Omnipheasant

Message

-1

Could LLMs Learn to Detect Bias Autonomously, Like Tesla’s Self-Driving Cars?

LLMs are shaped by human curator making decisions about what data is “ethical” or “safe.” This curation introduces biases, focusing on politically salient issues like fairness for marginalized groups while often overlooking subtler distortions, such as selective outrage or perfectionist comparisons. What if LLMs could judge input themselves, learning from...

Apr 18, 2025•0

Message

-1 karma

1 post

Member for 4 years

Omnipheasant — LessWrong

Omnipheasant

Message

-1

Omnipheasant

Could LLMs Learn to Detect Bias Autonomously, Like Tesla’s Self-Driving Cars?

Apr 18, 2025•0

Message

-1 karma

1 post

Member for 4 years

Could LLMs Learn to Detect Bias Autonomously, Like Tesla’s Self-Driving Cars?

Omnipheasant

10mo

Inspired by Tesla’s Full Self-Driving (FSD) system, which learns from real-world driving data, including crashes, I propose that LLMs could use self-supervised learning to evaluate internet data autonomously. By verifying predictions over time and analyzing emotionally charged accusations against comparative data, LLMs could become more robust and less dependent on human curators. These methods are just two... (read 896 more words →)

LESSWRONG
LW

LESSWRONG
LW

Omnipheasant

Omnipheasant

Omnipheasant

Could LLMs Learn to Detect Bias Autonomously, Like Tesla’s Self-Driving Cars?

Omnipheasant

Omnipheasant

Omnipheasant

Could LLMs Learn to Detect Bias Autonomously, Like Tesla’s Self-Driving Cars?