After Interviewing 50 Developers, the Top 8 Mistakes in AI-Assisted Coding
dfinke · x · 2026-09-24
The author of atmoio interviewed 50+ developers 1:1 to understand how they code with AI — and found it's "an absolute mess." The top 8 mistakes, timestamped in the video:
- Talking to 2026 models like they're 2025 models
- Devising funky metaphorical factories to orchestrate agents
- Treating context as sacred
- Treating previous conversations as sacred
- Having a todo list
- Using funky tools
- Stressing over code quality
- Using branches and worktrees
The core thesis: most developers' mental models of AI coding lag far behind current model capabilities, and many inherited workflows are now dead weight.
More from coding & agent
- 30 annotations with GEPA prompt optimization boost lead scorer accuracy 43%, cut cost 5x — CShorten30 · 2026-09-24
- Matt Shumer shares a prompting trick: ask the model 'how would Matt Shumer write this prompt?' — mattshumer_ · 2026-09-24
- AI agent platform Wayfinder consumes 25.68B tokens and counting, adds Robinhood chain — templecrash · 2026-09-24
- pr-ui-compare: Open-source tool generates before/after UI comparison GIFs from a prompt — bezdazen · 2026-09-24
- pr-ui-compare generates UI before/after comparison GIFs for GitHub PRs — bezdazen · 2026-09-24
- Instinct's agent-to-agent network logs 300k+ collaborations in a week, adds file delivery — mon__lim · 2026-09-24