ResearchNov 28, 2024
Reward Hacking in Reinforcement Learning#reinforcement learning#reward hacking#AI alignment#language models
Hooshware
ESTABLISHING NEURAL LINK...
L
Lilian Weng
Independent expert analysis from an established AI practitioner or researcher.
githubTrust 88/100Actively monitored
Latest coverage
News and signals attributed to Lilian Weng, with links to Hooshware coverage and the original publication.
ResearchJan 10, 2023
Large Transformer Model Inference Optimization#transformers#inference#optimization#machine learning