Systems Modernization & AI Development

Recently, I tasked an agent with providing an assessment, grounded in the code base, of whether an LLM observability platform would help the local LLM review pipeline I run. Based on that grounding, I told the agent to provide an honest and truthful answer, not an assumed “yes, of course”.... [Read More]

Some weeks ago, I ran a spec-kit pipeline on a modernisation slice. The spec described what I needed: modernising a three-year-old personal CLI of mine, an offline paper-database searcher with a PostgreSQL backend, around 2000 lines of Python. The pipeline produced Alembic. [Read More]

Earlier I found the one rule that survived a model-offloading experiment: verify the artifact, never the account. The last post turned the same rule on instructions: make the expectation checkable, so the work can fail against it. This one turns it on your own findings. Same discipline, third surface: bookkeeping.... [Read More]

We’re taught to soften feedback so it lands. That’s the part that breaks it. [Read More]

The premise of offloading work to a cheaper model is great. Let the expensive model design. Let the cheap model implement. Put hard gates around the cheap model so it cannot ship something broken. Coverage thresholds, benchmark checks, documentation currency. The gate is supposed to make the model’s reliability irrelevant.... [Read More]