“LLM evaluation”

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

Review pane for calibrating an LLM judge: load a promptfoo CSV, mark your own labels and see where they differ from the judge.

3D walk-through of the computations inside a small GPT-style language model.

Sample apps and an expression playground for the WebNN API, which runs neural networks on device hardware from the browser.

Checks a Content Security Policy for weaknesses that allow script injection.

Evaluates a typed math expression and supports functions such as sqrt, sin, cos and abs.

Scores how good a translation is without needing a reference.

Runs one text through several sentiment models to compare their outputs.