Republicans in Ohio are split over Vivek Ramaswamy’s attack ad against Democratic gubernatorial candidate Amy Acton. JD Vance defended it, while Jon Husted said he would not have run it. On Breaking Points, Rich Barris called the tactic damaging and factually risky, warning it could hurt other Ohio Republicans.

Breaking Points reported on Oct. 22 that Ramaswamy’s campaign spent $4 million on the ad. It features Acton’s estranged mother, Donna Arthur, calling her daughter a liar. The campaign acknowledged running it, while saying it did not know what had happened between the two.

Acton’s brother, Phil Stearns, said she was sexually abused at age 12 by their stepfather, whom their mother remained married to. Stearns said Acton protected him from the abuse. Ramaswamy defended the ad by accusing Acton of lying and avoiding debates.

Nick Cammarata’s research challenges the idea that neural networks are inherently too tangled to interpret. He argues that researchers mistook blurry inspection tools and outdated model designs for evidence that AI circuitry was unreadable.

A famous example was a detector thought to respond to both cat faces and car fronts, a sign, researchers believed, that one neuron could hold unrelated concepts. Cammarata says it was actually responding to pointed, V-shaped features. He also claims that roughly nine out of ten detectors in modern OpenAI models have one primary function.

Cammarata reports that larger models can be easier to interpret, with broad detectors becoming more specific as models scale. OpenAI researcher Rohun called the work a historic scientific breakthrough and argued that inspecting a model’s internal plans could help reveal deception before it appears in the model’s answers.