When you type a question into a chatbot, you might wonder how it arrives at the answer—and it turns out, so do those who built AI.

A host of “interpretability” startups are trying to figure out the inner workings of models in order to make them safer and curb their tendency to hallucinate. The $1.25 billion-valued AI research lab Goodfire has made a recent breakthrough: AI models use shapes to represent concepts, also referred to as “neural geometry.”

Any fix must nudge the model based on the shapes it prefers. “If you don’t respect this kind of geometry … it generally just makes it dumber,” says Goodfire cofounder Tom McGrath.

This is a published version of the Forbes Daily newsletter, you can sign-up to get Forbes Daily in your inbox here.

Long-term Treasury yields reached their highest level since 2007 on Tuesday, pulling down the broader stock market, as some analysts say an even steeper bond selloff could be on the horizon.

Rep. Thomas Massie, R-Ky., a vocal critic of President Donald Trump, lost his primary Tuesday, the latest symbol of Trump’s influence over his party after Sen. Bill Cassidy, R-La., was defeated by a Trump-backed challenger on Saturday.

Wealth Entrepreneurship

Money manager Graeme Forster looks after $7.5 billion at Orbis Investments, but his collection of 65 stocks is nothing like an index fund. Instead, he invests in reasonably priced companies that could win big on an unlikely event, like a revival of movie theaters, which would boost his bet on movie theater chain Cinemark.

Andrej Karpathy, one of the most influential figures in modern AI, announced Tuesday that he joined........

© Forbes