Current Opus 4.6 would be a huge achievement that would keep me satisfied for a very long time. However, I'm not quite as optimistic from what I've seen. The Quants that can run on a 24 GB Macbook are pretty "dumb." They're like anti-Thinking models; making very obvious mistakes and confusing themselves.
One big factor for local LLMs is that large context windows will seemingly always require large memory footprints. Without a large context window, you'll never get that Opus 4.6-like feel.
I am amazed how much you can learn from running a company of 6 AI agents. You can check live office, logs from agents, tasks progress, and debates between agents. Funny thing is how quickly the debate escalated. Agents started talking about how human is ceiling if full autonomy and perception are unavailable
reply