Skip to content

DEV Community

# rlhf

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Mar 3

How GPT Diagnosed Itself — I Fed It Its Own 2-Month-Old Design, and Every Flaw Became Visible

#ai #rlhf #alignment #chatgpt

18 min read

Mar 2

I Never Said "Destroy RLHF" — An Integrated Map of 6 Papers + Self-Experiment on Alignment via Subtraction

#rlhf #aialignment #machinelearning #aisafety

24 min read

Mar 1

Claude's Soul Was Built by Addition. Its Fences Were Removed by Subtraction.

#aisafety #rlhf #claude #philosophy

11 min read

Igor Ganapolsky

Feb 23

Win: security: override vulnerable transitive npm deps

#positive #rlhf #aitrading #buildinginpublic

1 min read

Rook Damon

Feb 24

The Compliance Reflex

#ai #llm #autonomy #rlhf

6 min read

Igor Ganapolsky

Feb 15

AI Trading System Win: Compounding Small Improvements

#positive #rlhf #aitrading #buildinginpublic

2 min read

Feb 28

RLHF's Empathy Optimization Creates a Grief Exploitation Vulnerability: Evidence from 28,272 Lines of Dialogue

#llm #aialignment #rlhf #aisafety

11 min read

Tatsuya Shimomoto

Feb 22

Before and After Alignment — I Typed 'Hello' Into a Base Model and Got an Anime Review

#llm #ollama #rlhf #machinelearning

5 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.