There’s an old saying that no one would ever eat a sausage if they knew how sausages were made. This is no doubt unfair to the meat-processing industry, for not all sausages are, as some wag famously observed, “cartridges containing the sweepings of the abattoir floor”. But it’s a useful cautionary principle when confronted by products whose manufacturers are – how shall we put it? – coy about the details of their production processes.
Enter, stage left, the tech companies currently touting their generative AI marvels – particularly those large language models (LLMs) that fluently compose plausible English sentences in response to prompts by humans. When asked how this miracle is accomplished, the standard explanations highlight the brilliance of the technology involved.
