postpriorx

That's per inference compute right? Or does it also include training compute?

For teams its very helpful too, as you entire team standardizes around a common set of artifact for planning and executing work (with explicit semantics). Avoids snowflake agent sessions and artifacts for planning, proposing and executing work.

The project evolution tracking argument does apply here, but another benefit is provides a standardized structure for planning and executing work that you can build your agentic code flows/loops around.

How does a poker solver select bet size? Doesn't this depend on posteriors on the opponent's 'policy' + hand estimation?

I was a transfer to UCSD - the transfer community itself is pretty large and one college (Sixth) houses a significant percentage, with dorms specifically for transfers. IMO there was far higher interesting diversity of folks there compared to rest of campus: veterans, addicts who got their shit together, tons of immigrants who couldn't afford going straight to UC (as well as your standard mostly 20-22 year old SoCal transfers) from which most people I know formed good networks.