Planning

“I think it is the complete opposite. I think the potential is even higher.”

“Planning, planning when the world is stable, there's a really good ROI. When the world is unstable, put all your planning time into building better product faster.”

“The transformer moment for reasoning and choosing action and being able to plan at different levels of granularity. We're still far away from doing that.”

“If you invest the time in the planning stage, I hundred percent believe you'll save a lot more money, and this will help you clear up a lot of ideas.”

“Understanding like what amount of research and planning is helpful and at what point you need action because action produces information.”

“The US Forest Service, I saw a stat, they spend 40% of their budget, which is about two hundred fifty million dollars a year on planning, right?”

“The LLMs are not good at planning, right? They're good at predicting the next step. And as part of that, you can't rely on LLMs to do the end-to-end Processing yet.”

“Sometimes I say that like the LLMs aren't [4137] Great at planning yet. [4138] So we can help them plan by telling them how to plan and code. [4140] Cause that's very explicit and that's a good way of communicating how they should plan and stuff like that.”

“Because accuracy has cost, make sure that you're only increasing the accuracy of planning for the things that have high value of that accuracy.”