Mike Knoop
speaker
927 appearances
4 recordings
1 series
first heard Mar 2025
last heard 18 Nov
Mike Knoop’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Nov 2025 with 1.
Appearances
So now green score.
uh you know, you guys have probably h like uh for for for a long time actually, I think games were considered to solve problem in AI.
You know, with AlphaGo and all the chess games and
Yeah.
Most of them use RL and so they're trying to take reward signal and understand you know what actions I took to produce the reward signal.
This is one of the things that efficiency helps with is it limits the ability for an agent to just naively be able to go ex gather a reward signal by spamming and playing the games hundreds of thousands of times.
This is something humans don't need to do, right?
You know, you already beat level two uh in what less than five minutes here with a very limited number of efficient, you know, actions that you took.
Um and this is something we don't see for
from the frontier like LM Stay or our other agents we've been testing.
the next level we we started introducing some new concepts here.
noticed, just start scaffolding new uh new things you have to learn, right?
Yeah.
It's not just learn one rule in level one and apply it for the entire game, but we found a really an element
Uh, one design goal is that all the games are fun.
Yes.
And one of the things we found when we're doing early design game design was that um folks did not find the games fun if they just took one rule they learned and did that just repeated it.
Right.
So introducing new things you have to continually learn throughout the game is a big function of uh whether humans can find these things actually entertaining and fun.
You know, my my sort of view generally on ASCFT stuff is em you want to be empirical about it.
Showing 381–400 of 927 · page 20 of 47
← Previous
Next →