Hello. What is on your mind today?
01 Rule-based dialogue, made visible
A conversation
you can inspect.
ELIZA Lab turns a famous interaction pattern into a small, honest learning tool. Every reply comes with its rule trace. Nothing leaves your browser.
- No accounts
- No transcript storage
- Not therapy
02 Live experiment
Talk to the rulebook.
Then open it.
Use a harmless, fictional prompt. The inspector shows what matched and how pronouns were reflected. The transcript exists only in this tab and clears on reload.
03 Under the surface
Small mechanism.
Large illusion.
Read the shape.
Whitespace and casing are normalized. The engine never sends the sentence elsewhere.
Choose one rule.
Patterns run in a documented order: safety boundary, greeting, feeling, reason, ownership, question.
Turn the sentence.
A tiny pronoun map changes “my” to “your” and returns the thought as a question.
Show the seam.
The selected rule and transformed fragment stay visible so the illusion never hides the method.
04 A clear boundary
A mirror is not a clinician.
ELIZA Lab is an educational software experiment. It does not understand a person, assess risk, provide treatment, or replace qualified care.
A small list of explicit safety phrases stops the simulation and points toward immediate human help. It is a boundary, not reliable crisis detection.
Read the safety and privacy model05 Refactored with intent
The useful idea survived.
The unsafe product did not.
The original 2023 Telegram prototype stored conversations and implied therapeutic use. This edition removes Telegram, MySQL, OpenAI and the PHP admin panel. What remains is a testable Rust engine and a transparent browser demonstration.