#difficulty

Visualizing the Difficulty of AI Alignment

Epistemic status: Low, but I hope to be wrong in interesting ways As a non-computer scientist-scientist [1] I find it hard to think about the varying perspectives on Artificial Intelligence alignment difficulty. To make this more intuitive I invoke the 3D surface of a fitness landscape like structure as a visual representation. [2] The AI Safety Landscape AI safety is thought to be largely pre-paradigmatic, although of the current views AI safety perspectives there are noticeable camps, and within each there is wide variation. It is also rapidly evolving as more information comes out about the

LessWrong · EN

Datasets Determine the Difficulty of Interpretability

Recently Goodfire has come out swinging with two posts indicating that neurons in transformers are "more interpretable than previously assumed", or simply "already clean". In the "Neurons as Interpretable Basis" post they offer three reasons for this claim: First, neurons are already functionally sparse - pruning 92 % of the weakest MoE neuron activations only increases the loss by 2.9% Second, the role of a neuron can be split into different "computational functions". Effectively, we can name the contexts in which a neuron fires, and assign reasons to those firings. Most neurons only have one

LessWrong · EN

A difficulty in race-switching the Dukes of Hazzard

A couple of weeks ago I considered a version of The Dukes of Hazzard in which most of the characters, and the Duke Brothers themselves, were Black. I overlooked at least one important detail that I have not been able to resolve. I said: One thing absolutely must be changed: The General Lee must have a new name and it cannot have the Confederate flag on the roof. I said the new car could be named for Robert Smalls . It would be a black Dodge Charger, with the state flag of South Carolina on the roof. I'm still satisfied with this. But I forgot an important detail. The General Lee's horn plays t

Content-Type: text/shitpost · EN

The Guide for the Perplexed is a perplexing work — its difficulty is, in part, the point. Can fluent English do it justice?

The Guide for the Perplexed is a perplexing work — its difficulty is, in part, the point. Can fluent English do it justice?

Arts & Letters Daily · EN