This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
10
Jessica Rumbelow — LessWrong
Jessica Rumbelow
AI researcher
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
42
Scientific Discovery in the Age of Artificial Intelligence
4mo
3
43
Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
1y
2
103
Introducing Leap Labs, an AI interpretability startup
3y
12
91
SolidGoldMagikarp III: Glitch token archaeology
Ω
3y
Ω
36
114
SolidGoldMagikarp II: technical details and more recent findings
Ω
3y
Ω
45
687
SolidGoldMagikarp (plus, prompt generation)
Ω
3y
Ω
208
15
Guardian AI (Misaligned systems are all around us.)
3y
6
27
The Ground Truth Problem (Or, Why Evaluating Interpretability Methods Is Hard)
3y
2
27
Why I'm Working On Model Agnostic Interpretability
3y
9
Comments