@codinginflow Like, every implementation is better when planned. Implement X means, first analyze my request, ask questions, create detailed plan, inplement tests, implement X. This takes time so Im trying to switch between two parallel sessions.
@GergelyOrosz Getting into a new technological stack would be much harder. For example, right now, I’m writing a lot of utility Bash and Python scripts and trying to build apps using technologies I’ve never worked with before. That would be much harder to do if I had to start from scratch.
Rewrite, check grammar, translate, extract...
Speed is critical in many use cases, and I don’t want to wait for reasoning to complete.
I see your point. This is my first time using multiple models, not just "the best one." The others are still very capable and for simple things "good enough".
It's interesting that people think prompts are the most valuable, not the infrastructure, technology, UX, internal benchmarks, ability to integrate new models quickly, or quickly assessing if adding 200$ tips to LLMs improves performance.