)

9 min read
14
Aug
'24

The importance of Entropy

2 min read
27
Jul
'24

Accelerating AI Alignment Research (Talk)

1 min read
09
Jul
'24

Using data attribution for AI alignment

5 min read
10
May
'24

Quantum Computing, Photonics, and Energy Bottlenecks for AGI

10 min read
03
May
'24

AI Insights #1: How Misalignment Could Lead to Takeover & Necessary Safety Properties

5 min read
23
Jan
'24

My current research and request for collaborators

3 min read
29
Dec
'22

But is it really in Rome? Limitations of the ROME model editing technique

3 min read
29
Dec
'22

An incomplete list of projects I'd like to work on in 2023

1 min read
19
Dec
'22

(Linkpost) Results for a survey of tool use and workflows in alignment research

1 min read
16
Dec
'22

How learning efficiently applies to alignment research

2 min read
07
Dec
'22

Differential Training Process: Delaying capabilities until inner aligned

3 min read
07
Dec
'22

Near-Term AI capabilities probably bring low-hanging fruits for global poverty/health

1 min read
05
Dec
'22

Is the "Valley of Confused Abstractions" real?

3 min read
05
Dec
'22

Foresight for AGI Safety Strategy

10 min read
28
Nov
'22

Notes on Cicero

3 min read
26
Nov
'22

Detail about factual knowledge in Transformers

2 min read
13
Aug
'22

Current Thoughts on my Learning System

4 min read
27
Jul
'22

What does "Effective" in EA mean to you?

3 min read
23
Jul
'22

Helping organizations survive disasters (and potentially avoid them altogether)

8 min read
22
Jul
'22

I'll be in Berkeley for SERI MATS for the next 2 months

1 min read
22
Jul
'22

AI Alignment YouTube Playlists

1 min read
21
Jul
'22

A descriptive, not prescriptive, overview of current AI Alignment Research

2 min read
23
Mar
'22

A survey of tool use and workflows in alignment research

1 min read
24
Sep
'21

Interesting Applications of GPT-3: Elicit

9 min read