calibration — How well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
Why it matters
TypeSafe's Jev claims to replace LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → calls for structured, programmatic decisions with sub-second latency and no free-text hallucinationWhen a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.Full definition → risk, offering agentic systems a cheaper, type-safe alternative to chat-model tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition → for high-volume decision points.
