TypeSafe founder podcast: why Jev couldn't be built inside OpenAI
In a two-hour podcast, Jev's creator describes a decision stack of choice, score, noul, a confidence gate and authorizing code, and explains why he wouldn't bet on pre-training.
TypeSafe founder (ex-OpenAI): "The thing I've said before is that if you gave me a billion dollars, I wouldn't pre-train. I still believe that to be true. If the whole company of TypeSafe disappears, maybe it'll take a year or two for people quality matters, we're going to be in a very goo position for a long time." in a 2-hour podcast, the man who built Jev explains why he couldn't build it inside OpenAI choice + score + noul + a confidence gate + code that authorizes - that's the entire stack worth more than any $500 agent engineering course on the internet watch today, then read how to wire that decision layer into a loop that runs itself in the article below
This post quotes another post: x.com/0xricker/status/2102396090012115030