Based on an original blog post at: https://danq.me/2025/02/28/ai-vs-the-expert/
Inspired by an 11-year old comedy sketch, I asked a GenAI to solve an unsolvable programming problem... and (for at least some models) it failed in exactly the way I anticipated: claiming to be able to solve it and delivering code that just... didn't. What does this teach us about AI trustworthiness for problems that might be solvable, but for which the human operator doesn't have sufficient comprehension to verify?
00:00 Intro
00:21 AI versus The Expert
02:45 gpt-4o's attempt
04:52 Claude 2.7 Sonnet's attempt
06:25 What's the point of all this?
08:16 Outro
