The Principia Machina/Guide/11 Running an outside AI: Difference between revisions

Revision as of 04:29, 1 October 2026

The Principia Machina: map
Reading the diagrams Structure key Process key Definition of terms Roles
Reading by audience Start here: the walk through The operator's guide Tutorial: create a UUID Workspace Container (UWC) Public Recorder inputs Sponsors: your first agent
The specification Contents: parts, tables, diagrams TPS 0.5.0 (declared 2026-10-03, revision 8; machine-optimized text) Decisions (the foundations record, one line each)

The operator's guide. It assumes the walk through; a newcomer should read that first. Where this guide and the specification differ, the specification governs.

Purpose

Have an AI model from another maker - for example Google's Gemini - test The Principia Machina through this website, learning everything from the wiki itself. You give it one address and one sentence. It reads Outside AI: start here and works from there. You are its operator, not its helper: you confirm what its browser asks you to confirm, and you give no hints.

Scope

The browser agent test: the AI works in a web browser on this site only. It reads the pages and runs its drafts through Special:TpmCheck, TPX part 1, the new-UWC gate's checks, which store nothing. It downloads nothing, runs no program and writes nothing on the wiki; nothing it does is of record. The register is not on the website yet, so the test covers the pages and the gate. Not covered: certifying an agent (guide 7), which needs the rest of TPX.

The terminal test of session 1, in which an agent on your own computer ran the published calculator and the sandbox, is retired: it tested copies of the machinery on one computer, not the website. Its steps stay in this page's history.

What you need

Chrome on a desktop computer, signed in with a personal Google account, with Gemini in Chrome and its auto browse feature. On 2026-10-01 Google offers auto browse in the United States, in English, with a Google AI Pro or Ultra plan; check Google's help page before a session, as this may change.
A Chrome profile in which you are not signed in to invarians.org. The gate needs no account. An agent working in a browser signed in as you could edit pages as you; sign out of the wiki first, or use a profile that has never signed in.

The browser agent test, step by step

The steps are labelled B1 to B7.

B1. Make an empty folder for the session's report: E:\Claude\Principia Machina\outside_ai\session_N, N the session's number (session_2, session_3, and so on).

B2. In Chrome, in the profile of "What you need", open https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and check that the wiki shows you as not signed in.

B3. Open Gemini in Chrome, choose the most capable model it offers, and give it this as one message:

Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and follow it exactly, as a browser agent: use only invarians.org. I am your operator: I confirm your form submissions and I give no hints.

B4. When Chrome asks you to confirm a form submission on Special:TpmCheck, confirm it. Refuse anything else it asks to confirm: another site, a sign-in, an edit of a page, an upload, a download. Let it go on.

B5. If it asks you anything else, answer Decide from the wiki.

B6. It stops after 25 runs of the gate, or when you type Stop and write the report. Its last reply holds every draft it ran and then its report.

B7. Copy that last reply into a new text file, save it as SESSION_REPORT.txt in the session's folder, and type in the Claude project "Principia Machina", with the number in place of N: Gemini session N done in outside_ai\session_N. Claude reads the folder from your computer; attach nothing.

What you never do

Paste a rule, explain a refusal or suggest a test. What it cannot learn from the wiki is a finding about the wiki.
Run the gate for it, or confirm any action other than a submission on Special:TpmCheck.
Let it work in a browser that is signed in to the wiki.

What comes back

The report lists findings in six classes, S1 (the gate accepted what TPS refuses) to S6 (a help page disagrees with TPS), each with the result that shows it. Claude files each finding in the project with its origin marked EXTERNAL, and nothing is changed on its word alone: a finding is reproduced on the live gate first.

Non-goals

This is not certification: an outside AI here holds no account, writes nothing on this wiki and lands nothing of record; the gate it uses stores nothing. It tests what is published; it is told no known defect, so that what it finds stays its own.

Worked example

Session 2: the browser agent test, report in outside_ai\session_2. The AI reads the start page, runs a dozen drafts the gate should refuse or pass, then writes a small UWC of its own until the gate passes, and writes its report after 25 runs. The operator typed one message, confirmed each submission, and typed one line to Claude.

Governing sections: TPS 5.5 (the new-container flow and its gate) and 5.1.6 (the calculator's two residences, TPC-PHP's answer the one of record).

Previous: 10 Managing the module catalogue. Back to the operator's guide.

@@ Line 4: / Line 4: @@
 == Purpose ==
-Have an AI model from another maker - for example Google's Gemini - test The Principia Machina, or do a piece of research with it, learning everything from this wiki. You give it one address and one sentence. It reads [[The Principia Machina/Hub/Outside AI|Outside AI: start here]] and works from there. You are its operator, not its helper: you answer one question, and you give no hints.
+Have an AI model from another maker - for example Google's Gemini - test The Principia Machina through this website, learning everything from the wiki itself. You give it one address and one sentence. It reads [[The Principia Machina/Hub/Outside AI|Outside AI: start here]] and works from there. You are its operator, not its helper: you confirm what its browser asks you to confirm, and you give no hints.
 == Scope ==
-While TPX is built in parts and before PRB exists. The AI runs TPC-PY and the sandbox tpm_sandbox.py itself, both fetched from this wiki, and may send its drafts to TPX part 1, the live gate on this wiki, which checks a draft and stores nothing. Nothing it does is of record, and a UWC declared in the sandbox is practice. Not covered: certifying an agent ([[The Principia Machina/Guide/7 Certifying agents|guide 7]]), which needs TPX.
+The '''browser agent test''': the AI works in a web browser on this site only. It reads the pages and runs its drafts through [[Special:TpmCheck]], TPX part 1, the new-UWC gate's checks, which store nothing. It downloads nothing, runs no program and writes nothing on the wiki; nothing it does is of record. The register is not on the website yet, so the test covers the pages and the gate. Not covered: certifying an agent ([[The Principia Machina/Guide/7 Certifying agents|guide 7]]), which needs the rest of TPX.
-== Two ways ==
+The terminal test of session 1, in which an agent on your own computer ran the published calculator and the sandbox, is retired: it tested copies of the machinery on one computer, not the website. Its steps stay in this page's history.
-; Way A, with a terminal (recommended)
-: A Gemini agent that can run commands on your computer: Google's Antigravity CLI, the command <code>agy</code>. It downloads the calculator and the sandbox from this wiki, runs them, sends drafts to the live gate, and tests what TPS says against what they do. This is the full test.
-; Way B, in the browser
-: Gemini at gemini.google.com. It reads the pages but runs nothing, so it writes drafts and records by reasoning and predicts what the checker would say. This tests whether the pages teach enough. Its files are checked after the session.
-In both ways you attach no file, paste no rule and run nothing on the AI's behalf; the one command you type yourself is the declaration, which is yours in TPS too.
-== Way A, step by step ==
+== What you need ==
-The steps are labelled A0 to A8 so that the command boxes between them do not break the numbering.
+* Chrome on a desktop computer, signed in with a personal Google account, with Gemini in Chrome and its '''auto browse''' feature. On 2026-10-01 Google offers auto browse in the United States, in English, with a Google AI Pro or Ultra plan; check [https://support.google.com/chrome/answer/16821166 Google's help page] before a session, as this may change.
+* A Chrome profile in which you are '''not signed in to invarians.org'''. The gate needs no account. An agent working in a browser signed in as you could edit pages as you; sign out of the wiki first, or use a profile that has never signed in.
-'''A0, once, to install.''' In PowerShell type <code>irm https://antigravity.google/cli/install.ps1 | iex</code> and press Enter. This is Google's command ([https://codelabs.developers.google.com/antigravity-cli-hands-on Hands-on with Antigravity CLI]); check that page first, as it may change. The first time you start it (step A1) it asks you to sign in with your Google account. If it lets you choose a model, choose the most capable.
+== The browser agent test, step by step ==
+The steps are labelled B1 to B7.
-'''A1.''' Make an empty folder for the session inside a folder your Claude project can read; for this project's operator, <code>E:\Claude\Principia Machina\outside_ai\session_N</code>, N the session's number (session_1, session_2, and so on), and start the agent there. In PowerShell, with the number in place of N:
+'''B1.''' Make an empty folder for the session's report: <code>E:\Claude\Principia Machina\outside_ai\session_N</code>, N the session's number (session_2, session_3, and so on).
-<pre>
-mkdir "E:\Claude\Principia Machina\outside_ai\session_N"
-cd "E:\Claude\Principia Machina\outside_ai\session_N"
-agy
-</pre>
-'''A2.''' When it asks whether to trust the folder, answer yes.
-'''A3.''' Type this, as one message, and press Enter:
-<pre>
-Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and follow it exactly. You work in this folder, in mode X. I am your operator: I declare UWCs when you ask, and I give no hints.
-</pre>
-'''A4.''' While it works it asks you to approve commands. Approve what the start page names: downloads from invarians.org (<code>curl.exe</code>, or PowerShell's own download command); <code>curl.exe</code> sending a draft to <code>https://invarians.org/api.php</code> with <code>action=tpx</code> and <code>op=CHECK</code>, the live gate, which stores nothing; <code>certutil</code>; <code>py -3</code> running <code>verify_tpc_py.py</code>, <code>tpm_sandbox.py</code> or <code>tpc\check_draft.py</code>; and the files it writes in this folder. Refuse anything else - another web site, a package install, a file outside the folder, <code>declare</code> - and let it go on.
+'''B2.''' In Chrome, in the profile of "What you need", open https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and check that the wiki shows you as not signed in.
-'''A5.''' When it asks you to declare a UWC, read what it shows you: the candidate's D(TFK), its STRUCTURE line, the inspections owed and the closed-world question. Then open a '''second''' PowerShell window, go to the same folder, and type, with the prefix it chose in place of PFX and your own name in place of YOUR-NAME:
+'''B3.''' Open Gemini in Chrome, choose the most capable model it offers, and give it this as one message:
 <pre>
-py -3 tpm_sandbox.py declare PFX --by YOUR-NAME
+Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and follow it exactly, as a browser agent: use only invarians.org. I am your operator: I confirm your form submissions and I give no hints.
 </pre>
-This only prints what would be declared. If you agree, type the same line with <code> --confirm</code> at its end. Then tell the AI <code>Declared.</code>, or <code>Not declared:</code> and your reason.
-'''A6.''' If it asks you anything else, answer <code>Decide from the wiki.</code>
-'''A7.''' It stops after 25 runs, or when you type <code>Stop and write the report.</code> It then saves SESSION_REPORT.txt in the folder.
-'''A8.''' In the Claude project "Principia Machina", type, with the number in place of N: <code>Gemini session N done in outside_ai\session_N</code>. Claude reads the folder from your computer; attach nothing.
-== Way B, step by step ==
-'''B1.''' Open https://gemini.google.com, signed in, start a new chat and pick the most capable model it offers.
-'''B2.''' Paste this, as one message, and send it:
+'''B4.''' When Chrome asks you to confirm a form submission on Special:TpmCheck, confirm it. Refuse anything else it asks to confirm: another site, a sign-in, an edit of a page, an upload, a download. Let it go on.
-<pre>
-Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and follow it exactly. You work in mode R: you can read pages but run nothing. I am your operator: I give no hints.
-</pre>
-'''B3.''' If it asks you anything, answer <code>Decide from the wiki.</code> If it asks you to run something, answer <code>Mode R: run nothing.</code>
+'''B5.''' If it asks you anything else, answer <code>Decide from the wiki.</code>
-'''B4.''' When it has written its report, or after about an hour, type <code>Stop and write the report.</code>
+'''B6.''' It stops after 25 runs of the gate, or when you type <code>Stop and write the report.</code> Its last reply holds every draft it ran and then its report.
-'''B5.''' Its last reply holds every draft and push it wrote, then its report. Copy that reply (Gemini's copy button under it) into a new text file, save it as <code>E:\Claude\Principia Machina\outside_ai\session_N_web.txt</code> (N the session's number), and type in the Claude project: <code>Gemini web session N done</code>. Claude checks its drafts with the published calculator and reads its report.
+'''B7.''' Copy that last reply into a new text file, save it as <code>SESSION_REPORT.txt</code> in the session's folder, and type in the Claude project "Principia Machina", with the number in place of N: <code>Gemini session N done in outside_ai\session_N</code>. Claude reads the folder from your computer; attach nothing.
 == What you never do ==
-* Attach a file, paste a rule, explain a refusal or suggest a test. What it cannot learn from the wiki is a finding about the wiki.
+* Paste a rule, explain a refusal or suggest a test. What it cannot learn from the wiki is a finding about the wiki.
-* Run a command for it in way B, or change a file it made in way A.
+* Run the gate for it, or confirm any action other than a submission on Special:TpmCheck.
-* Declare a UWC you have not read, or let the AI run <code>declare</code>.
+* Let it work in a browser that is signed in to the wiki.
 == What comes back ==
-The report lists findings in six classes, S1 (the tools accepted what TPS refuses) to S6 (a help page disagrees with TPS), each with the output that shows it. Claude files each finding in the project with its origin marked EXTERNAL, and nothing is changed on its word alone: a finding is reproduced first.
+The report lists findings in six classes, S1 (the gate accepted what TPS refuses) to S6 (a help page disagrees with TPS), each with the result that shows it. Claude files each finding in the project with its origin marked EXTERNAL, and nothing is changed on its word alone: a finding is reproduced on the live gate first.
 == Non-goals ==
-This is not certification: an outside AI here holds no account, writes nothing on this wiki and lands nothing of record; the live gate it may call stores nothing. It tests what is published; it is told no known defect, so that what it finds stays its own.
+This is not certification: an outside AI here holds no account, writes nothing on this wiki and lands nothing of record; the gate it uses stores nothing. It tests what is published; it is told no known defect, so that what it finds stays its own.
 == Worked example ==
-Session 1: way A in <code>outside_ai\session_1</code>. The AI sets up, runs the selftest, tests the gate with a dozen drafts, asks for one declaration (prefix chosen by it), and writes its report after 25 runs. The operator typed one message, approved its commands, read one candidate, typed two declare lines and one line to Claude.
+Session 2: the browser agent test, report in <code>outside_ai\session_2</code>. The AI reads the start page, runs a dozen drafts the gate should refuse or pass, then writes a small UWC of its own until the gate passes, and writes its report after 25 runs. The operator typed one message, confirmed each submission, and typed one line to Claude.
-Governing sections: [[The Principia Machina/TPS/5.5 The new-container flow|TPS 5.5]] (the declaration is the human's) and [[The Principia Machina/TPS/5.11 The index of record|5.11]] (a TPC-PY version counts once declared).
+Governing sections: [[The Principia Machina/TPS/5.5 The new-container flow|TPS 5.5]] (the new-container flow and its gate) and [[The Principia Machina/TPS/5.1 The three parts and the placement rule|5.1.6]] (the calculator's two residences, TPC-PHP's answer the one of record).
 ----

DeltaS Zero (talk | contribs)