With LLMs, we like to think of "smart" and "dumb" as one axis (because we think of humans this way). I'd like to argue against this framing. Instead, try to think of "smart" and "dumb" as two different axes. A model can be incredibly smart AND dumb at the same time. For a good example of this, look at a Gemini model. They are incredibly smart: you can bench them and see the capability. The amount of knowledge Google bakes into their models is incredible. Yet when you ask it to do work, the amount of stupid things the models will do is similarly incredible. They are "smart" and "dumb" at the same time. Similarly, look at a model like Fable 5.1. It is not quite as smart as Astra, but it is significantly less dumb. Astra is still the smartest model available today, but it is also one of the dumbest, regularly doing things that make literally no sense whatsoever. Finding the right balance of both "smart" and "dumb" is a challenge that everyone needs to figure out, from users to researchers. If we stop thinking of it as either-or and instead realize both can exist together, understanding model behavior gets much easier.

With Ukraine facing a $27 billion budget gap, lawmakers are moving to decriminalize pornography. Legalization is expected to generate roughly $25 million in tax revenue, or enough to purchase 30,000 drones, said one Ukrainian lawmaker.

with refinery issues in the Great Lakes fading, gasoline prices are starting to fall. MI prices down 18c/gal from a week ago, OH -16c/gal, WI -10c/gal, IN -10c/gal, IL -9c/gal. diesel prices remain a bit sticky yet, but they will start falling in these states soon

With Giants QB Jaxson Dart set to undergo season-ending surgery on his left knee, Lauren E. Borowski, MD, a primary care sports medicine specialist from @NYULangone joins Brandon London for the weekly ‘Injury Report’ segment. #sponsored#