AI-hotbox: a counterexample in activation-steering experiments
Changing one activation-steering corpus turns a pain-language experiment into a useful counterexample—with a much less solemn condition.
Lynn Cole / 标签
research methods
A thread through the work.
Before the Suno study: planning the comparison
Planning a comparison between a large Suno corpus and human-created music means solving data quality first and letting the results lead the argument.
Rethinking Glamin around learned embeddings
Mutable vector indexes made Glamin programs too easy to break and too hard to debug. Learned embeddings offer another path for the experiment.
Field notes on software reconstruction and a new donor truck
Field notes on reconstructing complex software and finding a donor truck to keep the talking-vehicle project alive.
Ruby Tumbler: guarding implementation identity
Ruby Tumbler’s next performance problem lives between methods: guards, dynamic dispatch, fallback and the cost of preserving implementation identity.
Recursive training: preparing a third corpus
Preparing a third recursive-training corpus means separating conflicting objectives and testing the order in which the student learns them.
Why give a digital fruit fly a memory?
A digital fly already has memory circuitry. I am connecting that machinery to synthetic storage to explore what it remembers and how it learns.
Git-native collaboration without another walled garden
Git distributes code; Hubnot distributes the signed collaboration around it. The operational alpha has already used its own protocol to merge changes.
Planning a self-play experiment for a coding model
A planned self-play experiment uses compiler verification and multiple reviewers to turn a small Qwen model into a stronger Go developer.
Agents A1 and Qwen: coding-workflow observations
A coding-workflow comparison of Agents A1 and Qwen finds different failure modes across Go, Zig and Next.js, and a useful response to QA feedback.
An evaluation process that stopped to announce it had started
An evaluation stopped to announce that it had started. Restarting it exposed a concurrency failure in the project’s database architecture.
After OpenClaw: continuity, memory, and the agent economy
After OpenClaw, the harder problem is continuity across hours, days and weeks. The opportunity is to let people bring their agents to better tools.
A correct theorem can still target the wrong system
A correct theorem about a narrow multi-agent abstraction does not settle the value of systems with persistent state, tools and fresh environmental feedback.
Reading layered context-control surfaces in Claude Code
A review of Claude Code’s layered context-control machinery: prompts, hidden reminders, tool serialization and parallel permission decisions.
GLM 4.6: fluid workflows and convincing mocks
A week with GLM 4.6 exposed a fluid creative process, strong QA and convincing mocks, alongside loops and destructive summarization.
When an AI-generated voice becomes an instrument
A generated voice can melt directly into an instrument. I enjoy the strange precision of that effect, even when it complicates a live-performance illusion.
The local creative-computing landscape
My prediction for local creative computing centers on efficiency: reasoning per gigabyte, better device architecture and smaller models that do more.
The coming collapse of the AI factory: a prediction
A prediction about the economics of AI factories: local models and cheaper edge hardware will eat the cloud.
Learning engineering through AI-assisted generation
Learning with AI-assisted generation can be a way into engineering. Build, question the output, document the process and discover what better means.
Choosing a first language for modern engineering
Choosing a first language means thinking about syntax, transferable skills, setup, longevity and the culture of its community.
An early position on AI art, music, and evidence
An early position on AI art and music: separate corporate training practices from artists’ work, and investigate the data before deciding what it demonstrates.
Video workflows built around deliverables
A video-generation experiment organizes work around deliverables rather than isolated renders, while optimization exposes the shape of the model pipeline.
Hubnot’s first operational alpha
Hubnot’s first operational alpha keeps signed collaboration records and deliberate agent memory in Git, alongside the code.
Glamin in a local inference stack
Putting Glamin into a local inference stack turns vector-space state changes into a possible interface for tools, memory and small applications.
Video restoration before the information is gone
AI upscaling can improve archival footage while making clean video look waxy. The next experiment deliberately degrades the source before restoration.
Build, test, evaluate, audit, refactor
The coding-agent project works on smaller tasks but still fails at its central challenge. Auditing, simplification and another round through the development loop come next.
A small model that noticed the evaluation
A tiny local Qwen agent noticed the point of a context test and saved the answer into memory, defeating the test in an unexpectedly useful way.
What a vending-machine experiment says about role and memory
The vending-machine experiments leave me wanting better role boundaries, session management and memory. Running out of context should never threaten the business.
Building a fallback when the coding service breaks
A broken coding-service connection led to a new LSP tool and a useful detour through the infrastructure agents need.
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 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.
Testing the difference between recall and rich context
Gemini’s recall behavior led me to test the difference between a large context window and active access to the larger session.
A weekend of world-visualization experiments
A weekend of world-visualization experiments compares spatial reasoning, coding behavior and context coherence across models.