What Is RLCD? The Secret Behind Jev

WalterGR | 8 hours ago

RLCD, not defined in the article, is Reinforcement Learning for Calibrated Decisions.

borgel | 7 hours ago

Ah, so not Reflective LCD [1] then.

[1] https://www.e3displays.com/reflective-lcd-display-monitor/

[OP] tnspacetime | 7 hours ago

If you need any background info on Jev read this:

https://software.human-tokens.dev/

daemonk | 8 hours ago

Yeah the calibration is really what makes it useful in practice for quick, small decisions. Asking a LLM to give scores to a problem will yield inconsistently scaled/anchored results that changes at a whim.

The blog is pretty heavy on statistics. I'll have to study it more when I have time. Is it essentially bootstrapping results to statistically normalize the answers?

[OP] tnspacetime | 7 hours ago

I have not studied it properly too. Good that it has both code and note though.

firejake308 | 7 hours ago

> The operational signal was always relative preference. The scalar merely hid it.

Is this another Claude-ism? "X was always Y. The Z merely hid it." Or am I overcalling it?

agos | 6 hours ago

not overcalling, it’s rife with claudisms

dilyevsky | 5 hours ago

You're right to question this and OP shouldn't have done it.