On Tuesday, January 14, 2025, at 6:12 PM, Matt Mahoney wrote: > Wolpert's theorem is fundamental to the alignment problem. Either you can > predict what AI will do, or it can predict you, but not both. We use > prediction accuracy to measure intelligence. If you want to build an AI that > is smarter than you, then you can't predict what it will do. This means you > can't control it either, because that would require you to predict the > effects of your actions.
Yes it is intuitively obvious, but it does seem that there may be a theoretical special case, not that it would be practical or achievable but it does make one wonder about the structure of things. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tff34429f975bba30-Mcafb1739aacc57cd3070ba95 Delivery options: https://agi.topicbox.com/groups/agi/subscription
