And have you tried connecting GPT-2 to arithmetic coding to see if it can compress the dataset it trained on well? If it predicts so well, we can see its effect, even though it's breaking the rules of the Hutter Prize. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T2a0cd9d392f9ff94-Mae317d2540b01c7ec7ce90c2 Delivery options: https://agi.topicbox.com/groups/agi/subscription
- Re: [agi] The limitations of th... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... stefan.reich.maker.of.eye via AGI
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... Matt Mahoney
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... immortal . discoveries
- Re: [agi] The limitations o... James Bowery
- Re: [agi] The limitations of the validit... TimTyler
- Re: [agi] The limitations of the va... James Bowery