Find a note that interests you, then explore its prerequisites, references, and related discussions.
213 notes
How execution control, tools, state and verification turn model proposals into bounded work.
How step limits, tool validation, verification, cancellation, and durable state keep agent loops useful and recoverable.
Choose what an AI assistant should remember and retrieve, without confusing stored notes, search results, and authority.
Let AI find gaps, explain one step, and provide practice while keeping recall and problem solving with the learner.
Understand production agent harness responsibilities through Codex runtime state, context compaction, integration surfaces, and two-layer security controls.
How to assemble a small, current working set while preserving provenance and durable state outside the model window.
A practical way to label specifications, vendor claims, benchmark results, observations, and recommendations without pretending they prove the same thing.
Recover an agent’s progress after interruption without duplicating the side effects of retries.
A protocol-level view of MCP architecture, lifecycle, primitives, transports, trust boundaries, and alternatives.
This case preserves the Pi version and observation dates recorded below
How to package a repeatable agent procedure, test its trigger and outcome, and manage portability and code-execution risk.
How classical software engineering principles—design concepts, ubiquitous language, TDD, deep modules, and gray-box delegation—resolve failure modes in AI-assisted coding.
Design tools whose inputs, authority, side effects, failures, and evidence remain legible to models and operators.
Block target, group, temporal, and preprocessing leakage by defining prediction time, entities, and train-only pipelines.
Start from deployment distribution, splits, metrics, thresholds, and uncertainty instead of treating one test score as universal ability.
Break requests into measurable stages and explain how concurrency, caching, and batching affect waiting time.
Understand low-bit weight approximation, separate weight, activation, and KV-cache quantization, and estimate deployment costs.
Separate prediction accuracy, reliable probabilities, and worthwhile actions using independent calibration and evaluation data.
Measure evidence retrieval, ranking, faithfulness, and answer quality separately to locate a RAG system’s bottleneck.
Identify model artifacts and comparison conditions before selecting a model.
Follow next-token distributions to complete answers, including temperature, top-k, top-p, search, stopping, and structured output.
Distinguish model families by visible context, training objectives, and output heads, from BERT classifiers to generators and sequence converters.
Follow a token through MoE routing to distinguish total parameters, active parameters, memory, speed, load balancing, and communication.
Use image–text retrieval and visual question answering to distinguish objectives, patches, modality connectors, information loss, and evaluation.
Open an overview to find a topic’s scope and suggested reading routes.