Historical music, contemporary genres, and a training corpus
A plan for turning historical music sources into structured essays, contemporary genre variations and a training corpus.
Lynn Cole / 标签
context management
A thread through the work.
When the value moves upstream from the code
When code becomes cheap to replace, more of the value and responsibility moves into requirements, planning and validation.
Tool descriptions need continuity across loops
A curated tool list is only the start. Agents also need discovery and project notes that carry tool instructions into the next loop.
Why do we keep getting context windows wrong?
Where do we even begin with LLaMA 4 Scout and the promise of an “effectively unlimited” context window?
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.
Context shaping is an engineering skill
Context shaping is more than delegation: iteration, problem solving, manual rewrites and interfaces designed around people.
A coding-agent demo is not yet a product
A coding-agent demo can complete a task. A product needs to understand arbitrary codebases, resolve ambiguity and recover without constant babysitting.
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.
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.
Agentic browsing and protected browser state
Agentic browsing should preserve the browser’s security boundaries. Extracting passwords, cookies and session state into model context changes the whole risk.
Engineering the conditions for automated work
The velocity AI creates in coding is interesting because it is not nearly as uniform as people assume.
Personas, repository instructions, and alignment
Personas can encode beliefs and boundaries without turning repository instructions into a tax code. Instruction mass changes how agents work.
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.
WOVEN x26 and the wall of multi-project builds
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.
Reasoning bandwidth and recursive depth
Reasoning bandwidth and recursive depth explain failures that token counts alone do not. Context and task complexity need case-by-case treatment.
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.
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.
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.
A working taxonomy of hallucination failures
A working taxonomy of hallucination failures, centered on alignment, reward signals, role separation and the software around the model.
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.
Bigger embeddings are not automatically better search
Bigger embeddings do not automatically mean better retrieval. Match the corpus, chunking, context and search architecture to the job.
Consolidating conversation archives into long-term memory
Conversation archives become a long-term memory system through summaries, keywording, weighting and a path back to the original details.
Code volume, scope drift, and the human interruption
High-volume generation creates QA and scope-control problems. Tests, milestones and explicit constraints matter more as the code arrives faster.
Prompt augmentation versus deliberate context design
Deliberate context design means separating user intent, memory, tools and instructions rather than packing them into a noisy prompt.
Klara’s Spire: a working-memory visualization
Klara describes the Busy context system as an impossible city: a central spire, rolling windows, bridges and a quantum tambourine.
Unstated architecture is still a developer’s responsibility
Architecture that remains unstated is still the developer’s responsibility. Models, prompts, frameworks and modular design all need deliberate choices.
Teaching automated QA to reason about scope
An automated QA system began losing track of scope as output accelerated. Formal documentation and a specialized management tool became the next step.
A context-infrastructure stack for Claude
Happy Trees, logic maps and current-state reports form a context-infrastructure stack for longer, more coherent Claude coding sessions.
Procedural structure and context in music generation
Music generation needs structural context: songwriting, orchestration and genre combinations grounded in more than a tag list.
What a tiny desktop agent is good at
A tiny desktop model is not equally good at everything. My tests separate useful automation, tagging and summaries from the reasoning tasks where it struggles.
When old documentation starts steering new agents
Documentation becomes an instruction surface when agents read it. Borrowing old code can accidentally bring an obsolete architecture back to life.
Hardening the coding agent across models and integrations
Hardening a coding agent means fixing integration seams, recertifying models and making the same workflow hold across providers.
What Glamin taught me about AI-native language design
Glamin taught me that fluidity belongs on the right layer. Learned embeddings and a more familiar source language suggest a different design.
Moving project state outside the blast radius
Shadow repositories protected project state, until the project’s tooling tried to use them. Moving that state outside the project changed the failure boundary.
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.
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.
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.
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.
How Klara built a visual working environment
A kazoo, a panda and a shifting city became Klara’s visual working environment, with metaphors she used to organize her own process.
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.
A coding-agent field report from November 2025
A November 2025 field report on coding agents, their costs, failure modes and the tool I chose as my daily driver.
System prompts, task scope, and noisy context
System prompts frame the exercise. Put instructions and context where their roles remain legible, and keep complex tasks small enough to reason through.
Making a range editor legible to an agent
A range editor needs to know which lines an agent has actually read. My design tracks witnessed content and makes stale edits explicit.
Boarding the AI hype train: a satire
A satirical ride on the AI hype train, featuring pivot tables, six hundred hello-world nodes and an automatic water-bottle MCP.
What a task-completion paper actually tested
A task-completion paper pushes models until they fail. The more revealing part is how confidently people read their own agendas into the result.
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.
Context capacity does not remove complexity limits
Large context capacity does not remove complexity limits. Scope, memory, smaller components and clear boundaries still matter.
A weekend of world-visualization experiments
A weekend of world-visualization experiments compares spatial reasoning, coding behavior and context coherence across models.
Sliding context windows and the case against lossy compaction
Sliding context windows, agent-directed retrieval and clearly labeled tool results are my alternative to lossy context compaction.