reward function

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.

An episode of FunFunFunction explaining monads in JavaScript as functors that also implement flatMap. It builds on the preceding functor episode and works through code examples.

A Downfall-style parody in which Hitler rages about functional programming concepts such as monads and Haskell. It runs about four minutes.

Martin Donald explains the Wave Function Collapse algorithm using Sudoku-like constraint solving and shows how he implemented it with Blender and Godot. It links demos and reference articles.

A short excerpt from Dr Russell Barkley's 2012 Burnett Lecture on ADHD, focused on treatment. He argues ADHD is a disorder of executive function and self-regulation, and that environments should be designed to compensate.

Part 1 of a lecture by physicist Albert Bartlett on the exponential function and its consequences for population growth, resource use and energy. It argues that steady growth rates quickly lead to enormous quantities.

An animated visualization of basic quantum mechanics using a free particle, with simulations based on the actual equations. It covers waves, particles, and how measurement collapses the wavefunction.

Stephen Wolfram gives a 13-minute tour of the Wolfram Language, a symbolic, functional programming language with a built-in knowledgebase. He demos querying large datasets, interactivity and deployment.

John Scholes builds a depth-first tree-search operator step by step in a Dyalog APL session. It covers higher-order functions and runs the search on the N-Queens problem.

Tom Scott features Kurtis Baute inside a sealed homemade biodome as carbon dioxide builds up, showing how stale air with elevated CO2 affects cognitive function. Sources include studies on CO2 and cognitive scores.

A short Art of the Problem clip explaining Diffie-Hellman key exchange, using a paint mixing analogy for one-way functions and touching on modular arithmetic and discrete logarithms.

An Extra Credits episode on how games use Skinner box operant conditioning and reward schedules to keep players playing and spending. It argues for more immersive design mechanics than simple reward loops.

The first clip from Russell Barkley's 30 Essential Ideas about ADHD series, introducing ADHD as a chronic developmental disability. It is part of a lecture series on the disorder by a leading ADHD researcher.

A humorous 10-minute parody sequel to Erlang: The Movie, in which Erlang's creators discuss the aging language and meet a surprise helper. It plays on the Outlaw Techno Psychobitch joke for OTP.

A short How to ADHD explainer, featuring Brendan Mahan, on why simple tasks can feel impossible for people with ADHD. It introduces the 'wall of awful', a pile of past failures, shame and anxiety that builds up in front of a task and blocks starting it.

A Dyalog demonstration of developing a Sudoku solver in APL, using an algorithm by Arthur Whitney with performance work by John Scholes. The narration steps through the array-oriented solution.

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.

Dan Pink's TED talk argues that traditional carrot-and-stick rewards often fail for creative work, drawing on the candle problem and social science research. He points to autonomy, mastery and purpose as better motivators.

Gary Wilson's TEDxGlasgow talk argues that internet pornography hyperstimulates the brain's reward system and can cause symptoms that reverse when people stop. TED notes that several claims are not supported by respected academic studies.

An Extra Credits episode on China's Sesame Credit, which gamifies obedient citizenship through a social score. It covers how the system rewards conformity and pressures people through their friends' behavior.

The first part of a long series documenting Dave Bull's Tokyo woodblock workshop as it produces a reproduction of Hokusai's The Great Wave. It follows the carving, proofing and printing of the reward print for Kickstarter backers.

A short Veritasium video explaining regression to the mean and how ignoring it leads to wrong conclusions about punishment versus reward, medical treatments and sports streaks. It uses the example of flight instructors who believed criticism works better than praise.

Linus Akesson demonstrates the Commodordion, a fully functional 8-bit accordion built around Commodore 64 hardware with bellows made of floppy disks. He performs Scott Joplin's Maple Leaf Rag and tells the story of the build.

Milton Friedman explains why the US tax code is enormously complex and why meaningful reform is unlikely. He argues that politicians profit from the complexity, since tax breaks are products they sell and the code works as a tool of reward and punishment. The clip is about 14 minutes from his lecture series.

A BBC Earth clip from Inside the Animal Mind in which a crow named 007 solves an eight-step puzzle to get a reward. It showcases crow problem-solving.

A short cartoon explaining how language models like ChatGPT work, from autocomplete and conditional probabilities to neural networks, gradient descent and backpropagation. It shows how networks act as universal function approximators.

KRAZAM parody sketch in which an Excel streamer, Makro, treats the XLOOKUP function as a game-breaking meta change, spoofing e-sports commentary.

Folding Ideas examines weird, algorithm-gamed children's content on YouTube, from automated toddler videos and educational spam to exploitative prank channels. It looks at how autoplay and recommendation systems reward this material.

Inigo Quilez shows step by step how to build a simple heart shape from mathematics and shaders, with code on Shadertoy. It is an introduction to procedural graphics and signed distance functions.

An excerpt from Russell Barkley's lecture on ADHD, focusing on inhibition, impulsivity and emotional regulation. It explains ADHD as a problem of response inhibition and emotional impulsivity.

Andreas Antonopoulos argues that money has a fourth function beyond store of value, medium of exchange and unit of account, which is as a system of control. He covers the history of money and why it does not flow freely.

Excerpts from W. Edwards Deming's Red Bead Experiment, where workers draw beads from a bowl and are judged on red ones that are largely down to chance. It shows how system variation, not individual effort, drives results.

A five-minute demo of the Common Lisp debugger fixing a bug, recompiling a single function, and resuming execution from the failed stack frame. It shows how to avoid re-running long computations.

Steve Jobs's January 2007 MacWorld keynote segment introducing the original iPhone. He presents it as a widescreen iPod, a phone and an internet communicator in one device.

A short demonstration of a crow using a purpose-built vending machine, in which the bird exchanges objects for rewards. The creator sells the machine as a kit.

A VICE News piece on China's Social Credit System, including a neighbor-watch pilot where paid watchers record behavior. It covers rewards for high scores and public shaming or restrictions for low ones.

A short Supernova 2007 provocation in which Clay Shirky uses a 1300-year-old Japanese shrine, rebuilt periodically, as a metaphor for how networks change business and collective creativity.

A short amateur clip of a Moscow grocery store from 1989, filmed by a visiting production worker. The shelves look sparse, and the uploader adds a note on the hard-working people living under a system that did not reward them.