))
The Search Gap: Teaching AI to Create Counterintuitive Chess Puzzles
Manage episode 516812695 series 3690682
المحتوى المقدم من Mike Breault. يتم تحميل جميع محتويات البودكاست بما في ذلك الحلقات والرسومات وأوصاف البودكاست وتقديمها مباشرة بواسطة Mike Breault أو شريك منصة البودكاست الخاص بهم. إذا كنت تعتقد أن شخصًا ما يستخدم عملك المحمي بحقوق الطبع والنشر دون إذنك، فيمكنك اتباع العملية الموضحة هنا https://ar.player.fm/legal.
We unpack a DeepMind study on training an AI to generate genuinely creative chess puzzles, using reinforcement learning and a three-part creativity framework: uniqueness, novelty, and counterintuitiveness via a 'search gap' between shallow and deep engine evaluations. Stockfish ensures a unique solution; Levenshtein distance enforces novelty in both the puzzle and the solution; and a diversity filter guards against reward hacking. Results showed a tenfold rise in counterintuitive puzzles (0.22% baseline to 2.5%), surpassing human puzzle rates in a large dataset. Expert reviewers found the AI puzzles more creative and enjoyable. We discuss broader implications: a general blueprint for nurturing AI creativity in domains like Go, mathematics, and even prompting large language models, turning shallow intuition into deeper, surprising insight.
…
continue reading
Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.
Sponsored by Embersilk LLC
1476 حلقات
مشاركة
