Anthropic \ Tracing Model Outputs to the Training Data

$Thumbnail of Anthropic \ Tracing Model Outputs to the Training Data$

RelatedHighlights

Powerful AI systems can help us interpret the neurons of weaker AI systems. And those interpretability insights often tell us a bit about how models work. And when they tell us how models work, they often suggest ways that those models could be better or more efficient. —Dario Amodei, Anthropic

Sarah Wang • What Builders Talk About When They Talk About AI | Andreessen Horowitz

Nicolay Gerold added

It's a little bit of a conundrum. A model we do not understand explains another model we do not understand.

Thumbnail of www-x-com-ai-ctrl-status-1815718168460927322

Anthropic CEO Dario Amodei: "You can say a million things to a model and it can say a million things back, and you might not know that the million and oneth was something very dangerous." If Anthropic misses a dangerous AI threat, who faces the consequences?

ControlAI

x.com

Michael Iversen added

Generative AI is quite good at certain parts of the value chain of knowledge work, but thinks quite differently from humans. Anthropic, a company that focuses on understanding how AI works, has found that humans working side-by-side with expert AI assistants to perform various tasks produce superior performance compared to either the AI or a human

Noah Smith • Generative AI: autocomplete for everything

sari added

The fact that most individual neurons are uninterpretable presents a serious roadblock to a mechanistic understanding of language models. We demonstrate a method for decomposing groups of neurons into interpretable features with the potential to move past that roadblock.

Anthropic • Tweet

Davey added

OpenAI vs. Anthropic vs. Cohere

sacra.com

Abie Cohen added

they could try “switching to a different model, augmenting the training data in some way, collecting more or different kinds of data, post-processing outputs, changing the objective function, or something else.” Our interviewees recommended focusing on experiments that provided additional context to the model, typically via new features, to get the... See more

Shreya Shankar • "We Have No Idea How Models will Behave in Production until Production": How Engineers Operationalize Machine Learning.

Nicolay Gerold added

While LLMs continue to devour web-scraped data, they’ll increasingly consume their own digital progeny as AI-generated content continues to flood the internet. This recursive loop, experimentally confirmed, erodes the true data landscape. Rare events vanish first. Models churn out likely sequences from the original pool while injecting their own un... See more

Azeem Azhar • 🔮 Open-source AI surge; UBI surprises; AI eats itself; Murdoch’s empire drama & the internet’s Balkanisation ++ #484

MargaretC added