Peter Yang highlights ultra-light specs on OpenAI’s Codex team, Lenny Rachitsky shares the “dark factory” pattern, and Harrison Chase breaks continual learning into model, harness, and context layers for agents.
“We write very few specs on the Codex team. We're talking 10 bullet points and that's it.”
“the "dark factory" pattern”
“teams don't write any code or even look at their code.”
“with agents - there's actually three different levels you could "learn" at:”
“- model - harness - context”
This finding is one of many signals tracked across Indiehacking. The live feed updates every few hours with new authority voices, debates, and emerging ideas.
← Back to Indiehacking