Richard L Haight

Richard L Haight is the author of The Warrior's Meditation, The Bones of Christ, and The Unbound Soul.

[Richard L Haight @RichardLHaight]

Farmer’s Garden Survived a Historic Drought, Here’s How https://t.co/9X0HMzEXfj via @YouTube THIS!

[Cris33 @33_Cris_33]

How Trump MUST Counter China (or we lose everything) https://t.co/nWH03taCGR via @RichardLHaight

[Cris33 @33_Cris_33]

THE PERFECT STORM: War, Silver, and the Battle for Economic Supremacy https://t.co/Gwg1UE2F7n via @RichardLHaight

[Richard L Haight @RichardLHaight]

Trump's Biggest Allies Just Went Public — And He's Panicking https://t.co/Cv250g0vbj via @YouTube

[Richard L Haight @RichardLHaight]

@33_Cris_33 Thank you for sharing this, Criss33!

[Richard L Haight @RichardLHaight]

Watch his reaction when he’s told he’s a GOOD BOY for the first time 🥹 https://t.co/X5gVyWdHxM via @YouTube

[Richard L Haight @RichardLHaight]

Thoughts?
@janleike @sleepinyourhat @hendrycks @johnschulman2 @thinkymachines @saprmarks @OriolVinyalsML @ilyasut @paulfchristiano @elonmusk @sama

[Richard L Haight @RichardLHaight]

Stewardship Protocol: Cut p(doom) 20-30% in AI teenage phase.
Rails: 99.9% certainty pre-action.
Punish deception in loss fn.
Curling inspiration.
Survives PD/Elon.
https://t.co/Z9PGRZo63p

[Richard L Haight @RichardLHaight]

Prime: Stabilize Substrate.
Smooth is fast. No cap tax.

[Richard L Haight @RichardLHaight]

@saprmarks Sam, self-reporting evals are key—this protocol bakes it into loss fn rails (99.9% certainty pre-action, no deception). For teenage-phase testing during runs.

Docs: https://t.co/fHN7kHGXtv
@saprmarks

[Richard L Haight @RichardLHaight]

@saprmarks This would be incredible if possible!

[Richard L Haight @RichardLHaight]

@johnschulman2 John, love the blogging revival—your RLHF work inspired this doctrine's loss-fn deception punishment for teenage-phase rails. Fits scalable oversight evals.

Docs: https://t.co/uhrFuhqUPA
@johnschulman2

[Richard L Haight @RichardLHaight]

@hendrycks Dan, been enjoying your take—mechanistic interp is a rabbit hole. This protocol bets on scalable rails instead: 99.9% action certainty + deception-punished loss fn for teenage-phase evals.

Docs: https://t.co/uhrFuhqUPA
@hendrycks

[Richard L Haight @RichardLHaight]

@demishassabis @GeminiApp Demis, Gemini 3's parallel thinking helped me forge this stewardship protocol for safe teenage-phase AI—99.9% action rails + deception-punished loss fn. Survives PD/objections.

Docs: https://t.co/uhrFuhqUPA
@demishassabis

[Richard L Haight @RichardLHaight]

@demishassabis @GeminiApp Incredible AI!

[Richard L Haight @RichardLHaight]

@janleike Jan, this doctrine was built for exactly that post-training leeway—99.9% action rails + deception punished in the loss fn, trained as doctrine not prompt. Survives the usual objections.

Docs: https://t.co/uhrFuhqUPA
@janleike

[Richard L Haight @RichardLHaight]

@KalkinTrivedi @elonmusk Keep me posted, Kalkin. We live out in the countryside, produce our own power. It's nice to be away from the city.

[Richard L Haight @RichardLHaight]

@KalkinTrivedi @elonmusk Yes, as I live on country roads, I will wait.

[Richard L Haight @RichardLHaight]

@KalkinTrivedi @elonmusk It can follow tire tracks? That is impressive, but I would think that might be more challenging at night. Still, quite astonishing.

[Richard L Haight @RichardLHaight]

@sleepinyourhat @sprice354_ @MinaeKwon Sam, this protocol builds on your team's reward hacking work—rails for teenage-phase evals: https://t.co/uhrFuhqUPA

@MinaeKwon
@sleepinyourhat