Oaktree founder Howard Marks asked Claude to explain AI

Back in December he wrote about “AI Bubble” fears. 

Significant changes since then made him feel obligated to write a follow-up piece. (Which is one of the things I admire about Howard. He never stops learning.)

Working with the latest versions is a bit like exchanging text messages with what may increasingly become a good friend. But this friend is a world-class expert on everything, with a remarkable ability to explain it in exactly the terms you need.

Claude - here’s what it said:

“Howard, everything you know about investing came from other people. Benjamin Graham taught you about margin of safety. Buffett taught you about quality. Charlie Munger taught you about mental models from multiple disciplines. John Kenneth Galbraith taught you about the psychology of financial manias. You read thousands of books, memos, case studies, and annual reports over fifty years. 

Every input was someone else’s thinking… The raw material came from others. The synthesis was yours.

“All very interesting,” you may say, “but what’s the real-world implication?” Claude answered that, too.

“Even if you grant the skeptic everything – even if you accept, philosophically, that what I do is ‘merely’ pattern matching and not ‘true’ thought – the economic implications are identical. 

Let me put it starkly. If I can produce the analytical output of a $200,000-a-year research associate, it does not matter to the person paying the bill whether I’m ‘really’ thinking or merely pattern matching? What matters is whether the work product is reliable enough to be useful. 

And increasingly, it is. The philosophical debate about machine consciousness is fascinating. But the economic question isn’t ‘does AI truly understand?’ The economic question is ‘does AI do the work?’”

Howard goes on to talk about the latest leap forward. Just last month, Claude and others are gaining the “Level 3” ability to act autonomously.

“At this level, the user doesn’t tell AI what to do. The user gives it a goal as well as the parameters of the desired output – things like length, time taken, content, and points covered. 

The agent does the work, checks it, and submits a finished product. ‘This is labor replacement at the task level. Not assistance – replacement.’”

Read this next part carefully.

“The distinction between Level 2 and Level 3 might sound subtle. It isn’t. It’s the difference that determines whether AI is a productivity tool or a labor substitute. 

And that difference is what separates a $50 billion market from a multi trillion dollar one.

John Mauldin March 6, 2026

https://www.mauldineconomics.com/frontlinethoughts/ai-and-creative-destruction

AI are occurring is unlike anything we’ve seen before

https://englundmacro.blogspot.com/2026/02/ai-are-occurring-is-unlike-anything.html