Why do LLMs make stuff up? New research peers under the hood.

Large language models predict human sensory judgments across six modalities

Determining the extent to which the perceptual world can be recovered from language is a longstanding problem in philosophy and cognitive science. We show that state-of-the-art large language models can unlock new insights into this problem by providing a lower bound on the amount of perceptual information that can be extracted from language. Specifically, we elicit pairwise similarity judgments from GPT models across six psychophysical datasets…

Why do LLMs make stuff up? New research peers under the hood.

One of the most frustrating things about using a large language model is dealing with its tendency to confabulate information, hallucinating answers that are not supported by its training data. From a human perspective, it can be hard to understand why these models don't simply say "I don't know" instead of making up some plausible-sounding nonsense. Now, new research from Anthropic is exposing at least some of the inner neural network "circuitr…

Anthropic's Claude Is Good at Poetry—and Bullshitting

Researchers looked inside the chatbot’s “brain.” The results were surprisingly chilling.

Anthropic researchers make progress unpacking AI's 'black box'

Anthropic has pioneered a new method for revealing how Claude and other LLMs 'think,' hinting at why the models hallucinate and can be jailbroken.

Researchers at the Hebrew University of Jerusalem have found that the number of processed documents at RAG (Retrieval Augmented Generation) affects the performance of AI language models, even if the overall length of the text remains the same.The article Less is more: RAG systems work better with reduced document numbers first appeared on THE-DECODER.de.

"Gaslighting" is what you talk about when someone tries to specifically unsure another person – that also works with LLMs.