Frequently Asked Questions
Q: What is Njx’Log?
A: A public notebook for the things I am building and thinking through: AI products, evals, agentic RL, multimodal systems, and the engineering details that usually hide behind demos.
Q: What kind of posts will appear here?
A: Mostly field notes. Some are build logs, some are experiment reports, some are product reflections. I prefer concrete traces: what changed, what broke, what the metric said, and what I still do not know.
Q: What will you not write here?
A: I try not to write generic AI commentary. If a post has no code, no product scar, no eval detail, or no honest uncertainty, it probably belongs somewhere else.
Q: Can I cite, translate, or share a post?
A: Yes. Keep a link to the original post, and feel free to tell me where it traveled. I like seeing notes find another desk.
Q: Are you open to collaboration or conversation?
A: Yes, especially around AI products, eval infrastructure, agent workflows, multimodal applications, and strange little tools that make research easier to use.
Q: How can I reach you?
A: The cleanest paths are GitHub, Hugging Face, or Twitter / X.