All episodes / EP.01
AI vs. Humans: Who Should Control the Code?
· 33 min Watch on YouTube
When a coding agent changes login while fixing padding, who catches it? Oksana and Konstantin discuss scope, human oversight and accountability for generated code.
Episode chapters
- 00:00Meet Oksana & Kostya
- 00:31Good code vs a product that works
- 05:12AI mistakes: data leaks & broken systems
- 06:25Human oversight still matters
- 09:51Why local AI feels disappointing
- 12:32Context, instructions & wrong expectations
- 17:02Asked for padding—AI hacked the login
- 17:42Who pays for AI mistakes?
- 23:15"Legacy" code written five minutes ago
- 26:43Are engineers becoming managers?
- 31:16She thought GitHub was angry
- 32:35Final thoughts & subscribe
Read next
- Software engineering ·
A code review checklist for AI-generated changes
Review an AI-generated patch for changes outside its scope, verify tests against the original bug, and decide who owns the merge.