person
Rob Miles
AI safety YouTuber
Former Nottingham PhD candidate who became the most-watched AI safety educator on YouTube. Translates Bostromian and Yudkowskian arguments into accessible video form.
Profile
expertise
Applied technical
Technical fluency from an adjacent field (security, robotics, formal methods, statistics) or applied AI work, but not on frontier loss curves or core ML theory.
AI safety educator. CS background. YouTube channel and Computerphile videos shape much public AI-safety understanding.
recognition
Field-leading
Widely known inside the AI and AI-safety community. Appears repeatedly in top venues, podcasts, or governance forums. Not a household name to outsiders.
Educational reach via YouTube. Less mainstream-press profile.
vintage
Deep-learning rise
Came up post-AlexNet. ImageNet, AlphaGo, transformer paper. DeepMind, Google Brain, FAIR establish the modern lab template.
Computerphile AI safety videos from 2017. Educational career is deep-learning era; frames safety for that audience.
Hand-classified. See the board for the criteria and the full grid.
Strategy positions
Alignment firstendorses
Solve technical alignment before capability thresholds closePublic educator on alignment theory: instrumental convergence, specification gaming, inner alignment, mesa-optimization, deceptive alignment. Explains them in plain language for non-technical audiences.
You don't need the AI to hate you. Almost any objective, pursued hard enough, runs us over as a side effect.
We need to know how to build AGIs we can trust before we build the AGIs. Right now we don't know how, and that is the whole problem.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Rob Miles's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-24.