AIs will be used in “unhinged” configurations
Writing up a probably-obvious point that I want to refer to later, with significant writing…
Category: Opinion
Sanity Weekend Retrospective
Last December, we ran a workshop on exploring civilizational sanity. Our core team consisted of…
What do we know about AI company employee giving?
Many Anthropic employees, especially, are sympathetic to AI safety and (will) have lots of money.…
The Day After Move 37
I was a few months into 21 years old when a hijacked plane crashed into…
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
TL;DR We release AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with…
Economic efficiency often undermines sociopolitical autonomy
Many people in my intellectual circles use economic abstractions as one of their main tools…
Letting Claude do Autonomous Research to Improve SAEs
This work was done as part of MATS 7.1I pointed Claude at our new synthetic…
Don’t Let LLMs Write For You
Content note: nothing in this piece is a prank or jumpscare where I smirkingly reveal…
Questions to ask when everyone is shooting themselves in the foot
Why is everyone shooting themselves in the foot? What's wrong with institutions/incentives that makes foot-shooting an…
The case for satiating cheaply-satisfied AI preferences
A central AI safety concern is that AIs will develop unintended preferences and undermine human…