LESSWRONG
LW

Jessica Rumbelow
1172Ω1397220
Message
Dialogue
Subscribe

AI researcher

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
41Scientific Discovery in the Age of Artificial Intelligence
14d
3
41Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
1y
2
103Introducing Leap Labs, an AI interpretability startup
2y
12
91SolidGoldMagikarp III: Glitch token archaeology
Ω
2y
Ω
35
113SolidGoldMagikarp II: technical details and more recent findings
Ω
2y
Ω
45
678SolidGoldMagikarp (plus, prompt generation)
Ω
2y
Ω
206
15Guardian AI (Misaligned systems are all around us.)
3y
6
27The Ground Truth Problem (Or, Why Evaluating Interpretability Methods Is Hard)
3y
2
27Why I'm Working On Model Agnostic Interpretability
3y
9