moosehater

I was thinking the same thing in terms of running out of data a few months ago. But aren't most gains in the past year+ due to reinforcement learning in some form? Which doesn't need "fresh data" per se, as the model effectively creates the data as it goes. As long as engineers can come up with proper environments, tasks/goals, rewards, and actions, I don't really see data being a limit to model improvement in an agentic sense. Maybe as a knowledge base

What made you use Clojure for business logic and DBs rather than using Elixir for everything? The JVM ecosystem?

Yup, this is essentially what the original concept of the Jungle genre was built around. Chop up the Amen Break, mix the notes(?) around, repeat them as you see fit, and add other samples/vocals around the drum patterns you've created.

A couple favorites from the 90s:

https://youtu.be/mL2Bgj-za5k?si=fhXHhNGjA-RZkiD7

https://youtu.be/a5meT63flnM?si=ggvypNCFfUUq3Qxq

Got it. This all makes sense to me. Very targeted tooling that is specific to your company's CI platform as opposed to a dark factory where you're creating a bunch of new code no one reads. And it sounds like these level 8 agents are given specific permission for everything they're allowed to do ahead of time. That seems sound from an engineering perspective.

Also would be interested in an example of "validation layers that trim hallucinations with handwritten linters" but understand if that's not something you can share. Either way, thanks for responding!

Do you feel like you are still learning about the programming language(s) and other technologies you are using? Or do you feel like you are already a master at them?

Do you ever take the time to validate what one of the agents produces by going to the docs? Or is all debugging/changing of the code done via LLMs/agents?

I'm more like level 2 right now and genuinely curious if you feel like learning continues for you (besides with agentic orchestration, etc.) And if not, whether or not you think that matters.