Using Consensus Mechanisms as an approach to Alignment — LessWrong

AI alignment is just the problem of AI bias writ (terrifyingly) large: We are assigning more societal decision-making power to systems that we don’t fully understand. D o these two groups of experts charged with making AI safe actually get along? T hese are two camps, and they’re two camps that sometimes stridently dislike each other.

I strongly suspect a much deeper challenge has just presented itself to humanity. It increasingly feels like there is a deep conceptual and technical connection between the two domains that calls for careful research. It feels like AI and crypto are mathematical evil twins of sorts; that each is somehow deeply incomplete without the other. The mild... See more

OpenAI’s Misaligned Superaligners > they had undeniably good intentions > but companies, economies, nations, are built on compromise > leadership is forced to make those decisions sometimes Counterfactual > Jan and Superalignment team were listened to > 4o release was delayed to 2025 > what would have happened? > Elevenlabs had professional q... See more