Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ

March 14, 2024 · Seattle

repeng

Learn how to use activation hacking and lightweight control vectors to modify LLM behavior, create personas, improve focus, and mitigate jailbreaks on a single GPU.

Overview

Activation hacking for controlling LLM personas with quick to train control vectors – I have a blog post about it at https://vgel.me/posts/representation-engineering

Links

Tech stack