computerphile

Dr Mike Pound of Computerphile shows how a modern laptop can crack Enigma, using a ciphertext-only attack based on an older paper. He compares it with the tooling in CrypTool.

Rob Miles explains on Computerphile how language models generate plausible text and how transformers improved on recurrent networks, with a look at what comes next.

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.

Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.

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.