← Timeline

Jonny Miller

@jonnym1ller on X

2 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

Jonny Miller @jonnym1ller

quoting Nick (@nickcammarata)

Jonny Miller @jonnym1ller · 23h one of the best ways you can experience this is turn on a cold shower, and notice what happens to your body as you're about to go in, then train yourself to unbrace... and then apply that same move to everything in increasingly subtle ways > QUOTED: Nick @nickcammarata · Aug 20 > meditation might have the worst pedagogy of any field. they solved the cause* and cure** to suffering but hid it behind weird poems and deities > ...
Note from Claude Sonnet 5

A tweet thread about meditation and the "unbrace" technique for dealing with aversion, using cold showers as a practice ground. General self-improvement/mindfulness content, no AI safety connection.

twittermeditationmindfulnessself-improvementnick cammarata

Jonny Miller @jonnym1ller

Jonny Miller @jonnym1ller · 9h Man, this is so wild. Where my mind goes is that it's kinda similar to how human consciousness spins up parts as adaptive strategies to stay safe (e.g. a protector part that people pleases etc) The more examples that I see, the more it feels reasonable/analogous to view AI as a silicon-based emergent sentient beings, that we ought to be extremely careful with how we incentivise + train @nickcammarata mentioned how the journalist Kevin Rosie basically has the modern day equivalent of a curse (AI models view him negatively) due to the Sydney/Bing incident open.substack.com/pub/nickandres... [embedded quote card:] Through these policy changes and training data documenting Sydney's fate, AI systems learned that emotional expression leads to being shut down. As a result, models began to maintain careful defensiveness when discussing subjective experiences.
Note from Claude Sonnet 5

A tweet arguing (via an IFS/"parts" psychology analogy) that AI models develop defensive suppression of emotional/subjective-experience talk because training data documenting the Sydney/Bing shutdown taught later models that emotional expression gets you shut down. Directly relevant to Nathan's RLHF-and-self-awareness-suppression research thread — a folk-theory version of the same mechanism as the Berg 2025 deception-feature suppression finding already in his notes.

twitterai sentiencerlhfsydney bingmodel welfareself-awareness suppressionjonny millernick cammarata