Knowledge/Domain
How systems built on language models actually work, and how they fail.
Drag to pan · hold ⌘/ctrl and scroll — or pinch — to zoom.
A neural network trained to predict text, used as a general-purpose instruction-following system.
Agents & Language Models·32 connections
Giving a model a set of callable functions so it can act on the world rather than only describe it.
Agents & Language Models·25 connections
The property that identical inputs may produce different outputs, and what it costs to test around.
Agents & Language Models·23 connections
Shaping a model's input to make the desired behavior reliable rather than occasional.
Agents & Language Models·21 connections
The bounded span of tokens a model can attend to in a single request.
Agents & Language Models·20 connections
Fluent, confident output that is not grounded in anything real.
Agents & Language Models·17 connections
The sub-word unit a language model actually reads and writes; the unit of cost and of context.
Checking data against a declared shape at runtime, and using the result as the typed value.
Agents & Language Models·15 connections
The finite allowance of model usage a task may consume, and the design decisions it forces.
A rule constraining what a model may do, enforced by prompt, schema, or surrounding code.
Agents & Language Models·14 connections
Capturing a real interaction once and replaying it deterministically in later test runs.
The standing instructions that frame every turn of a conversation with a model.
The cycle of model turn, tool call, observation, repeat — the basic mechanism of an AI agent.
Agents & Language Models·13 connections
A repeatable test suite for model behavior, since prompts and tool descriptions cannot be type-checked.
The text supplied to a language model to elicit a response.
Untrusted content that reaches a model's context and is treated as instruction.
Turning audio into text, and the reasons real-world accuracy is set by the signal more than by the model.
Agents & Language Models·12 connections
A hash over everything that determined a result, used to detect when the result has gone stale.
Constraining a model to emit data conforming to a declared schema rather than free text.
Reviewing work with an explicit mandate to refute it, from a perspective that did not produce it.
Agents & Language Models·11 connections
Restricting a model's next-token choices to those a formal grammar permits.
Reverse-engineering the computation a trained network learned into human-legible features and circuits.
A model instance spawned by another to handle a scoped task with its own context.
Durable facts stored outside the context window and recalled into later sessions.
Agents & Language Models·10 connections
Requiring a person's judgment at chosen points in an otherwise automated process.
Using a language model to score another model's output against a rubric.
A process whose next state depends only on the present state, and the basis of pre-neural text generation.
An open protocol for exposing tools, data, and prompts to AI applications through a uniform interface.
Coordinating several model instances on one body of work, each with its own context.
A packaged, invocable set of instructions that loads into an agent's context on demand.
Agents & Language Models·9 connections
Splitting work across parallel workers and recombining their results.
A vocabulary for describing the shape of JSON data, and the lingua franca of model tool interfaces.
Choosing which model handles which step, trading capability against cost and latency.
Fetching relevant documents at query time and feeding them into the prompt, so a model answers from retrieved text rather than memory.
Agents & Language Models·8 connections
Continuing to train an already-trained model on a narrower dataset to specialize its behavior, instead of prompting the base model.
Agents & Language Models·7 connections
A parameter that scales how sharply a model favors its most likely next token, trading determinism for variety.
Prompting a model to write out intermediate reasoning steps before its final answer, which measurably improves accuracy on multi-step problems.
Agents & Language Models·5 connections
A datastore built to find the nearest neighbors of a high-dimensional vector quickly, at a scale exact search can't reach.
A numeric vector representing a piece of content such that semantic similarity between items becomes geometric distance between vectors.
Agents & Language Models·4 connections
Storing a model's weights at lower numeric precision to shrink memory and speed inference, at some cost to accuracy.