🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Want to get into alignment research? Alex Cloud & I mentor *Team Shard*, responsible for gradient routing, steering vectors, MELBO, and a new unlearning technique (TBA) :) We discover new research subfields. Apply for mentorship this summer at forms.matsprogram.org/turner-app-8

Just released GDM’s 100+ page approach to AGI safety & security! (Don’t worry, there’s a 10 page summary.) AGI will be transformative. It enables massive benefits, but could also pose risks. Responsible development means proactively preparing for severe harms before they arise.

Just realized that Simulators doesn't explain the "emergent misalignment" result, since IIRC they found that simply k-shot prompting the model doesn't elicit evil outputs. If finetuning on insecure code drew out an "evil" persona, then so should k-shot prompting.