Before You Put an LLM in a Flow
Let an LLM generate content if the result is reviewable. Do not let it make the business decision.
Tag: ai
4 posts in this channel.
The Prompt Wasn't Wrong. The Handover Was.
Before giving work to a coding agent, ask what you would need to tell a developer who already knew the codebase.
GPT-5.6: Which Model and Effort Should You Actually Use?
GPT-5.6 is a meaningful step beyond GPT-5.5, but choosing well means using Terra by default, Sol deliberately, and Luna only for bounded work.
Why TurboQuant Actually Matters
TurboQuant matters because it attacks KV-cache pressure, one of the physical costs of serving long contexts to many users.