"My job is to figure out the right context and guardrails so that when you prompt “Build me a dashboard,” the result actually looks like your existing product."
What is the challenge here? Yes if you don't guide an LLM it will come up with it's own design.. but you can just tell it to use your brand and assets and it works pretty well
Define better. Faster to literally write the code - LLM. Deeper understanding of how it works - write yourself. Less skill atrophy - write yourself. More fun - write yourself. You can argue all these points and they’ll be different for everyone, but my feeling is that everything I listed in the original comment are clear additives to my process/learning.
I am out of the loop with Cursor. Did they make their own LLM model or do you mean they just capture what is being sent to other models and that is valuable?
They have a few in models that powered the app, including one that applied edits. Recently they also started fine tuning Kimi models under the “composer” brand, and Composer 2.5 is a very cost effective coding model. But I suspect that the real value is in the distribution they have, which is what I primarily meant.
It's the framework I'm most familiar with. As it was intended to be a personal project I just chose it because it was the easiest way for me to build it.
What is the challenge here? Yes if you don't guide an LLM it will come up with it's own design.. but you can just tell it to use your brand and assets and it works pretty well
reply