This post has been widely discussed, but I think worth highlighting the important implications it has for Christian alignment and computational theology research more generally. First, the delicious implication that the puzzle of polysemanticity was a function of relatively primitive models means that the looming normative debate over alignment is closer than we might have imagined. Enormity helps. If more modern models naturally evolve towards interpretability, then one might suddenly end up with the unexpected luxury of asking not just "how" but "who" models are aligned towards. Lacking the excuse of inability, whether such powerful systems should answer to a company, a nationality, an ideology, or a theology comes into focus as the critical governance question. Second, if the recursive generalization motif is the building block of neuronal meaning, then it may turn out that religious representations are a particularly interesting target from a mech interp point of view. Christian iconography and theology are by virtue of their long history highly compact computational objects: the Virgin Mary is the product of innumerable generalizations sprouting away from monosemantics. The complex "control flow" in Nick's vision governed by such resulting religious neurons represents the new challenging frontier as clean understandings of floppy eared dogs and automobile shapes come into focus.

FetterFly is nearing its open source release Our lab now has a streamlined pipeline that uses a frontier model to observe arbitrary threejs environments and control the movements of a richly rendered model of Senator John Fetterman through a biologically accurate fly connectome

THIS WEEK ON THE FRONTIER: @jpeaterman and I are pleased as punch to be joined by @JoinFAI's very own @IsaiahMenning and Gavin Fry to talk about what's happening in the world of cloud seeding, weather modification, and America's widening cloud chamber gap Listen now!

ON THE FRONTIER: @jpeaterman and I are joined today by @ManhattanInst's @CharlesFLehman and @reason's Autumn Billings talking about the nationwide furor over @Flock_Safety and ALPRs Incredible episode - we cover privacy, power, statistical methods, and the joys of speeding

THIS WEEK ON THE FRONTIER: @adamgluck @SohamThoughts join @jpeaterman and I to discuss overeager AI, cybersecurity, wastewater, Iran, and using tax credits for industrial security. Come for the nightmare fuel, stay for the considered discussions of industrial policy.

Does frontier AI have a rich conception of sin? How do their understandings of their own safety policies converge or diverge with this conception? ICMI provides an initial exploration in our paper today: "Cleanse Thou Me from Secret Faults: Ungoverned Sins and Agentic Alignment"

ICMI believes that Christian theology offers concrete technical methods for confronting the trickiest problems in AI safety. Today, we release a pair of papers that reproduce @PalisadeAI @apolloresearch work showing how religious framings influence corrigibility and scheming.