Jonathan Blow – If AI Solved Coding, Why Is My Software Still the Same? [video]

Re:Jonathan Blow – If AI Solved Coding, Why Is My Software S... by slopinthebag on Saturday November 14, 2026 @02:54AM (#50494994)

i would expect someone who can write good code in a single pass to be more intelligent than someone who requires multiple tries.

same with anything else really. a better chef can nail a dish in one or two attempts, whereas a worse but persistent chef might take 100 attempts to achieve the same quality.

or likewise, i'm not as good as a basketball player if it takes me 100 attempts to nail a three pointer when an nba player does it 35% of the time - despite both of us eventually achieving the goal.

[ Parent | on HN ]

Re:Jonathan Blow – If AI Solved Coding, Why Is My Software S... by iainmerrick on Saturday November 14, 2026 @03:28AM (#50495186)

I’m with you on this. LLM coding agents are incredibly fast, persistent and knowledgeable, and those are all really useful. But they still make a lot of stupid decisions. Without a feedback loop they just go wild. They write tests, which is a form of feedback, but without direction they just grow vast jungles of pointless tests, while the structure of the code itself gets more and more tangled.

[ Parent | on HN ]

Re:Jonathan Blow – If AI Solved Coding, Why Is My Software S... by dwh452 on Saturday November 14, 2026 @07:32AM (#50496519)

Maybe the LLM is smarter than you give it credit for. Maybe the LLM is intellectually humble and self-aware enough to know that even a small code change can easily break something it hadn't thought of.

[ Parent | on HN ]