Before OpenAI dropped ChatGPT, nobody knew chat would be such a hit. Several labs had versions of these things, Google engineers were getting finessed by a rudimentary model just like in the movie Ex Machina that came out 10 years prior which was satirizing Google

But I don't agree that they aren't product-ized. There are many applications doing calls to LLMs behind the scenes and are hits, leveraging structured data very heavily and not having conversations with users at all. I would say that there is a predictable scope creep from executives to surface a conversational aspect though. We need to bring representation to that so we can point to some other best practice to push back

Can you give examples of wrapped LLM logic?

API calls are expensive and slow, so I’ve shied away from integrating them into my personal projects. And of course there’s always the risk of hallucination.