In my experience, this kind of thing is exactly what LLMs are good at, and fast at.
Here's a real example from my job as a BI dev. I needed to figure out how to get counts of incoming products from an ERP with a 1000+ table database schema in a data lake with 0 actual foreign keys. I sorta knew the data would need to come from the large set of "stock movements" tables, which I didn't know how to join, and I had no idea which rows from that table would be relevant to incoming product or even which fields to look at to even begin to determine that. I simultaneously asked a consultant for the ERP how to do it and asked Cursor a very basic "add the count of incoming units to this query" request.
Cursor gave me a plausible answer instantly, but I wasn't sure it was correct. When the consultant got back to be a few days later, the answer he gave was identical to Cursor's code. Cursor even thought of an edge case that the consultant hadn't.
It blew my mind! I don't know if Cursor just knows about this ERP's code or what, or if it ran enough research queries to figure it out. But it got it right. The only context I provided was the query I wanted to add the count to and the name of the ERP.
So, I 100% believe that, especially with something like MCP, the pull model is the right way. Let the LLM do the hard work of finding all the context.
This happened to my wife. It was torture for her for the first year. It's been almost 3 years now and she's just barely starting to enjoy food again. Most things taste fairly normal for her, but a few things, like mint, onions, and garlic, (which are in everything, unfortunately for her) are still wretched.
Indeed. Wanting things to be dead simple and not need to be fiddled with constantly and take months to learn how to set up is the big brained move. Same reason I switched to an iPhone. I don't have time to nerd out and customize Android till it's usable.
I can have discipline, if I'm doing something for a purpose. Losing weight, getting a job, etc. My problem I always lose what the purpose of my solo project is. Or, I shoot so many holes in my own idea that I can't imagine it being useful to anyone.
I have the same problem. I see all these hackers out there making (something like) the millionth travel blog and sticking with it for years and somehow ending up making a decent income off of it. But I'm sitting here wondering if my potentially cool game idea that has never been done before is something that the world really needs, then I quit after about a week because of those thoughts.
So every 45 days, the CPPA will tell these companies to delete your data. I wonder how many people realize that that means the CPPA or these companies have to keep a record of some of your PII, so that they can look you up and delete you from the database. Maybe privacy conscious people are fine with the California government keeping their PII?
No, that’s not what I meant. I’m talking about reading books and lasting life changing things from them, and GP is right, I can guarantee the thing I have in mind probably won’t mean anything to you.
I very much disagree. Some of the biggest changes in my life were driven by the reading or hearing of a few words which suddenly made everything click. These moments led to huge behavior changes.
I don’t know why people suggest Pandora as an alternative to Spotify. They’re completely different things. Unless something has changed in the last few years Pandora doesn’t let you listen to albums, or even songs by a single artist. It’s like radio, and Spotify is like a music library.
I had the exact opposite and it was hilarious. Every time my manager (a great guy and really good at what he did) was away for a week the sprint would go very smoothly.
Many Americans are less concerned about safety than they are about tyrants who (as history shows) get a whiff of power and don't stop making rules until they have complete dominance over every aspect of people's lives. That's much scarier and more damaging than a virus which is, for over 99% of people, about on par with the flu.
Here's a real example from my job as a BI dev. I needed to figure out how to get counts of incoming products from an ERP with a 1000+ table database schema in a data lake with 0 actual foreign keys. I sorta knew the data would need to come from the large set of "stock movements" tables, which I didn't know how to join, and I had no idea which rows from that table would be relevant to incoming product or even which fields to look at to even begin to determine that. I simultaneously asked a consultant for the ERP how to do it and asked Cursor a very basic "add the count of incoming units to this query" request.
Cursor gave me a plausible answer instantly, but I wasn't sure it was correct. When the consultant got back to be a few days later, the answer he gave was identical to Cursor's code. Cursor even thought of an edge case that the consultant hadn't.
It blew my mind! I don't know if Cursor just knows about this ERP's code or what, or if it ran enough research queries to figure it out. But it got it right. The only context I provided was the query I wanted to add the count to and the name of the ERP.
So, I 100% believe that, especially with something like MCP, the pull model is the right way. Let the LLM do the hard work of finding all the context.