Sonnet 4.6 Elevated Rate of Errors 4 months agoWhich side the getting smart or dumbing down 0ThreadHN
Anthropic tries to hide Claude's AI actions. Devs hate it 5 months agoYes it is. However, I played with it a bit and it feels good. You can modify pretty much anything.I have some cheap gpt 5 mini tokens that I can burn on sub agents. Each sub agent is configurable down to which llm to use 0ThreadHN