š£ EV Daily: AI's inner monologue goes public
Five things to know today + highlights from my conversations
Lead story: š§ AIās inner monologue goes public
Researchers from OpenAI, DeepMind and Anthropic, plus a slew of other AI bigwigs including Geoffrey Hinton and Safe Superintelligence CEO Ilya Sutskever, have published a paper-cum-open letter arguing that every step of an AIās internal reasoningāits chain of thought (CoT)ābe captured and made auditable. The signatories argue āglass boxā CoT logs should be not a nice-to-have but a requirement to operate safely. Research shows that a smaller AI model can effectively monitor a more powerful modelās chain-of-thought. However, powerful models may still learn to obscure their reasoning, so this approach doesnāt settle the AI safety debate.
Nevertheless, the safety argument makes sense: researcherās get valuable data, enterprises gain error forensics and regulators get a breadcrumb trail for safety checks. [Tomek Korbak, arXiv]
Key signals, quick scan
A 30-second scan of four secondary signals that hā¦
Keep reading with a 7-day free trial
Subscribe to Exponential View to keep reading this post and get 7 days of free access to the full post archives.