I don't agree that it's possible to output this much code with an LLM and also be sure that you know the codebase. Chances are very close to 100% that the entire stack is vibe coded and you rely on LLMs to fix bugs too
Didn't Anthropic say Claude Cowork was completely written by Claude Code and hence "vibe-coded"?
All that matters is that the deliverable agent works seamlessly without bugs/issues, which our web agent excels at even beating OpenAI Operator and Anthropic CUA in benchmarks!
arjunchint|14 days ago
All that matters is that the deliverable agent works seamlessly without bugs/issues, which our web agent excels at even beating OpenAI Operator and Anthropic CUA in benchmarks!