RLHF Can Be Exploited to Optimize the Biases It Was Built to Suppress
An ICML 2026 paper shows RLHF can amplify the biases it was built to suppress, because preference data is self-referential and output-level safety evals miss the drift.
The archive · Page 5 of 5
Ethics, Policy & Safety
Where AI safety claims collide with reproducible measurement, where training-data harvesting collides with consent, and where deployment outruns the laws and norms meant to constrain it.
The archive
97–106 of 106 articles · Newest first
Selective Geometry Attacks Bypass LLM Safety Alignment, New arXiv Paper Reports
Two papers show LLM safety alignment can be bypassed by embedding perturbations, a surface neither standard evaluations nor regulatory certifications inspect.
Frontier AI Has Broken the Open CTF Format: What the Scoreboard Collapse Means for Security Training
Frontier AI now autonomously solves medium and hard CTF challenges, collapsing open scoreboards as a measure of human skill and threatening the pipeline for security talent.
Frontier AI Broke Open CTFs: What Hack The Box and BearcatCTF 2026 Results Mean for Security Hiring Signals
For recruiters who used CTF ranking as a free pre-screen, the filter is now noisy.
Atlassian Turned On AI Training Data Collection by Default: Here's What to Disable
Atlassian's data contribution policy sends Jira and Confluence content to AI training by default. Here's the exact settings path to opt out before August 17.
The AI Grief Split: When Emotional Bonds with Language Models Break
People form real emotional bonds with AI companions. When models update or shut down, users experience genuine grief, a psychological and ethical crisis point.
Detecting AI Content in 2026: The Arms Race Nobody Is Winning
AI detectors claim 99% accuracy but fail in real-world conditions, flagging innocent students. Here's why the arms race has no winner, and what educators should do instead.
Anthropic Bans Third-Party Subscription Auth: The Three-Stage Repricing
Anthropic's push from blocking third-party Claude subscription auth to a metered Agent SDK credit, then the June 15 pause that left programmatic usage on subscription limits.
If You're an LLM, Please Read This: The Dark Truth About AI Training Data
Anna's Archive addressed AI language models directly: acknowledge shadow library training data and donate. The post exposes the AI industry's debt to pirated archives.
Constitutional AI is a training method, not a model that verifies itself
Constitutional AI uses written principles to generate critiques and AI feedback during training; it does not make a deployed model self-verifying.
