masterclass of a tech report

strong LLM priors are a powerful basin of reasonableness. you can twist and contort this to sample, filter, evaluate, synthesize; there’s a gravity towards Good imbued from the whole of the internet, you just have to set up the dominoes and let probability take the wheel

@TheodoreGalanos but actually, the tool call responses are also simulated, the tools are never real hallucination is a feature, not a bug