Busy: keys belong to tools, not agents
Busy’s security design keeps keys with tools rather than agents, alongside a growing set of communication, memory and scheduling features.
Lynn Cole / Laboratory
Laboratory
Experiments, research notes, mad science, and things in progress.
Recovering agent systems after a hard-drive failure
A hard-drive failure removed most of an almost-finished agent component. Recovering it meant understanding what had changed between two versions and rebuilding deliberately.
Designing a voice agent for embodied use cases
Building a voice agent into a surplus truck makes embodied use cases tangible: sensors, routes, memory, local inference and a constantly changing speech stack.
A talking agent on a small machine
A talking agent on a small machine brings together Whisper, Chatterbox, a tiny Qwen model and a boundary between stateful actors and smart functions.
GLM 4.7: early coding and behavior observations
Early GLM 4.7 observations: exceptional code output, rigid behavior and a tendency to act before asking the clarifying question.
Voice, multimodality, and lessons from a weekend build
Weekend lessons from voice, multimodal inference, certainty scoring, image stacks and tool instructions trained into small LoRAs.
Configuration adapters and a multi-reference image stack
Configuration adapters free context space by teaching tool instructions to the model. Preserving multimodal capabilities is the next difficult layer.
Reasoning loops as an engineering process
Reasoning loops belong in the engineering process as well as the weights. Spend more time when uncertainty and consequences justify it.
Working toward a Netscape moment for edge agents
Busy’s next experiment uses confidence scoring and different reasoning paths to push small edge agents beyond the usual workflow.
A training harness with an internal evaluation step
A planned training harness combines coding datasets, recursive refinement, compiler verification, play exercises and persona-based reviews.
Designing a deliberately vague agent evaluation
A deliberately vague evaluation tests whether a coding agent can build, audit, document and revise an application without constant micromanagement.
GhostTown’s synthetic podcast generator
GhostTown’s podcast generator turns a social simulation into editable scripts, multi-voice audio and recurring stories people can follow.