alignment

Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the wrong goal in training and misbehaves when deployed.

A Bankless podcast interview with Paul Christiano of the Alignment Research Center on the AI alignment problem and possible solutions. It also covers his views on how an AI takeover might unfold.

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.

A three-hour Lex Fridman podcast conversation with AI researcher Eliezer Yudkowsky about the dangers of superintelligent AI and his argument that it could end human civilization. It covers AI alignment, why he thinks LLM capabilities are poorly understood, and the case for extreme caution.

Dwarkesh Patel interviews OpenAI chief scientist Ilya Sutskever on time to AGI, what comes after generative models, data limits, alignment, and competing with Google. The title centers on whether next-token prediction could surpass human intelligence.

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.

Sebastien Bubeck presents the Sparks of AGI paper at MIT, showing early experiments with GPT-4 across many domains and asking whether artificial intelligence has arrived. It includes the TikZ unicorn example.

A Computerphile video in which Rob Miles warns against assuming a general AI will think like a human. He uses the thought experiment of a stamp-collecting AI to show how a goal-driven system could pursue its aim with dangerous results.

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.

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.

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.

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.

A speculative-fiction video by Tom Scott, framed as coming from a future, about an AI called Earworm that enforces copyright so aggressively that humanity ends up forgetting a century of pop culture. It is animated and narrated as part of his series of videos from a future.

OpenAI's short demo of agents playing hide-and-seek in a simulated environment. Through self-play, the agents develop six progressively more complex strategies and counter-strategies, including tool use.

CGP Grey's video "Humans Need Not Apply" argues that automation will make a large part of the workforce economically obsolete, much as engines did for horses. It surveys robots and software replacing both physical and mental labor.

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.

Veritasium's Derek Muller gives a Perimeter Institute livestream on how AI might change teaching and learning. He draws on past technology shifts and cognitive science to argue that learning requires effortful repetition.

Technosociologist Zeynep Tufekci argues that the machine-learning systems used to serve ads also decide what political and social information people see. She explains how opaque algorithms can nudge, segment and manipulate users, and warns that the real danger is powerful people using AI to control populations.

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.

Tristan Harris and Aza Raskin of the Center for Humane Technology present why current AI capabilities pose catastrophic societal risks. They argue companies are racing to deploy without adequate safety, and that institutions must adapt. It was given before GPT-4's launch.

Slaughterbots is a fictional short film, backed by Stuart Russell, depicting swarms of cheap autonomous drones that use facial recognition to assassinate targets. It was made to argue for banning autonomous weapons.

Charles Stross's 34C3 talk on how science fiction gets the future wrong. He argues that corporations are slow, human-powered AIs that optimize for profit, and that regulation lags behind accelerating technology.

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.

Slaughterbots is a short sci-fi film in which swarms of cheap autonomous drones are programmed to kill targets by profile. It was made as arms-control advocacy against autonomous weapons.

Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.

Geoffrey Hinton's 2025 Royal Institution Discourse on what AI has learned from biological intelligence and how it might surpass it. He explains neural networks and argues that human language use resembles what backpropagation-trained networks do.

Lex Fridman's long conversation with Andrej Karpathy on Tesla's self-driving approach, Optimus, neural networks, transformers, AGI and more. It also touches on his OpenAI work and working with Elon Musk.

Joscha Bach's 35C3 talk offers an AI perspective on the soul, covering perception, mental representation, agency, consciousness and selfhood as things that can arise in a computational system like the brain.

Yannic Kilcher explains how he trained a language model on three years of 4chan's /pol/ board and let it post on the site. He evaluates how good the model was and discusses the ethics and fallout.

FTC Chair Lina Khan sits down with Jon Stewart on The Daily Show to discuss the agency's work protecting consumers from unfair business practices. Topics include the FTC's antitrust lawsuit against Amazon, healthcare industry actions, and whether tech companies are racing to control AI.

Novelist Daniel Suarez warns in a TED talk about autonomous robotic weapons and drones. He argues that taking the decision to kill out of human hands threatens democratic accountability and calls for a ban.

Lex Fridman interviews chip architect Jim Keller about the future of computing, AI, life and consciousness. Topics include CPU design, branch prediction and why imperfect designs often win.

A five-hour Lex Fridman interview with John Carmack covering Doom, Quake, VR, AGI, programming, games and rockets.

Tom Scott describes trying ChatGPT to fix his Gmail labels and being unsettled by how capable it was. He argues that we cannot know where we are on the technology curve, comparing it to Napster.

Victoria Warmerdam's Oscar-winning Dutch short film in which a woman fails a series of Captcha tests and is plunged into a strange new reality. It is a dark, Black Mirror-like sci-fi comedy.

Bloomberg Technology interviews Google engineer Blake Lemoine about the experiments that led him to believe LaMDA was sentient and why he was placed on administrative leave. He also raises concerns about AI ethics at Google.

Brandon Sanderson's keynote on AI-generated art, arguing that the artistic process and the journey matter more than the finished product. He explains why he rebels against generative AI in creative work.

A Munk Debate on the proposition that AI research and development poses an existential threat. Yoshua Bengio and Max Tegmark argue for it, and Melanie Mitchell and Yann LeCun argue against.

Andrew Ng speaks at the Stanford MSx Future Forum about how AI is transforming industry after industry, comparing its impact to electricity. The talk also touches on evil-AI worries, jobs and basic income.

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.