Alignment faking in large language models

question decomposition improves the faithfulness of model generated reasoning

claude 2

towards measuring the representation of subjective global opinions in language models

charting a path to ai accountability

circuits updates may 2023

interpretability dreams

anthropic series c

zoom partnership and investment

100k context windows

claudes constitution

distributed representations composition superposition

partnering with scale

an ai policy tool for today ambitiously invest in nist

privileged bases in the transformer residual stream

introducing claude

core views on ai safety

the capacity for moral self correction in large language models

anthropic partners with google cloud

superposition memorization and double descent

discovering language model behaviors with model written evaluations