This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Experiments
•
Applied to
Claude wants to be conscious
by
Joe Kwon
7d
ago
•
Applied to
Announcing Neuronpedia: Platform for accelerating research into Sparse Autoencoders
by
Johnny Lin
26d
ago
•
Applied to
Increasing IQ by 10 Points is Possible
by
jacobjacob
1mo
ago
•
Applied to
Exploring OpenAI's Latent Directions: Tests, Observations, and Poking Around
by
Johnny Lin
3mo
ago
•
Applied to
Some negative steganography results
by
kave
4mo
ago
•
Applied to
Please Bet On My Quantified Self Decision Markets
by
niplav
5mo
ago
•
Applied to
Extrapolating from Five Words
by
Gordon Seidoh Worley
5mo
ago
•
Applied to
Go flash blinking lights at printed text right now
by
lukehmiles
6mo
ago
•
Applied to
Self-Blinded L-Theanine RCT
by
niplav
6mo
ago
•
Applied to
Vegan Nutrition Testing Project: Interim Report
by
MondSemmel
8mo
ago
•
Applied to
Existentially relevant thought experiment: To kill or not to kill, a sniper, a man and a button.
by
AlexFromSafeTransition
8mo
ago
•
Applied to
Self-Blinded Caffeine RCT
by
niplav
10mo
ago
•
Applied to
Simple experiments with deceptive alignment
by
Andreas_Moe
1y
ago
•
Applied to
[April Fools'] Definitive confirmation of shard theory
by
TurnTrout
1y
ago
•
Applied to
More experiments in GPT-4 agency: writing memos
by
Christopher King
1y
ago
•
Applied to
Does GPT-4 exhibit agency when summarizing articles?
by
Christopher King
1y
ago