You need to be logged in to mark episodes as watched. Log in or sign up.
Season 2025
2025x1 Computer Timescales Mapped onto Human Timescales Episode overview
Air date
Jan 07, 2025
This episode has no summary.
This episode has no summary.
2025x2 Solve Markov Decision Processes with the Value Iteration Algorithm Episode overview
Air date
Jan 16, 2025
Returning to the Markov Decision Process, this time with a solution. Nick Hawes of the ORI takes us through the algorithm, strap in for an epic episode!
Returning to the Markov Decision Process, this time with a solution. Nick Hawes of the ORI takes us through the algorithm, strap in for an epic episode!
2025x3 Quicksort Algorithm in Five Lines of Code! Episode overview
Air date
Jan 21, 2025
Quicksort is a well known algorithm for sorting, Professor Graham Hutton shows how it works and then how to implement it in just five lines of code!
Quicksort is a well known algorithm for sorting, Professor Graham Hutton shows how it works and then how to implement it in just five lines of code!
An AI model that changed the fortunes of silicon valley overnight. Deep Seek has been released open source, and requires far less hardware and investment. Mike Pound is based at the University of Nottingham.
An AI model that changed the fortunes of silicon valley overnight. Deep Seek has been released open source, and requires far less hardware and investment. Mike Pound is based at the University of Nottingham.
Relatively speedy-to-access cache saves your computer having to trudge over to the RAM, but with multiple levels of cache memory, how does it all work?
Relatively speedy-to-access cache saves your computer having to trudge over to the RAM, but with multiple levels of cache memory, how does it all work?
The algorithm for differentiation relies on some pretty obscure mathematics, but it works! Mark Williams demonstrates Forward Mode Automatic Differentiation.
The algorithm for differentiation relies on some pretty obscure mathematics, but it works! Mark Williams demonstrates Forward Mode Automatic Differentiation.
2025x7 No Regrets - What Happens to AI Beyond Generative? Episode overview
Air date
Feb 24, 2025
Discussing ideas of what happens after Generative AI plateaus, Dr Jakob Foerster is based at the University of Oxford.
Discussing ideas of what happens after Generative AI plateaus, Dr Jakob Foerster is based at the University of Oxford.
Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection, except not...
Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection, except not...
2025x9 Carbon: (C++)++ ? Can Carbon De-Throne C++? Episode overview
Air date
Mar 04, 2025
Carbon is a brand new programming language still under development. It aims to dethrone C++ by being interoperable & compatible in both directions. Dr Guiffreida from the University of .. show full overview
Carbon is a brand new programming language still under development. It aims to dethrone C++ by being interoperable & compatible in both directions. Dr Guiffreida from the University of Nottingham gives us the lowdown on this ambitious new programming language.
GTC AI Conference is held each year by Nvidia and showcases AI and related technologies. This year Computerphile visited, here's a taste of what we saw. Full interviews coming soon, and yes, we did speak to him!
GTC AI Conference is held each year by Nvidia and showcases AI and related technologies. This year Computerphile visited, here's a taste of what we saw. Full interviews coming soon, and yes, we did speak to him!
Nvidia CEO and co-founder Jensen Huang on various applications of GPUs and the rise of AI in all aspects of parallel processing.
Nvidia CEO and co-founder Jensen Huang on various applications of GPUs and the rise of AI in all aspects of parallel processing.
2025x12 Ai Will Try to Cheat & Escape (aka Rob Miles was Right!) Episode overview
Air date
Apr 02, 2025
As Large Language Models improve, the tokens they predict form ever more complicated and nuanced outcomes. Rob Miles and Ryan Greenblatt discuss "Alignment Faking" a paper Ryan's team .. show full overview
As Large Language Models improve, the tokens they predict form ever more complicated and nuanced outcomes. Rob Miles and Ryan Greenblatt discuss "Alignment Faking" a paper Ryan's team created - ideas about which Rob made a series of videos on Computerphile in 2017.
Discussing how scammers take advantage of the way certain online systems work to leverage the delays. Dr Tim Muller is based at the University of Nottingham.
Discussing how scammers take advantage of the way certain online systems work to leverage the delays. Dr Tim Muller is based at the University of Nottingham.
What is Cuda and why do we need it? An Nvidia invention, Cuda is used in many aspects of parallel computing. We spoke to Stephen Jones, one of the architects of Cuda at the recent GTC conference.
What is Cuda and why do we need it? An Nvidia invention, Cuda is used in many aspects of parallel computing. We spoke to Stephen Jones, one of the architects of Cuda at the recent GTC conference.
Research suggests the rate at which AI is able to stay 'on task' is doubling every seven months. Is this the AI equivalent of Moore's Law? - Sydney Von Arx works on adversarial stress-testing at METR (Model Evaluation & Threat Research.)
Research suggests the rate at which AI is able to stay 'on task' is doubling every seven months. Is this the AI equivalent of Moore's Law? - Sydney Von Arx works on adversarial stress-testing at METR (Model Evaluation & Threat Research.)
Bashing out low-level code, it can be annoying to re-type the same commands over and over when you need to repeat a routine. Matt Godbolt explains how we can save frequently used code as a subroutine and reuse whenever its needed.
Bashing out low-level code, it can be annoying to re-type the same commands over and over when you need to repeat a routine. Matt Godbolt explains how we can save frequently used code as a subroutine and reuse whenever its needed.
Following the theme of AI research and safety, Aric Floyd talks about how some Large Language Models might follow the all too human trait of sandbagging - "lying" about their true capabilities.
Following the theme of AI research and safety, Aric Floyd talks about how some Large Language Models might follow the all too human trait of sandbagging - "lying" about their true capabilities.
2025x21 MikeBot3000: Can We Build an AI Mike from Open Source Tools? Episode overview
Air date
May 29, 2025
Open source tools for creating videos? Lewis decides to help Mike take a break by creating 'MikeBot3000' - an AI generated Mike Pound...
Open source tools for creating videos? Lewis decides to help Mike take a break by creating 'MikeBot3000' - an AI generated Mike Pound...
"If your name's not down, you're not coming in!" - How the CPU's "Bouncer" keeps some memory off-limits. Matt Godbolt continues the series on low-level computing.
"If your name's not down, you're not coming in!" - How the CPU's "Bouncer" keeps some memory off-limits. Matt Godbolt continues the series on low-level computing.
2025x28 Zip It! - Finding File Similarity Using Compression Utilities Episode overview
Air date
Jul 15, 2025
Finding Genome similarity can just be a case of zipping the relevant files in the right order. Buck Shlegeris is CEO of Redwood Research
Finding Genome similarity can just be a case of zipping the relevant files in the right order. Buck Shlegeris is CEO of Redwood Research
Writing a text editor can't be that hard can it? Surely just a case of shifting around a bunch of ASCII characters? Dr Steve Bagley is based at the University of Nottingham
Writing a text editor can't be that hard can it? Surely just a case of shifting around a bunch of ASCII characters? Dr Steve Bagley is based at the University of Nottingham
Gödel's Incompleteness Theorem explained with Pen, Paper & Lean (the proof assistant) Professor Thorsten Altenkirch is based at the University of Nottingham.
Gödel's Incompleteness Theorem explained with Pen, Paper & Lean (the proof assistant) Professor Thorsten Altenkirch is based at the University of Nottingham.
2025x32 The Next Big SHA? SHA3 Sponge Function Explained Episode overview
Air date
Aug 20, 2025
If a bug is found in SHA2, SHA3 is already waiting in the wings! Mike Pound takes us through how it works. Dr Mike Pound is based at the University of Nottingham.
If a bug is found in SHA2, SHA3 is already waiting in the wings! Mike Pound takes us through how it works. Dr Mike Pound is based at the University of Nottingham.
Bringing together some of the concepts from the series on CPU, Memory & low level computer architecture, Matt Godbolt explains how an Operating System might work in conjunction with some .. show full overview
Bringing together some of the concepts from the series on CPU, Memory & low level computer architecture, Matt Godbolt explains how an Operating System might work in conjunction with some of the other concepts to provide the user with a seamless experience.
Following on from 'MikeBot3000' we're delving into just how the Generative AI systems create video. Lewis Stuart is based at the University of Nottingham.
Following on from 'MikeBot3000' we're delving into just how the Generative AI systems create video. Lewis Stuart is based at the University of Nottingham.
Is there one ring to rule them all? Kevin Tucker goes deep into the world of mathematical rings, among other things.
Is there one ring to rule them all? Kevin Tucker goes deep into the world of mathematical rings, among other things.
2025x36 Sleeper Agents in Large Language Models Episode overview
Air date
Sep 12, 2025
It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits we don't know about until it's too late.
It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits we don't know about until it's too late.
Where does it all start? How is it was say "C is written in C" - Matt Godbolt breaks it down by building it up!
Where does it all start? How is it was say "C is written in C" - Matt Godbolt breaks it down by building it up!
2025x41 Network Layers Model (Networking Basics) Episode overview
Air date
Oct 09, 2025
"The best-laid plans of mice and men often go awry" - as the ISO team were designing a beautiful, structured layered model, people were already building their own. Dr Richard G Clegg of Queen Mary University London explains the network layers model.
"The best-laid plans of mice and men often go awry" - as the ISO team were designing a beautiful, structured layered model, people were already building their own. Dr Richard G Clegg of Queen Mary University London explains the network layers model.
2025x42 How Sora2's AI Video Generator Can Clone You Episode overview
Air date
Oct 16, 2025
Amazing photo-realistic video generation is one thing, but being able to insert yourself in there, how does that work? Lewis Stuart from the University of Nottingham explains how a LoRA means you don't have a huge retraining job on your hands!
Amazing photo-realistic video generation is one thing, but being able to insert yourself in there, how does that work? Lewis Stuart from the University of Nottingham explains how a LoRA means you don't have a huge retraining job on your hands!
IP Location services almost work by accident rather than by design, Richard explains how they operate. Richard G Clegg is based at Queen Mary University of London.
IP Location services almost work by accident rather than by design, Richard explains how they operate. Richard G Clegg is based at Queen Mary University of London.
Researchers suggested there's more AI generated content appearing on the web than human generated content - Mike Pound from the University of Nottingham talks about why this might be a problem.
Researchers suggested there's more AI generated content appearing on the web than human generated content - Mike Pound from the University of Nottingham talks about why this might be a problem.
Need to get to your goal quickly? Ensure you plan the right path! Robots need to work out how to get from here to there somehow! Ayse explains some of the methods they choose. Assistant .. show full overview
Need to get to your goal quickly? Ensure you plan the right path! Robots need to work out how to get from here to there somehow! Ayse explains some of the methods they choose. Assistant Professor Ayse Kucukyilmaz is based at the University of Nottingham.
As AI systems become more capable, rule-based safeguards, hard-coded restrictions, and simple alignment strategies start to break down. Buck Shlegeris talks about some tactics we might use as detailed in a recent paper.
As AI systems become more capable, rule-based safeguards, hard-coded restrictions, and simple alignment strategies start to break down. Buck Shlegeris talks about some tactics we might use as detailed in a recent paper.
If there are missing episodes or banners (and they exist on TheTVDB) you can request an automatic full show update:
