Factory dev: stop treating AI tech debt as a 'future model problem' — GPT-6 still can't fix it
Madisonkanna · x · 2026-11-17
Factory's Dexter Horthy pushes back on a popular mindset: since the Claude 3.5 days, developers have been treating AI-generated tech debt as something future models will solve.
- "We're at GPT-6 and we're not as close to this as we thought we might be." "People say 'that's fine, it's a GPT-7 problem' — but I'm not going to mortgage my codebase on a bet that a model that fixes debt in place arrives in six months."
- He believes models may eventually maintain codebases so well you won't need to read key parts, but we're not there yet — either keep the code together or be ready to rewrite.
- Listeners added two takeaways from the episode: prioritize understanding over speed — grasping AI's design choices lets you challenge it more effectively; and accepting AI output as-is offers no competitive edge — your taste and expertise in iterating are the moat.
More from coding & agent
- Principal Engineer Proposes Lower AI Token Budgets for Junior Engineers — Madisonkanna · 2026-11-17
- Dev recaps Factory podcast: accepting AI output as-is gives no competitive edge — Madisonkanna · 2026-11-17
- Notable AI builder says workflow has shifted to cloud agents with unlimited Claude tokens — jiayuan_jy · 2026-11-17
- Jane Street's yminsky: agents are bad at software design — but does design still matter? — charliermarsh · 2026-11-17
- Linear: by October, 53% of PRs were reviewed by an agent and the author alone — jiayuan_jy · 2026-11-17
- Five-stage agent routine that stopped an LLM deleting my repo — with the Brief prompt to steal — Iiifebri · 2026-11-17