Jonathan Whitaker(@johnowhitaker):TIL, Anthropic's production alignment procedure uses ~30M training examples :) I'm recording a video (maybe live) with @alexisgallagher today on the Open Character Training paper, if you're interested in this kind of thing :)

Jonathan Whitaker

@johnowhitaker

Data scientist, AI researcher, aspiring gentleman scientist

Joined October 2015

1.2K Following 10.3K Followers

Jonathan Whitaker@johnowhitaker

2026.08.28 17:44

TIL, Anthropic's production alignment procedure uses ~30M training examples :) I'm recording a video (maybe live) with @alexisgallagher today on the Open Character Training paper, if you're interested in this kind of thing :)

Anthropic@AnthropicAI

2026.08.28 17:13

New Fellows Research: Can Claude autonomously align other AIs? We gave Claude 48 hours and 1 GPU to improve the alignment of small models. It researched and proposed methods, then trained and tested the models on its own. It worked surprisingly well.