david_shi

Every time I ask the latest models to write something, it defaults to LLMisms like contrastive negation and long unnecessary lists. Is there a way to desloppify AI writing, or is this just the new status quo?

An agent's value is proportional to the permissions it's been granted. There's been a lot of hype around solutions like default denial proxies, key vaults, and more, but nothing seems to address the core tension: an…

What did you build and how is it going? Did you get any adoption?

Single-agent setups hit a scaling limit. Agents that are overloaded with skills and integrations, get slower and less reliable, just when coding agent hit their context window limits. That's why we built Operator…