On Brains, Minds, And Their Possible Uses
On Brains, Minds, And Their Possible Uses
Cognitive Biases in Large Language Models. Audio version.
1×
--:--
--:--

Cognitive Biases in Large Language Models. Audio version.

TL;DR: LMs exhibit some cognitive biases. Additionally, explain how cognitive biases can come about in humans. Raising questions about how universal deductive inference is.
Jan Hendrik Kirchner
Apr 14, 2022
Share
On Brains, Minds And Their Possible Uses
Cognitive Biases in Large Language Models
Humans, one might say, are the cyanobacteria of AI: we constantly emit large amounts of structured data, which implicitly rely on logic, causality, object permanence, history—all of that good stuff. All of that is implicit and encoded into our writings and videos and ‘data exhaust’. A model learning to predict must learn to understand all of that to get…
Read more
3 years ago · 1 like · Jan Hendrik Kirchner
0 Comments
On Brains, Minds, And Their Possible Uses
On Brains, Minds, And Their Possible Uses
Welcome to my little corner of mindspace
Listen on
Substack App
RSS Feed
Appears in episode
Jan Hendrik Kirchner
Recent Episodes
Via productiva. Audio version.
 • Jan Hendrik Kirchner
Inferring utility functions from locally non-transitive preferences. Audio version.
 • Jan Hendrik Kirchner
Task Decomposition And Scientific Inquiry. Audio version.
 • Jan Hendrik Kirchner
Puberty as Cause X? Audio version.
 • Jan Hendrik Kirchner
The Unreasonable Feasibility Of Playing Chess Under The Influence. Audio version.
 • Jan Hendrik Kirchner
Serendipitous connections: applying explanations from AI to the brain. Audio version.
 • Jan Hendrik Kirchner
Belief-conditional things. Audio version.
 • Jan Hendrik Kirchner
On (Not) Reading Papers. Audio version.
 • Jan Hendrik Kirchner