Viewing profile — eugene-kim

will check this out. thank you!

Agentic coding loops work well when the LLM can run tests to verify its work. For backend code, this is straightforward - write a test, run it, iterate. For front-end work, I haven…

Lots of commenters are simply calling this a VSCode fork and I think they're missing something important as far as how this product fits into the market. Anthropic and OpenAI are i…

When using codex-cli / Claude Code, I look for opportunities to improve either the AGENTS.md file based on the path that the LLM is taking or to improve repo structure, docs, var n…