Verifying Ai Black Boxes Computerphile
Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains ... Amazing photo-realistic video generation is one thing, but being able to insert yourself in there, how does that work? Lewis Stuart ... How do we measure harm to improve the performance of The original version of text messaging had a flaw, but how can we investigate problems with software quickly and easily? Could a computer program find Fermat's Lost Theorem? Professor Altenkirch shows us how to get started with lean. EXTRA BITS ... We haven't got time to label things, so can we let the computers work it out for themselves? Professor Uwe Aickelin explains ...
The so-called 'Forbidden Technique' with Chana Messinger -- How do you go about making a device recognise individual sounds? Audio Analytic's Dr Chris Mitchell on how they approached ...
![[AI] 20. Black Box Algorithms (6:04)](https://i0.wp.com/i.ytimg.com/vi/glGwkpPEbD4/mqdefault.jpg?resize=320,180)