If you're working from OpenAPI, ideally you want to be able to process any, potentially full of shit formatting spec file. I find that half the integrations I run into have some old weird version of Swagger, and the rest work like hell to stay up to date with the 3.x spec track.
I agree, I wish, it will be a solved problem eventually. Just feeding a complex data model like that to the paper shredder that is the LLM, for making decisions about whether DELETE or POST is used is just asking for trouble.
If I had to wager a guess, and this is being conservative and fortunate, after about a year and exhausting unemployment you start staring into the wall and saying 'WTF' to yourself out loud. It's a bummer and discouragement is the last sort of thing that person needs at that point.
Out of frustration, and because this now validates what I was thinking but couldn't put my finger on, I sat an AI agent down to 100% tailor cover letters and which resume to use based on the description of the job in question.
Turns out none of that actually mattered if the whole point is to generate busy-work and turn HR into another function like sales/marketing afraid to lose their budget for the year, or even worse to evaluate market conditions poorly. This entire thing should be illegal with the study at hand as evidence to make it so.
I was watching Dark Side of the Ring on Vice TV the other day (a vice of mine by chance), and despite the fact that their eponymous block bold letter design language was intact during the promo commercials for upcoming shows, it was clearly all for Vice-adjacent syndicated TV shows that felt more at home on HGTV or worse. I was pretty shocked and figured they just suffered the same fate of The Learning Channel, may it forever rest in peace.
This is cool, I took a good stab at using it last night but implementing CORS in the project I wanted it for was a pain on my end. Likely my issue, they have pretty clear but unfamiliar instructions if you’re just getting into non-trivial CloudFlare management. Great concept though.
I agree, I wish, it will be a solved problem eventually. Just feeding a complex data model like that to the paper shredder that is the LLM, for making decisions about whether DELETE or POST is used is just asking for trouble.