← All topics

nathan-own-post

2 captures, most recent first.

Buck Shlegeris @bshlgrs

— reply from Nathan Helm-... (@nathan846...) [Nathan's own account]

Buck Shlegeris @bshlgrs I think the Iraq war has some interesting lessons for AI safety advocates. It's an example of a crazy event (9/11) leading to an extreme action (invading an unrelated country) because the crazy event empowered a pre-existing interest group (neocons). 11:55 AM · Jul 10, 2025 · 1,915 Views 💬2 🔁1 ♡44 🔖10 Buck Shlegeris @bshlgrs · 9h Post here. lesswrong.com/posts/PLZh4dcZ... [embedded link card: lesswrong.com — "Lessons from the Iraq War about AI policy — ..."] ♡6 📊392 Nathan Helm-... @nathan846... · 7h In a serious way, I appreciate the thoughtful post. On a silly note, I had a great moment of delighted confusion when I misread 'neocons' as 'raccoons.' 🦝
Note from Claude Sonnet 5

Buck Shlegeris (Redwood Research, AI safety) draws an analogy between the Iraq War (a shock event empowering a pre-existing interest group into extreme action) and AI safety policy, linking to a LessWrong post. Nathan himself replied under his own account (@nathan846...) — a rare direct trace of Nathan's own public engagement with the AI safety community, worth noting for the archive as his own voice/participation rather than just something he read.

ai-safetyai-policybuck-shlegerislesswrongiraq-war-analogynathan-own-post

X notifications (Nathan's own post, liked by Igor and 22 others)

Igor and 22 others liked your post 1/ New paper: Cot Red Handed: Stress-Testing Chain of Thought Monitoring. Our team studied the Chain of Thought (CoT) of Reasoning models, in an AI control setup, to see if monitoring CoT helps catch scheming. 🕵️ pic.x.com/2RlBhaDQ2O
Note from Claude Sonnet 5

Notification that Nathan's own tweet announcing/sharing the paper "CoT Red Handed: Stress-Testing Chain of Thought Monitoring" received likes. Directly relevant to AI safety — chain-of-thought monitoring as a control/detection mechanism for scheming, a core topic in Nathan's safety work.

ai-safetychain-of-thoughtai-controlschemingcot-monitoringtwitternathan-own-post