What is it like to be a neural net?

·LessWrong··

A condensed presentation of Gradland and Metabolic Fire. Code is here. This is intended as the first of two posts. Thomas Nagel argued we cannot know what it is like to be a bat, because a bat's experience is organised around biophysical apparatus we lack. The obstacle is that we cannot imagine the structure of echolocation from the inside. That is a failure of imagination; it is not an argument that structure is irrelevant. We know a lot about the structure of large language models. Not everyth...

Read full article →

Related Articles

Agents let AI safety share experiments hourly, not just papers monthly
Jason Fantl · LessWrong · 28m ago
Measuring alignment drift via trajectory prefixes
Owen Terry · LessWrong · 30m ago
Constraining the capacity of physical side channels for AI verification and security
emlynsg · LessWrong · 36m ago
Can parts of the HuggingFace incident be simulated?
Benedikt Droste · LessWrong · 36m ago
MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 2mo ago