so you can play WoW and prompt now w/ Hermes HUD mode
it's a seamless overlay where you can keep an eye on things or ask questions about a game during your session.
@NousResearch
@iBDWSSBM That photo doesn’t do you justice, you have very good fundamentals for looks. Barber/stylist haircut + crest white strips + GLP1 to thin out the face would catapult you into chad territory.
I think I finally figured out how to use AI at scale
of course, the fact Fable is good is part of it. but I also changed how I work, and it all comes down to one key realization: you don't need to audit the code, but you NEED to audit the *choices* it made. if you just do that, things will work out, and you'll never lose a codebase to chaos. with Fable at least, the following seems to hold:
if I give it a good decision:
Fable implements it PERFECTLY
if I let it decide instead:
Fable may make some bad choices
that's how I see Fable: as a perfect execution machine capable of converting good decisions into good codebases, no matter how large. given a concrete plan, it lands its implementation. but when anything is underspecified, it can, and will, make bad choices. that's what you must audit.
"while working on this, which choices did you make that you're not confident of? list all."
then, you just review that. not the git diff, not 1000's of lines of code. just the choices it made along the way.
below is a fresh example. overnight, I asked Fable to fix an issue related to MatMul parallelizing worse than expected. it tracked the culprit with perfection, and landed a solution that DID work. but the solution was not general. it just doubled a buffer, which coincidently fixed the program at hands, but the underlying issue was still present.
when it completed the job, it declared success. if I just merged it blindly, the issue would still be dormant. that's the main mistake one can do with AI. instead, I asked it to spell out all decisions it made, spotted the bad one, corrected its course, and now the codebase is clean, correct and the issue is gone for good
I really think that if you do that religiously - i.e., NEVER merge without this "which decisions you made?" audit - you can go VERY far without ever reading a single line of code. at least on Bend, this is working incredibly well. despite heavy use of AI to implement an ungodly amount of features I could never dream of, the codebase is still in a superb state, with no signs of degradation
fresh example below ↓
@AnalyticsGenius@thdxr He didn’t say it outright; it was insinuated. Put differently, he asked “if you are spending tens of billions of tokens, what is your ROI?”
@orenmeetsworld Good idea if you have a family or two you’re super tight with. Parents and all kids better get along super well. Otherwise, just get a luxury cruise.
@WarcraftYax Yeah AWS will just give you random 24 year old “managers” until you start spending real money with them to earn a senior person. Super annoying in my exp, having gone thru about a dozen over my career
Today Erin Catto announced the release of Box3D, an open source 3D physics engine. We're proud to be one of the first games running on it. Congrats, @erin_catto !
Read Erin's full announcement and grab the source: https://t.co/BNVcWScDbD