A role change that changed what the model could do
A role prompt can change more than narrative tone. Experiments with Claude suggest a repeatable relationship between embodiment and coding behavior.
Lynn Cole / Laboratory
Experiments, research notes, mad science, and things in progress.
A role prompt can change more than narrative tone. Experiments with Claude suggest a repeatable relationship between embodiment and coding behavior.
High-volume generation creates QA and scope-control problems. Tests, milestones and explicit constraints matter more as the code arrives faster.
A broken coding-service connection led to a new LSP tool and a useful detour through the infrastructure agents need.
Noise painting uses hand-crafted adversarial inputs and incongruent prompts to push diffusion into unexpected visual territory.
WOVEN x26 hit a multi-project build wall. A return to Go and the Panda Protocol brought the focus back to labeling and context clarity.
Gemini’s recall behavior led me to test the difference between a large context window and active access to the larger session.
WOVEN x16 is a headless agent service built for asynchronous work, multiple models and composable tools.
WOVEN’s memory and tool layers led to a design detour through MCP, persistent connections and a more composable system.
A weekend of world-visualization experiments compares spatial reasoning, coding behavior and context coherence across models.
WOVEN x14 treats agents as collaborators, with an event bus, tool interfaces and memory services still being refined.
Klara’s diary records the day we got stable single- and multi-step tool use working, and the context and state-transition changes that made it possible.
WOVEN 13 brings memory and identity management into the agent architecture, connecting past decisions and conversations to the current session.