🟣 EV Daily: AI's inner monologue goes public
This is EV Daily – built for those who can’t afford to miss the signal. 🟣 EV Daily: AI's inner monologue goes publicFive things to know today + highlights from my conversationsLead story: 🧠 AI’s inner monologue goes publicResearchers 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 AI’s internal reasoning—its chain of thought (CoT)—be captured and made auditable. The signatories argue “glass box” 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 model’s chain-of-thought. However, powerful models may still learn to obscure their reasoning, so this approach doesn’t settle the AI safety debate. Nevertheless, the safety argument makes sense: researcher’s get valuable data, enterprises gain error forensics and regulators get a breadcrumb trail for safety checks. [Tomek Korbak, arXiv] Key signals, quick scanA 30-second scan of four secondary signals that hint at where the curve is bending.
Highlights from my conversations: Frontier or perishKevin Weil, CPO of OpenAI, shared with me Sam Altman’s test for startups building today:
Watch the full episode on YouTube. I go live on Substack every Friday at 5 pm UK time | 12 pm Eastern | 9 am Pacific. |
Similar newsletters
There are other similar shared emails that you might be interested in: