The LLMentalist Effect: how chat-based Large Language Models rep…
The new era of tech seems to be built on superstitious behaviour
Reckons
Elegant and powerful new result that seriously undermines large language models
Wowed by a new paper I just read and wish I had thought to write myself. Lukas Berglund and others, led by Owain Evans, asked a simple, powerful, elegant question: can LLMs trained on A is B infer automatically that B is A? The shocking (yet, in historical context, see below, unsurprising) answer is no: