Any insights into how this is able to generate the Microsoft logo SVG near the end of the article? I feel like this would be a nearly impossible task unless there was another layer of knowledge on top of the language model. I'm leaning toward the example being gamed in some way (e.g. retrying until it happened to work). EDIT: also notable is that the first ChatGPT answer decribes the color as 'orange' but the SVG ans…
For example Google Duplex, I remember many being very impressed by this:
https://www.youtube.com/watch?v=D5VN56jQMWM
That entire conversation was just hardcoded with some if-else statements depending on what the other part said. The tech isn't as impressive when you know that, and anyone who interacts with the tech will realize that these are just hardcoded actions very quickly, but the demos will look very cool.
So applying that level of hardcoding to these situations you take a hardcoded script, then put an LLM on top that just generates calls to these hardcoded scripts, and voila now you have the exact same assistant you had before but now it has a more advanced text parsing interface.
But it generates a lot of buzz since people think that the whole thing is AI powered when only parts of it are and the rest wont generalize into typical situations. In fact it is now often worse than before since you can't reliably invoke the scripts you want to invoke, instead you have to fight the AI interface trying to get it to read your question the way you want it to.