Viewing profile — bonjourjoel

LLMs are leaning toward Corporate first order. They will judge anything based on how much corporation would like it said. I call this "corporate RLHF" and they are ALL into it. The…

Agreed. But also this inequality: "Is this the end of human code review?" != "the end of human code review" Now since the problem in this study is more complex than 90 to 99.5% of …

Requirements as product owner are not covered at all by AI, 100% agree. But in this programming-only example study, the refactor changes the functionnality very seriously, and it h…

How? The agent does something incredibly difficult, and there is no human code review. Why do you think it doesn't match ?

In the following case study, the AI coding agent rebuilds a core system invariant in just three days, with minimal human input, running 31 verification passes and correcting 201 er…

Agreed, LOC is not a quality metric. Fair point. The real claim is zero regression over 7 months as the codebase grew from 0 to 500k lines, solo. I believe I'm the only person to b…

Here is the proof, a 5-hour uncut live session, no edits, no cuts: https://youtu.be/VPrU8WZJOVs Full article: https://medium.com/@bonjourjoel/i-built-a-500-000-line-produ... I beli…

Okay thanks for the feedback. I've re-written my readme description and made it shorter. I hope my method is more clear now. I added a 1mn video to explain without all this blah bl…

I built a review-first AI copilot for VS Code that enforces structured specs and lets you review every patch before it touches your repo. Demo (1 min): https://youtu.be/E7XcQx2j6Do…

I built AICode, a VSCode extension and methodology for writing AI-generated code that remains maintainable in large projects. It started as a manual workflow on ChatGPT.com: assemb…