Shard Theory - is it true for humans? (And is it a good model for value learning in AI?) – BlueDot Impact
AI Alignment (2024 Mar)

Shard Theory – is it true for humans? (And is it a good model for value learning in AI?)

By Rishika Bose (Published on July 3, 2024)

Shard theory proposes a view of value formation where experiences lead to the creation of context-based ‘shards’ that determine behaviour. Here, we go over psychological and neuroscientific views of learning, and find that while shard theory’s emphasis on context bears similarity to types of learning such as conditioning, it does not address top-down influences that may decrease the locality of value-learning in the brain.

 

Read the full piece here.

We use analytics cookies to improve our website and measure ad performance. Cookie Policy.