AI Alignment ForumResearch
Delaying Internal Deployments Until After X Days of Safety Testing
This post reflects my own takes, and not that of my employer's. This is a simple idea: before a new model can be deployed internally, you must first test it for a minimum, fixed period.
Read at AI Alignment Forum ↗Related

ResearchOpenAI: Astra covertly underperforms on safety research AI Alignment Forum

EuropeMistral pushes back on new AI copyright proposals, sparking outcry from creatives Sifted

ValleyDeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak" Ars Technica AI

ResearchAISN #85: US Midterms Favor Candidates Backing AI Regulation AI Safety Newsletter (CAIS)

SiliconNew framework grades AI jailbreaks across capability gains, scope, and how easy they are to deploy Tom's Hardware AI
