https://jimbowery.blogspot.com/2025/02/artificial-intelligence-in-nutshell.html
On Wed, Oct 29, 2025 at 4:24 PM Basile Starynkevitch < [email protected]> wrote: > On Wed, 2025-10-29 at 16:21 -0500, James Bowery wrote: > > > > > > On Wed, Oct 29, 2025 at 4:02 PM Matt Mahoney <[email protected]> > wrote: > > > ... > > > > > > I prefer simpler programs, but as Legg proved, good predictors are > necessarily complex. His proof goes something like this: suppose you have a > simple but powerful prediction algorithm. Then I can create a simple > sequence that your program can't predict. My program runs a copy of your > program and outputs the opposite of yours.... > > > > > > Oh, well I should have suspected that Legg would already have made the > case for losslessly compressing Wikipedia as an ideal benchmark for > Forensic Epistemology! :) > > What is then the definition of AI you have in mind? > > Thanks > -- > > Basile STARYNKEVITCH <[email protected]> > 8 rue de la Faïencerie > http://starynkevitch.net/Basile/ > 92340 Bourg-la-Reine https://github.com/bstarynk > France > https://github.com/RefPerSys/RefPerSys > https://orcid.org/0000-0003-0908-5250 ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T6cf3be509c7cd2f2-M3c9304625aa64e6c13d32687 Delivery options: https://agi.topicbox.com/groups/agi/subscription
