Hacker News Reader

As an avid observer of rocket design, I suppose that hasn't happened because SSTO may not have any good solutions. I further suppose that the design parameters are so constrained there is very little opportunity for a generative or evolutionary, or any other AI-driven design approach, to do more than optimize some components.

SpaceX's solution with Starship definitely demonstrates how difficult a problem it is. Raptor are the best engines humanity has, all the landing hardware is part of the launch tower to save weight, and those seem to be table stakes. Stoke aerospace has a fantastically genius solution with their regeneratively cooled heatshield / expander cycle aerospike engine. It literally turns the energy you're trying to burn off during re-entry into delta-v in the opposing direction while reducing weight and complexity.

As a rocket scientist I assure you it's been tried