This post was submitted by a SAIRC member either as a recommended read or student-created post. All credit remains with the original author.
A bimonthly roundup tracking the intersection of formal verification and AI security, noting that major AGI labs are now actively hiring formal methods talent. This issue covers a new minimal position paper on which AI security problems are actually tractable, hiring updates at Anthropic and OpenAI, and Gwern's recent work applying scaling laws to software engineering.