causal
Current LLMs Lack Intrinsic Goals
Ascribing intrinsic goals or desires to current language models is likely a category mistake because they learn passively from a stream of text, never genuinely interacting with the world, and after training are 'frozen'—their weights no longer adjust—whereas intrinsic, dynamic goals plausibly require more active learning and ongoing weight-adjusting interaction.
causalpending
Speaker
Raphael MilliereEvidence Quote
“At no stage in this process do we have an opportunity for genuine interaction between the model and the world or even between the model and the language on the world.”
Created: 6/13/2026, 12:19:51 AM
Your notes
Loading notes...