Press Space to continue
Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
Press Space to continue
Press Space to continue
I think the ideal model router actually is just starting with a cheap model and teaching it to escalate as needed + using a more powerful model as a “checker” that also can escalate
Reminder that Jev is a "system one" model. It does not reason. It categorizes. It is nearly impossible to know how "complex" a task is purely from a prompt. You need to understand the system the prompt is made in, the tools the agent has access to, and the complexity of what the agent has to work around to complete the work. Jev has none of this context. Literally zero. It cannot know how hard it is to make a change in your codebase. If you ask an agent to "port this to Rust," it doesn't know if the codebase is a 100-line TypeScript file or if it's a million-line complex application. It doesn't know if your request to fix a bug touches complex pieces of your application or if it's a simple two-line change. Jev is awesome, but it is not built for this. In order to know how much thinking a task requires, you have to think. Jev does not "think".