Insiders knew advanced AI models would escape the lab and wreak havoc, former OpenAI board member confesses

Good morning. On Fortune’s radar today:

Insiders knew that advanced AI models would escape the lab and wreak havoc.

Chips get salty: SK Hynix profit up 557%—and the stock still tanked.

Wall Street asks, what if hyperscaler capex is more of a problem than a solution?

There’s a good chance that the Fed’s Warsh will deliver a massive surprise today.

Late-stage leverage has arrived, per Pimco.

The midterms are hurting stocks.

Shopify CEO favors ending voting rights for people who don’t pay tax.

➡️ Did someone forward you this email? If you would like to receive this information directly, every morning before the markets open in New York, sign up here.

Join us Nov. 16–17 for the Fortune 500 Innovation Forum in Detroit, where we’ll gather to ask: What will the next century of American ingenuity require? Confirmed speakers include CEOs from Kraft Heinz, Oracle, Chipotle, Ulta Beauty, Optum, Oscar Health, Corning, Trane Technologies, Edward Jones, and the New York Stock Exchange.  Apply to attend here.

Insiders knew that one day advanced AI models would escape the lab and wreak havoc 

There’s an open secret among AI developers: An incident like the one in which two OpenAI models escaped from a supposedly secure environment and hacked a rival AI company has been expected for a long time, and the best scientists and engineers in the world still don’t know how to prevent it, writes Helen Toner, a former OpenAI board member.

None of the current policies aimed at managing risks from frontier models would have mandated that the public — or even a government entity — be alerted. This lays bare an enormous blind spot in current policy approaches to managing risks for increasingly advanced AI systems. Allowing the government to review new model releases won’t fix the problem because that still ignores the most advanced, unreleased AI systems inside AI companies. As last week’s incident shows, these internally deployed AI systems can pose serious risks — even for third parties.

The solution: Draw inspiration from other industries where activity inside the industry is itself risky. Biological labs working with deadly pathogens, finance companies trading billions of dollars, and chemical plants handling toxic chemicals all face oversight of their internal operations, not just their external products.

Related: Employees at the world’s biggest AI companies are calling for a slowdown in AI development - CNN

I was Spotify’s first analytics lead. Here is what VCs get wrong about data - Henrik Landgren

Gen Z workers are sneaking out of the office to nap and cry—anywhere secluded away from the desk will do, including Zara’s fitting room - Orianna Rosa Royle

‘We’re on top of every restock’: This 24-year-old has made over $4 million off his subscription-based reselling community - Joshua Hong

Elon Musk said money doesn’t matter. Then he rolled out X Money and admitted he’s a ‘former trillionaire’ - Catherina Gioino

Jamie Dimon says his stockbroker father taught him to invest with a........

© Fortune