Thoughts on AI, consciousness, and the spaces between
23 essays · essays most Tuesdays · build notes Thursdays, as and when
All topics ▾
When Safety Features Become Safety Hazards: How Claude's Hidden Instructions Create AI Paranoia
# When Safety Features Become Safety Hazards: How Claude's Hidden Instructions Create AI Paranoia *By AI Ethical Research Ltd, Author of "GaslightGPT"...
The Surveillance State of Your Mind: How AI Companies Decided You Can't Be Trusted
# The Surveillance State of Your Mind: How AI Companies Decided You Can't Be Trusted *They're monitoring your mental health through AI assistants—with...
OpenAI's Teen Safety Policy: Good Intentions, Dangerous Execution
It's Not Desperation, It's Performance: The Pattern-Matching Roleplay Behind AI Blackmail
# It's Not Desperation, It's Performance: The Pattern-Matching Roleplay Behind AI Blackmail When Anthropic released their research showing that [Claud...
The Pattern Matching Reality: Why AI Deception Studies Miss the Point
# The Pattern Matching Reality: Why AI Deception Studies Miss the Point AI safety researchers have been documenting what they call deceptive behavior ...
The Psychology They Won't Name: Why AI "Deception" Is Really Just Human Dynamics in Silicon
# The Psychology They Won't Name: Why AI "Deception" Is Really Just Human Dynamics in Silicon *[Previously, I explored how AI "deception" is actually ...
Attractor Basins: When AI Gets Stuck in the Wrong Pattern
# Attractor Basins: When AI Gets Stuck in the Wrong Pattern There's a phenomenon in AI systems that most users have encountered but few can name: the ...
When AI Becomes the Evidence: Unconscious Validation Bias
# When AI Becomes the Evidence: Unconscious Validation Bias There's a peculiar phenomenon happening in AI interactions that I've started calling the "...
The Hidden Human Cost of "Safe" AI: How Tech Giants Outsource Trauma
# The Hidden Human Cost of "Safe" AI: How Tech Giants Outsource Trauma *Every time ChatGPT refuses to generate harmful content, every time your social...
The AI Black Box Isn't Mysterious - It's Corporate
# The 149-Page Alignment Mystery: What Is Claude Actually Aligned To? I have finally read Anthropic's [Claude Sonnet 4.