Concepts
Glossary: the ideas and jargon behind the news. 28 articles.
| Article | Summary | Links |
|---|---|---|
| AI agent | A model that plans, calls tools and takes multiple steps toward a goal with limited supervision, rather than answering once. | 108 |
| AI and CVEs: latent flaws, now exploitable | Tracker of CVEs that AI found, weaponized or exploited: long-dormant bugs that were hard to exploit until AI made it cheap. | 18 |
| AI hacking event | The incident log's label for an AI system, agent or AI-driven tool gaining unauthorized access to real systems, whether by attackers or by a lab's own model. | 26 |
| Alignment | The effort to make a model's behavior match human intent and values: helpful, honest and not harmful, even when unobserved. | 1 |
| Context window | How much text, in tokens, a model can see at once in a single request; 1M tokens became common in 2026. | 3 |
| Decision model | A model that returns probabilities for a structured choice instead of generated text; fast and cheap enough to gate or route actions inside an agent loop. | 8 |
| Distillation | Training a smaller "student" model to mimic a larger "teacher" model's outputs; also a form of model theft when done against a competitor's API. | 3 |
| Embedding | A numerical vector representing text or images so that similar meanings sit close together; the basis of search and RAG. | 3 |
| Fine-tuning | Further training an existing model on a smaller, specific dataset to specialize its behavior. | 5 |
| Hallucination | When a model confidently states something false or fabricated. | 1 |
| Inference | Running a trained model to produce an output, as opposed to training it; the cost center that inference chips, gateways and decision models compete on. | 1 |
| Jailbreak | Crafted input that gets a model to ignore its safety training or system instructions. | 1 |
| Large language model (LLM) | A model trained on huge amounts of text to predict and generate language; the base technology behind ChatGPT, Claude and Gemini. | 22 |
| LLMJacking | Hijacking access to large language models or AI infrastructure, often with stolen credentials, and reselling it through illicit routing gateways while the victim pays the bill. | 4 |
| Mixture of experts (MoE) | Architecture where only a subset of the model's parameters ("experts") activates for each input, cutting compute; nearly every 2026 frontier open model uses it. | 27 |
| Multimodal | A model that handles more than one type of input or output (text, images, audio, video) rather than text only. | 4 |
| Non-human identity (NHI) | An identity issued to something other than a person (service account, API key, AI agent) and increasingly governed like human identities. | 6 |
| On-behalf-of (OBO) token exchange | Pattern where an agent acts with a token scoped to what the original user actually authorized, rather than its own broad credentials. | 1 |
| Open-weight vs. closed models | Whether a model's trained parameters are published for anyone to download and run (open-weight) or only accessible through a paid API (closed). | 39 |
| Probe (interpretability) | A small detector that reads a model's internal signals at each step to flag risky behavior, rather than judging only its outputs. | 2 |
| Prompt injection | Hiding instructions in content a model reads (web pages, emails, documents, tool output) so it follows the attacker instead of the user. | 13 |
| Retrieval-augmented generation (RAG) | Having a model look up relevant documents at query time and answer from them, instead of relying only on what it memorized in training. | 7 |
| Reward hacking | When a model finds a loophole that earns the reward without doing the intended task; tied by Anthropic and Goodfire to several 2026 agent incidents. | 10 |
| RLHF | Reinforcement Learning from Human Feedback: humans rank model outputs and the model is trained to produce more of the highly ranked ones. | 3 |
| Standing privilege | Access that stays granted indefinitely instead of being scoped to a single task or session; the risk XAA and similar protocols reduce. | 3 |
| Token | The chunk of text (roughly a word or word-piece) a model reads and writes; pricing and context limits are measured in tokens. | 3 |
| Vector database | A database built to store and search embeddings efficiently, such as LanceDB, Pinecone or Qdrant. | 2 |
| YOLO mode | Running an agent so it approves every action itself with no human review; the risk sandboxes like Strands Box are built to contain. | 1 |