Slopfix — we refactor vibecoded codebases
Your AI-built product works, but past 100,000 lines every change breaks two things. Three senior engineers make your codebase maintainable again. One week, fixed price, guaranteed.
We posted on Hacker News and made it into the frontpage. It caused a lot of great feedback. Thank you everyone! Did that happen to you? You have an AI-generated codebase that works, but adding a feature now takes days and breaks two other things? This happens to every vibecoded project past a certain size: the agent stops seeing the whole picture and starts duplicating code instead of finding it. We can help. What we do? We analyze your codebase for free. If we don't think we can help, we say so and you've lost nothing. If we can, you get a fixed price and a committed reduction target —…
saved by
related reading
- Coding Models Are Doing Too Much | whnrehiew.github.io
- claude code is not making your product betterethanding.substack.com
- AI is removing the middle class of software engineeringblog.florianherrengt.com
- How To De-Slop A Codebase Ruined By AI (with one skill)youtube.com
- Killing Coding Agent Slop With Adversarial Self-Playusetelos.ai
- If coding is solved, what now?: Measuring the sloppiness of code | EARENDILearendil.com
- Thoughts on slowing the fuck downmariozechner.at
- How Claude Code is built - by Gergely Orosznewsletter.pragmaticengineer.com
- Vibe engineeringsimonwillison.net
- Why We Built Our Own Background Agentbuilders.ramp.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Become a Real AI Heroaihero.dev