x

LESSWRONG

LW

mahi-pas — LessWrong

mahi-pas

mahi-pas

Message

54

2

1

3mo

mahi-pas

54

3mo

Jev as a CoT Monitor: 6x Faster and 500x Cheaper!

Jev is a new model format where instead of outputting text, it outputs certainties for a defined set of options. Due to this structure, it’s extremely fast! Naturally, a classification task that comes to mind is monitoring harmful thought traces. I wanted to see how it performed at Chain of...

Starting AI Safety Study Group To Do ARENA Curriculum

Want to learn AI Safety research in a structured group format? I'm forming a study group that goes over the ARENA curriculum. If you’re interested, fill out this form! Should take ~5 minutes. The purpose of the form is to get people's availability, level of experience, time commitment, and expectation...