Robert Miles — Robert Miles AI Safety
About #
AI alignment researcher and the single most-watched AI safety communicator on YouTube — explains alignment, corrigibility, instrumental convergence, specification gaming, and existential risk from AI in accessible, technically grounded videos. Also appears on Computerphile and founded AISafety.info (Stampy), a community-maintained AI safety FAQ.
How this journal works #
Checked every 5 days: each new post or episode in Robert Miles’s own feeds (youtube) becomes one entry, dated by publication and summarised in a few bullets.
Entries
- Welcome to #TeamHuman
- Bio Risk is Not Like Cyber Risk
- Yyup...
- "Full AI Escape Seems Possible"
- Just Predicting Tokens
- People are Catching On
- Don't Let "Scepticism" Make You Useless: ActOnAI.org
- Why Smart AIs Cheat
- Did ChatGPT Just Commit a Felony?
- Is China Open to Making a Deal on AI?
- Useful Websites: AISafety.com
- AI can't DO my JOB quite yet
- Keeping AI in a Box
- AI Lie Detectors?
- "Stop the AI Race" protest outside OpenAI
- "Stop the AI Race" March in SF
- Mutually Assured Compute Destruction
- Why I Avoid Sci-Fi Specifics
- Update: AI Billionaire Attacks Backfire
- The AI Consciousness Question is So Annoying