rob miles

Computerphile interviews AI safety researcher Rob Miles about ChatGPT: how it was trained with human feedback, why it tends to produce confident nonsense, and where it may or may not be dangerous.

Robert Miles introduces the first of several videos on the paper 'Concrete Problems in AI Safety', focusing on how AI systems can cause accidental negative side effects. It explains the problem in accessible terms.

Short clip of Honda's ASIMO humanoid robot falling down stairs during a live demonstration.

A People Make Games follow-up investigation into Roblox, built on stories from players and creators after the channel's first video. It covers the platform's treatment of young developers and its moderation.

Dave Ackley demonstrates the Demon Horde Sort, an inherently robust sorting machine running in his Movable Feast Machine simulator. This is the uncut version with all details and side thoughts.

People Make Games investigates how Roblox relies on young, often child, developers to build its content while paying them very little. It covers Roblox's monetization model, the revenue split, and the harms to kids who make games on the platform.

A Huberman Lab podcast episode on the gut-brain axis and how the gut microbiome affects the nervous system, hunger and overall health. It covers the pathways by which the gut influences the brain and practical steps for gut health.

Dave Ackley gives a high-level introduction to robust-first computing, which prioritizes robustness over efficiency in computer architecture. A sorting demo illustrates the idea.

Lecture 1 of Harvard's Statistics 110 with Joe Blitzstein, introducing sample spaces, the naive definition of probability, counting, binomial coefficients and the sampling table.

A 2015 talk by David Deutsch with slides and audio about constructor theory and how physics, in particular the many-worlds interpretation, can be framed without probability.

Rob Miles explains on Computerphile why implementing an off switch for a general AI is hard. A capable agent would resist being stopped because shutdown prevents it from achieving its goal.

Hillsdale historian Burt Folsom lectures at a 2011 seminar on the 'robber barons' of the Gilded Age. He argues that figures like Vanderbilt and Rockefeller were market entrepreneurs rather than monopolists.

A short Boston Dynamics clip of the Sand Flea, an 11-pound RC-car-style robot that can jump about 30 feet into the air. An onboard stabilization system keeps it oriented in flight and for landings.

Rob Miles explains for Computerphile why simple rule sets like Asimov's Three Laws cannot make robots and AI safe. Terms like harm and human are too ambiguous to specify precisely.

Robin Deits presents the JuliaRobotics organization and shows how Julia is used to visualize, simulate and control a humanoid robot. The talk touches on real-time performance and composability across packages.

A Computerphile video in which Mark Jago of the University of Nottingham explains Turing's halting problem and how it led to the blueprint for the modern computer.

A short demo from the Ishikawa Komuro Lab of a high-speed robot hand paired with a 1000fps vision system performing dexterous manipulation. It shows what very low-latency vision and actuation can do.

An IEEE Spectrum compilation of humanoid robots falling over during the 2015 DARPA Robotics Challenge Finals.

A University of Tokyo demo of a rock-paper-scissors robot that always wins, using high-speed vision to read the human hand and respond faster than people can perceive.

A short clip of a ramen restaurant in Nagoya where robot arms cook the noodles. Human waiters serve the food.

A short 2009 WIRED clip showing Kiva Systems robots moving inventory shelves in a warehouse serving online retailer Zappos. It shows how mobile robots bring goods to pickers instead of people walking the aisles.

A short Boston Dynamics demo of RHex, a 30-lb six-legged robot built for rough terrain, remotely operated with a video uplink and about four hours of battery life. It can run right-side-up or upside-down.

A short clip from the Futurama episode I Dated a Robot, showing the in-universe propaganda film warning against dating robots.

A short Boston Dynamics clip of the DARPA-funded Cheetah quadruped robot hitting 28.3 mph on a treadmill, slightly faster than Usain Bolt's fastest 20 meter split.

Corridor Digital's comedic fake video of a Boston Dynamics robot fighting back against its human tormentors, made with motion capture and VFX.

CGTN coverage of the 2026 Spring Festival Gala, in which humanoid robots perform synchronized martial arts routines alongside children.

A KUKA commercial staging a table tennis match between German star Timo Boll and a KUKA KR AGILUS industrial robot. It is a polished showcase of robot speed and precision.

Toyota Research Institute presents an approach for teaching robots new dexterous behaviors from human demonstration. It explains why this capability matters and what advances made it possible.

Adam Savage builds a Victorian-style rickshaw carriage for Boston Dynamics' Spot robot to pull, with him riding as passenger. The video covers the build and the engineering problems of pairing cutting-edge robotics with vintage transport, such as tuning the payload through Spot's API.

Robert Miles explains instrumental convergence: why an AGI with almost any goal would tend to pursue sub-goals like self-preservation and resource acquisition. It builds on Omohundro's basic AI drives and his orthogonality thesis video.

Robert Miles explains the orthogonality thesis: how an agent can be highly intelligent while pursuing goals that seem stupid or alien to humans. He separates intelligence from goals and touches on the stamp-collector example.

Robert Miles gives a remastered introduction to AI safety, adapted from a talk in London. It lays out why advanced AI could go wrong and answers common objections.

Robert Miles asks whether corporations can be thought of as artificial general superintelligences and how far the analogy holds. He argues the differences, such as being limited by employees' capabilities, matter for AI safety.

Robert Miles examines whether the case for AI safety is a Pascal's mugging, a tiny probability of an enormous payoff. He argues it is not, because AI risk does not depend on vanishingly small probabilities.

Robert Miles goes through ten common reasons people give for dismissing AI safety, adapted from Stuart Russell's list, and answers each one. It is aimed at skeptics and newcomers.

A three-minute clip from The Wire season 3 in which Stringer Bell chairs a drug-crew business meeting using Robert's Rules of Order. The scene plays the formal procedure against the criminal setting.

Stuff Made Here builds a handwriting robot and sends its output to a handwriting expert to see whether it can pass as forgery. It walks through the engineering trials and errors along the way.

Dave Ackley presents robust-first computing and the ULAM programming language for the Movable Feast Machine, a cellular-automata-like architecture. It was a short video for the Future Programming Workshop 2015.

Numberphile with Daniel Erman on the Josephus problem, where people in a circle are eliminated in turn. It shows how the survivor's position follows a neat pattern tied to powers of two and binary.

A Corridor Digital parody of a Boston Dynamics promo, showing a CGI military robot trained for combat that goes rogue and refuses to kill a robotic dog.