factual

Coding agents fail on novel, non-boilerplate code

Coding agents are good at boilerplate and code common on the internet, but they fail on unique, intellectually intense code: they over-rely on memorized common patterns, bloat code with defensive try-catch and production scaffolding, use deprecated APIs, and can't internalize custom non-standard implementations—so for novel work autocomplete is the sweet spot rather than full agents.

factualpending

Speaker

Andrej Karpathy

Evidence Quote

“They have too much memory from all the typical ways of doing things on the Internet that I just wasn't adopting.”

Source

Andrej Karpathy — AGI is still a decade away— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:26:44 AM

Your notes

Loading notes...