Mesa-Optimization

Applied to Principled Satisficing To Avoid Goodhart by JenniferRM 3mo ago

Applied to Pacing Outside the Box: RNNs Learn to Plan in Sokoban by Adrià Garriga-alonso 4mo ago

Applied to Finding Backward Chaining Circuits in Transformers Trained on Tree Search by abhayesian 6mo ago

Applied to Inner Optimization Mechanisms in Neural Nets by ProgramCrafter 6mo ago

Applied to The Human's Role in Mesa Optimization by silentbob 6mo ago

Applied to Visualizing neural network planning by Nevan Wichers 6mo ago

Applied to Measuring Learned Optimization in Small Transformer Models by J Bostock 7mo ago

Applied to Understanding mesa-optimization using toy models by tilmanr 7mo ago

Applied to Counting arguments provide no evidence for AI doom by Quintin Pope 9mo ago

Applied to The Inner Alignment Problem by Jakub Halmeš 9mo ago

Applied to Satisficers want to become maximisers by JenniferRM 1y ago

Applied to Mesa-Optimization: Explain it like I'm 10 Edition by brook 1y ago

Applied to Runaway Optimizers in Mind Space by silentbob 1y ago

Applied to Disincentivizing deception in mesa optimizers with Model Tampering by martinkunev 1y ago