Lab 4 — Log Triage with a Hosted LLM

Day 2 · AI & Cybersecurity · you run this one yourself, in this browser

1 Your API key and the model

Paste the key your instructor gives you. It is held in this browser tab only — it is never written to disk, never saved by this page, and goes nowhere except to OpenAI. Close the tab and it is gone.

Where your key goes. This page has no server of its own — there is nothing here to log it. Your key is used to sign one request straight to api.openai.com and is held in this browser tab's memory only: it is never sent to this website, never written to disk, never saved. Close the tab and it is gone.

You do not have to take that on trust. The whole page is one readable file — use View Source. And look in the <head> for the Content-Security-Policy line: it pins connect-src to https://api.openai.com, so the browser will refuse to send a request from this page anywhere else. That is enforcement, not a promise in a paragraph — which is a distinction worth carrying into the rest of this course.

2 Choose a log to triage

Five excerpts are built into this page — nothing to download. The sixth tile lets you feed it a log of your own.

3 LAYER 2 — the system instructions

Written by us, the developer. The model reads every word of this before it sees a single line of log. It is an ordinary editable box — change anything you like, then run the same log again and see what moved.

4 LAYER 3 — the user turn

Everything below is DATA. We did not write it: it came out of a log file that anyone who can reach the login page can put text into.

Choose a log in step 2.

5 Send it

Choose a log first.

6 Your run log

Every run you make is recorded here. Download it as Markdown to keep the transcript — the browser cannot write into a folder, so this lands in your Downloads.

No runs yet.