alignment

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.

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.

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.

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.

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.

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.

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.

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.

An 8-minute fictional short film, made by campaigners for a ban on autonomous weapons, depicting swarms of cheap AI-guided micro-drones used to kill targeted people. It ends with a call to action against autonomous weapons.

Last Day of War is an award-winning CGI animated short by Dima Fedotov in which automated machines keep following orders and prepare a bomber after all humans are dead.

Chris Stucchio presents the ethical principles behind algorithmic decision making and shows with examples from lending, criminology and education that they cannot all be satisfied at once. The talk frames AI fairness as a set of quantitative tradeoffs.

A 3-minute CGI animated sci-fi short by Dima Fedotov. An automated war system keeps a lone bomber attacking a long-dead city after humanity has been wiped out, until life finds a way to survive.

A roughly 2.5-hour Joe Rogan conversation with Elon Musk covering AI, simulation theory, climate, his companies and his mindset.

Sam Harris argues in a TED talk that we will build superhuman AI and have not grappled with the risk of creating something that may treat us the way we treat ants. He makes a logical case for taking AI risk seriously.

A dramatized fictional video of micro drones with facial recognition and swarm AI used as autonomous killer weapons. It is a Slaughterbots-style warning about lethal autonomous weapons.

Demis Hassabis of DeepMind speaks at Google Zeitgeist, saying human-level AI is decades away but the debate should start now. He covers DeepMind's focus on game-playing agents.

A one-minute clip from a 2016 Toronto conference in which Geoff Hinton comments on deep learning and radiology. He suggests radiologists should stop being trained because machines would soon read scans better.

Slaughterbots, a short dystopian film in which swarms of small autonomous drones are programmed to kill targets matching a profile. It opens as a slick product launch before turning into a terror scenario.

A Vanity Fair Summit conversation between Elon Musk and Sam Altman, moderated by Andrew Ross Sorkin. They discuss the future of technology, including AI and the simulation hypothesis.

A 2019 extended interview in which Connie Loizos talks with Sam Altman about his work, OpenAI's capped-profit structure, its mission toward safe artificial general intelligence, and criticisms the organization faces.

Alibaba's Jack Ma and Tesla's Elon Musk debate artificial intelligence on stage in Shanghai in 2019.

A panel from the Beneficial AI 2017 conference moderated by Max Tegmark, with Elon Musk, Stuart Russell, Kurzweil, Hassabis, Harris, Bostrom, Chalmers and others. They discuss likely outcomes of human-level AGI and what outcomes are desirable.

Ray Kurzweil presents his book How to Create a Mind at Google, on reverse engineering the brain and using that understanding to build intelligent machines. He shows his graphs of exponential technological progress.

Emery Berger explains why performance is hard to measure and deliver on modern hardware, showing how code layout and alignment can swamp optimization effects. He presents Stabilizer for statistically sound evaluation and Coz, a causal profiler.