Another tangent: I feel this speaks to the hazard on building on these generative AI APIs. Your product may work great on Day 1, but there’s no way to guarantee it’ll still work as well on Day 500. Either due the models being nerfed, or due to the models becoming stale over time.
This is extremely interesting, in the light of YC providing early access for AI startups (with one of the big benefits being OpenAI credits). YCombinator explicitly used to advise against building platforms and startups over somebody else's tooling for reasons like these, yet it seems that they are past that advice now and back on the hype train.
