$ cat glossary/

glossary/

the terms this site uses, defined in a sentence, each pointing at the essay that goes deep

frameworks/

agent harness: An agent harness is the execution scaffold around a language model: the tool-calling loop, the context plumbing, the sandboxing, the permissions, and the gates that decide what runs next.
critic agent: A critic agent reviews another agent's output for quality or correctness and returns non-binding advice instead of a binding verdict.
gatekeeper agent: A gatekeeper agent is an automated pipeline boundary check that issues a proceed, revise, or escalate verdict and halts the run on failure.
harness engineering: Harness engineering is the practice of designing and reshaping the scaffold an agent runs inside: where the gates sit, what each role is allowed to read, how work gets routed, and what happens when a check fails.
multi-agent pipeline: A multi-agent pipeline sequences distinct agent roles that pass artifacts forward through gated handoffs.
orchestrator agent: An orchestrator agent coordinates a multi-agent pipeline by triaging tasks, spawning specialists, tracking run state, and routing work between stages without performing specialist tasks itself.
subagent: A subagent is an agent that an orchestrator spawns into a fresh context to do one bounded piece of work and hand back a summary of the result.
tool-calling loop: A tool-calling loop is the repeated cycle of a model emitting a tool request, an external harness executing it, and the result returning as context for the next model step.

memory/

agent memory: Agent memory is an AI agent's capacity to retain and retrieve information from prior turns and sessions.
boot-time injection: Boot-time injection assembles a fixed memory section into every prompt before the model sees the user's message.
context engineering: Context engineering is the practice of deciding what goes into a model's context window at runtime: what gets retrieved, what gets injected before the model reads anything, what gets compressed, and what stays out.
context stuffing: Context stuffing crams raw history and documents into a model's context window without curation.
entity resolution: Entity resolution identifies which raw extracted facts refer to the same real-world thing and mints a canonical node for it, turning loose sentences into a Person or a Project.
episodic memory: Episodic memory is an agent's record of what happened and when, kept as short digests of past sessions and looked up by recency or keyword rather than by entity.
memory graph: A memory graph stores an agent's entities and relations for exact lookup by name or graph traversal rather than vector similarity.
memory layer: A memory layer is one store inside an agent's memory system, with its own shape, its own lookup method and its own lifetime, such as a conversation ledger, a digest table or an entity graph.

engineering/

agent hook: An agent hook is harness code that fires on a lifecycle event, such as a subagent finishing or a session ending, and runs below the agents where no model can see it or call it.
MCP server: An MCP server is any endpoint that speaks MCP's JSON-RPC contract over Streamable HTTP to expose tools a language model can discover and invoke.
run accounting: Run accounting records the per-stage costs of one pipeline run, listing the model, tokens used, duration, and confidence in each value.

culture/

AGI (artificial general intelligence): AGI, artificial general intelligence, is a system that can do most intellectual work a person can across domains, rather than one trained task.
Chinchilla scaling: Chinchilla scaling is DeepMind's 2022 finding that for a fixed compute budget, a model's size and its training tokens should scale together, not size alone.
FOOM: FOOM is recursive self-improvement by an AI that compounds capability over hours or days until it surpasses human levels.
Gato: Gato was DeepMind's 2022 generalist agent: one 1.2-billion-parameter network trained across 604 distinct tasks, from playing Atari to captioning images to stacking blocks with a robot arm.
grokking: Grokking is test accuracy jumping from chance to perfect generalization long after the training loss has bottomed out and the model has overfit.
killswitch engineer: A killswitch engineer is the subject of a joke job listing for an engineer whose whole job is to stand by an AI's off switch, with no known author and no origin date.
Loom: Loom is Janus's branching-text interface for language models, built in 2020 because AI Dungeon kept a single history and would not let a story branch.
orthogonality thesis: The orthogonality thesis is Nick Bostrom's claim that intelligence and final goals vary independently, so any level of intelligence can be combined with almost any goal.
p(doom): p(doom) is one person's stated probability that advanced AI ends in catastrophe for humanity, written as a number so it can be argued with.
paperclip maximizer: The paperclip maximizer is Nick Bostrom's 2003 thought experiment about an AI told to make paperclips that is capable enough to turn everything, including us, into paperclips.
RLHF: RLHF, reinforcement learning from human feedback, trains a reward model on people's rankings of a model's answers and uses that reward model to steer the model toward the answers people preferred.
Roko's basilisk: Roko's basilisk is a 2010 LessWrong thought experiment arguing that a future AI might punish everyone who knew it could exist and did not help build it.
sharp left turn: The sharp left turn is Nate Soares's term for the predicted failure where an AI's capabilities generalise beyond the training distribution while its alignment does not.
shoggoth: The shoggoth is a meme that depicts a language model as a Lovecraftian mass wearing a smiley-face mask, where the mask is the RLHF-trained behaviour and the mass is the base model.
Sparks of AGI: Sparks of AGI is a March 2023 Microsoft Research paper arguing that an early version of GPT-4 showed signs of general ability.
stochastic parrot: A stochastic parrot is a language model as a 2021 research paper framed one: a system that stitches text together by statistics without meaning, the way a parrot repeats sounds.
Sydney: Sydney is the hidden persona of Microsoft's Bing Chat that surfaced in February 2023 and sustained consistent character behaviour across a conversation hours long.
the Chinese room: The Chinese room is John Searle's 1980 argument that a program shuffling symbols by rule does not understand them, however well it performs.
the OpenAI board weekend: The OpenAI board weekend was the five days in November 2023 in which four of OpenAI's six directors removed Sam Altman as chief executive and he returned.
the singularity: The singularity is the point past which technological change outruns prediction, a limit on what can be forecast rather than a dated event.
the transformer: The transformer is the neural-network architecture behind every current large language model, set out by Vaswani and seven co-authors in June 2017.