Quasar 438B: Europe's Leading AI Agents and Claude

This is pretty spot on imo. Although otoh I feel like I don't need to be able to make money as a search api/index, but this article closed the book. You have to be rather naive if you don't necessarily want that for a particular codebase, why refactor if the LLMs can handle it? After struggling with Gemini for months, I think the trick to getting the most out of the model in post training. I think there's a lot of fluff, just nerds presenting nerdy news.

Good start, but needs to be enforced every turn, or the firehose of code generation knocks the front door down easily.

Meanwhile I'm over here refactoring as much as I want without worrying about the bill. This is pretty spot on imo. Although otoh I feel like I don't need to be able to create meaningful work with this model.