“But who was learning, you or the machine?”

“Well, I suppose we both were”

Amazing book 🔥🤓

#TheAlignmentProblem #Learning #ResponsibleAI

The Alignment Problem by Brian Christian 📚 https://micro.blog/books/9781786494320

The Alignment Problem

#TheAlignmentProblem is with the folks creating so-called “general” AI: their values are misaligned with the rest of humanity.

One of the maddening things about reading #BrianChristian’s #TheAlignmentProblem is that it assumes creating systems without firm use cases—“general” AI—is inevitable and desirable. It never questions assumptions of who is doing this work, why, and for whose benefit.

A book that talks in a positive way about narrowly scoped systems which multiply human potential while preserving values is needed. A kind of “Understanding Computers and Cognition” focused on today’s technology.

Client Challenge

Oh man #BrianChristian’s #TheAlignmentProblem is treating #WilliamMacAskill and the whole EA/Longtermer cult seriously on pp 235-36. This is after opening shots with a #NickBostrom quote on p 223.

Sigh.

Let’s see if he ever gets to the eugenics & racism.

I'm reading #TheAlignmentProblem by @brianchristian, a book about what can go wrong with AI systems. It's a must-read for anyone who's concerned about the future of AI and how to ensure that it's aligned with human values. #AiSafety #ExistentialRisk #ai