“Language models don’t apply to us because this is not a language problem,” Nesterenko explained. “If you ask it to actually create a blueprint, it has no training data for that. It has no context for that…” Instead, Quilter built what Nesterenko describes as a “game” where the AI agent makes sequential decisions — place this component here, route this trace there — and receives feedback based on whether the resulting design satisfies electromagnetic, thermal, and manufacturing constraints… The approach mirrors DeepMind’s progression with its Go-playing systems.
This is kind of interesting and cool, and it’s not a hallucinating LLM. I’ve designed a couple of simple circuit boards, and running traces can be sort of zen, but it is tedious and would be maddening as a job, so I can only imagine what the process must be like on complex projects from scratch. Definitely some hype levels coming from the company that give me pause, but it seems like an actual useful task for a machine learning algorithm.
Valerian. Recast both leads if you can, but in a pinch just DeHaan. Give Valerian himself a single iota of charisma and the movie ends up a slight but interesting lark instead of a slog.
There’s a line I’ve heard a couple times that if you swapped the pairs from Valerian and Passengers, both movies end up better, if maybe not quite “good.”