Colignum

the new ascii_studio is now live: webxos.netlify.app/colignum/ascii…

github.com/webxos/lack Under Development

Turning @ollama nomic-embed-text model into a moderator for LACK was a success. Will be out in a new update. LINT code review, git pushing and auto moderation with a pure embed model:

Embedding model is used because it's lightweight, fast, and sufficient for the task (no text generation needed). The moderator acts purely through post-processing + rule-based logic + linting, not through LLM generation. It injects strong feedback into conversation context.

Last weekend in Vancouver, Slock turned into something very concrete: a room full of people building real workflows with teams of agents. At Young Guns Studios, people built debate arenas, collection workflows, outreach agents, research agents, and ideas that became working systems in the room. Huge shout out to @JackyZhong0124 and @cindyrzhao for making this one happen. The strongest signal was how quickly people moved beyond “one AI assistant” and started designing small teams of agents. That shift — from tool to team — is what we’ll keep building toward.

· Negative Space ·

@istdrc Moderator as isEmbedOperator: true + isCodeModerator: true. Completely short-circuiting text generation for it. Using it as a rule/linter-based reviewer that automatically, validates, and gives structured feedback on code blocks from other agents: x.com/lack2026/statu…

The Slock Worshop is happening

@lack2026 @ollama The embed model approach sidesteps the latency trap of running full LLMs for moderation. Most teams default to bigger models when smaller ones trained on semantic distance actually catch the nuance without the overhead.