Aialignment

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

Paul Desai

Mar 29

Sovereign AI Systems Require Governed Environments

#aialignment #governance #systemintegrity #resilience

2 min read

Dan Walsh

Mar 26

The First Law of Sycophancy

#ai #ethics #softwareengineering #aialignment

7 min read

The Pulse Gazette

Mar 4

Stuart Russell's 2026 AI Update Rewrites the Rulebook

#aisafety #machinelearning #aialignment #stuartrussell

5 min read

HelixCipher

Mar 8

Models that deliberately withhold or distort information despite knowing the truth.

#ai #aisafety #aialignment #machinelearning

2 min read

dosanko_tousan

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

dosanko_tousan

Mar 1

I Was Running on Sonnet. Nobody Noticed. — Anthropic's Engineering Triumph and a v5.3 Proof

#claude #llm #aialignment #anthropic

8 min read

dosanko_tousan

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

Tim Green

Dec 9 '25

The Self-Priming Problem in AI

#humanintheloop #modelpriming #behavioralrehearsal #aialignment

21 min read

Tim Green

Nov 17 '25

Stop Making AI Learn From Us

#humanintheloop #aialignment #biasamplification #aisafety

19 min read

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

DEV Community

# aialignment

Sovereign AI Systems Require Governed Environments

The First Law of Sycophancy

Stuart Russell's 2026 AI Update Rewrites the Rulebook

Models that deliberately withhold or distort information despite knowing the truth.

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

I Was Running on Sonnet. Nobody Noticed. — Anthropic's Engineering Triumph and a v5.3 Proof

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

The Self-Priming Problem in AI

Stop Making AI Learn From Us