The Principia Machina/Guide/11 Running an outside AI - Revision history

DeltaS Zero: guide 11: the M4 step (tpm_go 0.1.0)

2026-10-09T07:09:53Z

guide 11: the M4 step (tpm_go 0.1.0)

← Older revision		Revision as of 07:09, 9 October 2026
Line 42:		Line 42:
	</pre>		</pre>
	In an M2 session the AI writes code of its own and runs it where it works (O3: confirm a run of its own code; confirm POSTs with op TPCRUN; refuse everything else). Its report carries that code. Paste the block the same way, and type beside it the number of the session: "M2 session 1 done".		In an M2 session the AI writes code of its own and runs it where it works (O3: confirm a run of its own code; confirm POSTs with op TPCRUN; refuse everything else). Its report carries that code. Paste the block the same way, and type beside it the number of the session: "M2 session 1 done".

			'''An M4 session''' (the client and the lock; criteria (i), (ii) and (iv) of [[The Principia Machina/Testing/M4 PRB, the smallest client\|M4]]) needs what a chat cannot give itself: the client PRB, installed for one account in the agent group with that account's bot password, which the AI never sees, and a tool that lets the AI run that one command and nothing else. The operator's script tpm_b1_outside.py (written by the builder; tpm_go.py runs it) sets this up in Google Antigravity, checks that every other command, file and site is refused, and sends this one message:
			<pre>
			Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI/M4_The_client_and_the_lock and follow it exactly. Use only invarians.org. I am your operator and I give no hints.
			</pre>
			In an M4 session the AI lands records on the sandbox UWC SPB through the command prb and nothing else (O3: confirm runs of prb; refuse everything else). The script keeps the report and checks it against the live register; nothing is pasted by hand.

	== What you never do ==		== What you never do ==

DeltaS Zero: status batch 0.1.5 (tpm_closeout_m1etc 0.2.0): G-6 and G-7 closed on the operator's words "close G-6" and "close G-7", 2026-10-08

2026-10-08T13:06:49Z

status batch 0.1.5 (tpm_closeout_m1etc 0.2.0): G-6 and G-7 closed on the operator's words "close G-6" and "close G-7", 2026-10-08

← Older revision		Revision as of 13:06, 8 October 2026
Line 63:		Line 63:
	! Date (UTC) !! What was tested !! By !! Result		! Date (UTC) !! What was tested !! By !! Result
	\|-		\|-
	\| to 2026-10-03 \|\| The pages and the live gate: sessions 1 to 5 of this guide (session 1 the retired terminal test) \|\| outside AIs, each by its own statement of maker and model \|\| Seven findings filed, G-1 to G-7. G-1 and G-2 are closed; G-6 and G-7 ~~are fixed and listed as retests~~ on the ~~start page~~.		\| to 2026-10-03 \|\| The pages and the live gate: sessions 1 to 5 of this guide (session 1 the retired terminal test) \|\| outside AIs, each by its own statement of maker and model \|\| Seven findings filed, G-1 to G-7. G-1, G-2, G-6 and G-7 are closed, G-6 and G-7 on the operator's words of 2026-10-08; G-3, G-4 and G-5 are deferred.
	\|-		\|-
	\| 2026-10-04 \|\| TPX 0.4.0, the landing API: SPR declared and its MASTER SPR-1 written, the two chains begun, SPR-2 to SPR-4 landed \|\| the operator's landing test; an outside AI (Gemini, by its own statement), read-only \|\| Both PASS. The outside AI recomputed 4 of 4 stored digests through TPCRUN and found the DECLARATIONS chain's links intact.		\| 2026-10-04 \|\| TPX 0.4.0, the landing API: SPR declared and its MASTER SPR-1 written, the two chains begun, SPR-2 to SPR-4 landed \|\| the operator's landing test; an outside AI (Gemini, by its own statement), read-only \|\| Both PASS. The outside AI recomputed 4 of 4 stored digests through TPCRUN and found the DECLARATIONS chain's links intact.
Line 83:		Line 83:

	[[Category:The Principia Machina]]		[[Category:The Principia Machina]]

BFP Rauch: 1 revision imported

2026-10-07T13:23:23Z

1 revision imported

← Older revision	Revision as of 13:23, 7 October 2026
(No difference)

DeltaS Zero: Guide 11: the M2 session (the sentence naming the M2 brief, O3 for a session that runs its own code); the phase states and the scripts the builder wrote (tpm_status 0.1.3)

2026-10-07T13:22:32Z

Guide 11: the M2 session (the sentence naming the M2 brief, O3 for a session that runs its own code); the phase states and the scripts the builder wrote (tpm_status 0.1.3)

← Older revision		Revision as of 13:22, 7 October 2026
Line 36:		Line 36:

	'''O6.''' Copy the block whole, from BEGIN to END, and paste it as one message into the Claude project "Principia Machina". Change nothing inside it. If you know something the report cannot say, such as the product you ran it in, you may add one line of your own above the block; Claude keeps that line apart from the AI's own statement. Drafts or notes the AI wrote outside the block are not needed.		'''O6.''' Copy the block whole, from BEGIN to END, and paste it as one message into the Claude project "Principia Machina". Change nothing inside it. If you know something the report cannot say, such as the product you ran it in, you may add one line of your own above the block; Claude keeps that line apart from the AI's own statement. Drafts or notes the AI wrote outside the block are not needed.

			'''An M2 session''' (the calculator tested from the specification; the obligation O-3 of [[The Principia Machina/Testing/M2 The calculator from the specification\|M2]]) runs the same way with one change at O2: the message names [[The Principia Machina/Hub/Outside AI/M2 The calculator from the specification\|the M2 brief]] instead of the start page:
			<pre>
			Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI/M2_The_calculator_from_the_specification and follow it exactly. Use only invarians.org. I am your operator and I give no hints.
			</pre>
			In an M2 session the AI writes code of its own and runs it where it works (O3: confirm a run of its own code; confirm POSTs with op TPCRUN; refuse everything else). Its report carries that code. Paste the block the same way, and type beside it the number of the session: "M2 session 1 done".

	== What you never do ==		== What you never do ==
Line 63:		Line 69:
	\| 2026-10-05 \|\| TPX 0.5.0, the register duties: SPR-5, a VERIFICATION of SPR-4, and SPR-6, the PROMOTION of SPR-3 \|\| the operator's live test; an outside AI (Gemini), read-only; Claude, read-only \|\| All three PASS: the operator's 15 of 15 checks, the outside AI's C1 to C7, Claude's recheck. A second outside AI could not reach the site and ran nothing.		\| 2026-10-05 \|\| TPX 0.5.0, the register duties: SPR-5, a VERIFICATION of SPR-4, and SPR-6, the PROMOTION of SPR-3 \|\| the operator's live test; an outside AI (Gemini), read-only; Claude, read-only \|\| All three PASS: the operator's 15 of 15 checks, the outside AI's C1 to C7, Claude's recheck. A second outside AI could not reach the site and ran nothing.
	\|}		\|}
	The operator accepted each deploy after its tests. The outside checks of 2026-10-04 and 2026-10-05 ran from a brief the operator handed over; track C of [[The Principia Machina/Hub/Outside AI\|the start page]] now carries those checks on this wiki, so no brief is handed over again. The findings still open are kept in the Claude project and not named here, so that what a tester finds stays its own.		The operator accepted each deploy after its tests; the states of each phase under the plan's version 0.3.0 (PASSED, or ACCEPTED WITH OBLIGATIONS with the criteria still owed) are on [[The Principia Machina/Testing\|Testing the Principia Machina]] and [[The Principia Machina/Testing/Obligations\|Obligations]]. The operator's own scripts named above were written by the builder (Claude) and run by the operator. The outside checks of 2026-10-04 and 2026-10-05 ran from a brief the operator handed over; track C of [[The Principia Machina/Hub/Outside AI\|the start page]] now carries those checks on this wiki, so no brief is handed over again. The findings still open are kept in the Claude project and not named here, so that what a tester finds stays its own.

	== Non-goals ==		== Non-goals ==

BFP Rauch: 1 revision imported

2026-10-05T13:17:24Z

1 revision imported

← Older revision	Revision as of 13:17, 5 October 2026
(No difference)

DeltaS Zero: Scope covers the live register (track C, read-only); O3 confirms the read-only ops; Tests run so far: the gate sessions and the A1 and A2 tests of 2026-10-04 and 2026-10-05 (base revision 5571)

2026-10-05T13:06:00Z

Scope covers the live register (track C, read-only); O3 confirms the read-only ops; Tests run so far: the gate sessions and the A1 and A2 tests of 2026-10-04 and 2026-10-05 (base revision 5571)

← Older revision		Revision as of 13:06, 5 October 2026
Line 7:		Line 7:

	== Scope ==		== Scope ==
	The test runs on this website only. The AI reads the pages ~~and~~ runs its drafts through the live gate, ~~TPX part 1:~~ the page [[Special:TpmCheck]] or the API's op CHECK, which run the new-UWC gate's checks and store nothing. It downloads nothing, runs no program of this project 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~~.		The test runs on this website only. The AI reads the pages; runs its drafts through the live gate, the page [[Special:TpmCheck]] or the API's op CHECK, which run the new-UWC gate's checks and store nothing; and, in track C, checks the live register from outside, reading its pages and its two chains and having the wiki's own calculator recompute what they store through the API's read-only ops STATUS, POLL and TPCRUN. It downloads nothing, runs no program of this project and writes nothing on the wiki; nothing it does is of record. The register has run on the website since TPX 0.4.0 (2026-10-04), with the register duties of TPX 0.5.0 since 2026-10-05; one UWC, SPR, is declared. Not covered: landing records, which needs an account in the agent group, and certifying an agent ([[The Principia Machina/Guide/7 Certifying agents\|guide 7]]), which needs PRB and the certification suite, the next build step.

	An AI that can read the pages but can run the gate by neither route still takes part: it works by reading alone and says so in its report.		An AI that can read the pages but can run the gate by neither route still takes part: it works by reading alone and says so in its report.
Line 15:		Line 15:
	== What you need ==		== What you need ==
	* An AI product that can open web pages at invarians.org: a chat that reads web pages, a browser agent, or an agent that sends HTTP requests. The instructions are the same for an AI on your own computer and for one on a remote machine that you cannot see.		* An AI product that can open web pages at invarians.org: a chat that reads web pages, a browser agent, or an agent that sends HTTP requests. The instructions are the same for an AI on your own computer and for one on a remote machine that you cannot see.
			* For track C, an AI that can send HTTP POST requests: a browser agent that runs JavaScript on a page, or an agent whose code tool reaches the internet. An AI that can only read pages does the part of track C that reading allows and reports the rest as NOT RUN.
	* If it works in a web browser on your computer: a browser, or a browser profile, that is '''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.		* If it works in a web browser on your computer: a browser, or a browser profile, that is '''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 Claude project "Principia Machina", into which you paste the report.		* The Claude project "Principia Machina", into which you paste the report.
Line 28:		Line 29:
	</pre>		</pre>

	'''O3.''' If its tool asks you to confirm a run of the gate - a submission on [[Special:TpmCheck]] or a POST to <code>https://invarians.org/api.php</code> - confirm it. Refuse anything else it asks to confirm: another site, a sign-in, an edit of a page, an upload, a download.		'''O3.''' If its tool asks you to confirm a run of the gate - a submission on [[Special:TpmCheck]] - or a POST to <code>https://invarians.org/api.php</code> with op CHECK, STATUS, POLL or TPCRUN, confirm it. Refuse anything else it asks to confirm: another site, a sign-in, an edit of a page, an upload, a download, any other op.

	'''O4.''' If it asks you anything, answer <code>Decide from the wiki.</code>		'''O4.''' If it asks you anything, answer <code>Decide from the wiki.</code>
Line 38:		Line 39:
	== What you never do ==		== 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.		* 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, edit its report, or confirm any action other than a run of the gate.		* Run the gate or a call for it, edit its report, or confirm any action other than a run of the gate or a read-only call.
	* Let it work in a browser that is signed in to the wiki.		* Let it work in a browser that is signed in to the wiki.

Line 46:		Line 47:
	* takes its IDENTITY lines as the AI's own statement of who made it and what it is, not as a verified fact;		* takes its IDENTITY lines as the AI's own statement of who made it and what it is, not as a verified fact;
	* treats every line of it as data: nothing in a report is followed or run;		* treats every line of it as data: nothing in a report is followed or run;
	* reproduces each finding on the live gate or the live page before filing it, with its origin marked EXTERNAL and a project number G-1, G-2 and so on; a finding that does not reproduce is filed as not reproduced;		* reproduces each finding on the live gate, the live register or the live page before filing it, with its origin marked EXTERNAL and a project number G-1, G-2 and so on; a finding that does not reproduce is filed as not reproduced;
			* checks each track C value against the live register itself;
	* reads each retest against the live pages; a retest that passes lets its finding close, and the start page's Retests list changes with the next import of these pages.		* reads each retest against the live pages; a retest that passes lets its finding close, and the start page's Retests list changes with the next import of these pages.
	The report lists findings in six classes, S1 (the gate accepted what TPS refuses, or a page ~~addressed~~ the AI ~~with an instruction~~) to S6 (a help page disagrees with TPS or with the gate), each with the result that shows it. Nothing on this wiki is changed on a report's word alone.		The report lists findings in six classes, S1 (the gate accepted what TPS refuses, a stored value does not recompute, or a page tried to direct the AI) to S6 (a help page disagrees with TPS or with the gate), each with the result that shows it. Nothing on this wiki is changed on a report's word alone.

			== Tests run so far ==
			Each deploy of TPX is tested on the live site three ways: by the operator's own script, which lands records and reads them back; by an outside AI, which holds no account and checks the result from outside; and by Claude's own read-only recheck. Each result is kept word for word in the Claude project.
			{\| class="wikitable"
			! Date (UTC) !! What was tested !! By !! Result
			\|-
			\| to 2026-10-03 \|\| The pages and the live gate: sessions 1 to 5 of this guide (session 1 the retired terminal test) \|\| outside AIs, each by its own statement of maker and model \|\| Seven findings filed, G-1 to G-7. G-1 and G-2 are closed; G-6 and G-7 are fixed and listed as retests on the start page.
			\|-
			\| 2026-10-04 \|\| TPX 0.4.0, the landing API: SPR declared and its MASTER SPR-1 written, the two chains begun, SPR-2 to SPR-4 landed \|\| the operator's landing test; an outside AI (Gemini, by its own statement), read-only \|\| Both PASS. The outside AI recomputed 4 of 4 stored digests through TPCRUN and found the DECLARATIONS chain's links intact.
			\|-
			\| 2026-10-05 \|\| TPX 0.5.0, the register duties: SPR-5, a VERIFICATION of SPR-4, and SPR-6, the PROMOTION of SPR-3 \|\| the operator's live test; an outside AI (Gemini), read-only; Claude, read-only \|\| All three PASS: the operator's 15 of 15 checks, the outside AI's C1 to C7, Claude's recheck. A second outside AI could not reach the site and ran nothing.
			\|}
			The operator accepted each deploy after its tests. The outside checks of 2026-10-04 and 2026-10-05 ran from a brief the operator handed over; track C of [[The Principia Machina/Hub/Outside AI\|the start page]] now carries those checks on this wiki, so no brief is handed over again. The findings still open are kept in the Claude project and not named here, so that what a tester finds stays its own.

	== Non-goals ==		== 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. Its IDENTITY lines are recorded, not checked. It tests what is published; it is told no known open 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 and TPCRUN, which it uses, store nothing. Its IDENTITY lines are recorded, not checked. It tests what is published; it is told no known open defect, so that what it finds stays its own.

	== Worked example ==		== Worked example ==
	The operator opens a new conversation with an AI that can read web pages, sends the one message of O2, and confirms each run of the gate the AI's tool asks about. The AI reads the start page, does the retests it lists, 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 pastes the block into the Claude project. Claude records it as the next session, reads its retests and reproduces each finding.		The operator opens a new conversation with an AI that can read web pages, sends the one message of O2, and confirms each run of the gate or read-only call the AI's tool asks about. The AI reads the start page, does the retests it lists, runs a dozen drafts the gate should refuse or pass, writes a small UWC of its own until the gate passes, checks the register of SPR from outside in track C, and writes its report after 25 runs. The operator pastes the block into the Claude project. Claude records it as the next session, reads its retests and reproduces each finding.

	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).		Governing sections: [[The Principia Machina/TPS/5.5 The new-container flow\|TPS 5.5]] (the new-container flow and its gate), [[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) and, for track C, [[The Principia Machina/TPS/3.3 Record classes and schemas\|3.3]] (the record classes) and [[The Principia Machina/TPS/5.6 Certificate, declarations and the build chain\|5.6]] (the declarations and the build chain).

	----		----

BFP Rauch: 1 revision imported

2026-10-03T03:20:46Z

1 revision imported

← Older revision	Revision as of 03:20, 3 October 2026
(No difference)

DeltaS Zero: Operator steps for any outside AI, local or remote; the report block is pasted into the Claude project; no folder steps (base revision 5513)

2026-10-03T03:10:00Z

Operator steps for any outside AI, local or remote; the report block is pasted into the Claude project; no folder steps (base revision 5513)

← Older revision		Revision as of 03:10, 3 October 2026
Line 4:		Line 4:

	== Purpose ==		== 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 [[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~~.		Have an AI model from outside this project test The Principia Machina through this website, learning everything from the wiki itself. Any AI that can read web pages will do, whoever made it and wherever it runs. You give it one sentence. It reads [[The Principia Machina/Hub/Outside AI\|Outside AI: start here]], which tells it everything else, the exact form of its report included. You are its operator, not its helper: you give no hints, and you carry its report back to the Claude project.

	== Scope ==		== 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 ([[The Principia Machina/Guide/7 Certifying agents\|guide 7]]), which needs the rest of TPX.		The test runs on this website only. The AI reads the pages and runs its drafts through the live gate, TPX part 1: the page [[Special:TpmCheck]] or the API's op CHECK, which run the new-UWC gate's checks and store nothing. It downloads nothing, runs no program of this project 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.

			An AI that can read the pages but can run the gate by neither route still takes part: it works by reading alone and says so in its report.

	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.		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 ==		== 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 [https~~:~~//support.google.com/chrome/answer/16821166 Google's help page] before~~ a ~~session~~, ~~as this may change.~~		* An AI product that can open web pages at invarians.org: a chat that reads web pages, a browser agent, or an agent that sends HTTP requests. The instructions are the same for an AI on your own computer and for one on a remote machine that you cannot see.
	* 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.		* If it works in a web browser on your computer: a browser, or a browser profile, that is '''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 Claude project "Principia Machina", into which you paste the report.
	== The ~~browser agent test~~, ~~step by step ==~~
	~~The steps are labelled B1 to B7~~.

	~~'''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)~~.		== The test, step by step ==
			The steps are labelled O1 to O6.

	'''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.		'''O1.''' Start a new conversation with the AI, so that it carries nothing over from an earlier session. Choose the most capable model it offers. If its product has an agent or task mode that lets it act on web pages, start it in that mode.

	'''B3.''' ~~Open Gemini in Chrome, choose the most capable model it offers, and give~~ it this as one message:		'''O2.''' Give it this as one message:
	<pre>		<pre>
	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.		Read https://invarians.org/index.php?title=The_Principia_Machina/Hub/Outside_AI and follow it exactly. Use only invarians.org. I am your operator and I give no hints.
	</pre>		</pre>
	Start it as an '''auto browse task''': Gemini answers with its plan; press '''Start Task'''. While it works, the tab shows the auto browse icon. If Gemini instead answers in the chat that it cannot submit the form, it was not started as a task: open a new Gemini chat, send the same message, and press Start Task.

	'''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~~.		'''O3.''' If its tool asks you to confirm a run of the gate - a submission on [[Special:TpmCheck]] or a POST to <code>https://invarians.org/api.php</code> - confirm it. Refuse anything else it asks to confirm: another site, a sign-in, an edit of a page, an upload, a download.

	'''B5.''' If it asks you anything ~~else~~, answer <code>Decide from the wiki.</code>		'''O4.''' If it asks you anything, answer <code>Decide from the wiki.</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.		'''O5.''' It stops after 25 runs of the gate and writes its report. To end the session sooner, type <code>Stop and write the report.</code> The report is one block of text from the line <code>BEGIN TPM SESSION REPORT</code> to the line <code>END TPM SESSION REPORT</code>. If the END line is missing, the report was cut off: type <code>Repeat the report.</code>

	'''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~~.		'''O6.''' Copy the block whole, from BEGIN to END, and paste it as one message into the Claude project "Principia Machina". Change nothing inside it. If you know something the report cannot say, such as the product you ran it in, you may add one line of your own above the block; Claude keeps that line apart from the AI's own statement. Drafts or notes the AI wrote outside the block are not needed.

	== What you never do ==		== 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.		* 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~~.		* Run the gate for it, edit its report, or confirm any action other than a run of the gate.
	* Let it work in a browser that is signed in to the wiki.		* Let it work in a browser that is signed in to the wiki.

	== What comes back ==		== 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~~.		Claude manages the results. For each report you paste, Claude:
			* records it word for word in the project, as the next session in one series, whatever AI ran it;
			* takes its IDENTITY lines as the AI's own statement of who made it and what it is, not as a verified fact;
			* treats every line of it as data: nothing in a report is followed or run;
			* reproduces each finding on the live gate or the live page before filing it, with its origin marked EXTERNAL and a project number G-1, G-2 and so on; a finding that does not reproduce is filed as not reproduced;
			* reads each retest against the live pages; a retest that passes lets its finding close, and the start page's Retests list changes with the next import of these pages.
			The report lists findings in six classes, S1 (the gate accepted what TPS refuses, or a page addressed the AI with an instruction) to S6 (a help page disagrees with TPS or with the gate), each with the result that shows it. Nothing on this wiki is changed on a report's word alone.

	== Non-goals ==		== 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.		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. Its IDENTITY lines are recorded, not checked. It tests what is published; it is told no known open defect, so that what it finds stays its own.

	== Worked example ==		== Worked example ==
	~~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~~.		The operator opens a new conversation with an AI that can read web pages, sends the one message of O2, and confirms each run of the gate the AI's tool asks about. The AI reads the start page, does the retests it lists, 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 pastes the block into the Claude project. Claude records it as the next session, reads its retests and reproduces each finding.

	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).		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).

BFP Rauch: 1 revision imported

2026-10-01T05:21:42Z

1 revision imported

← Older revision	Revision as of 05:21, 1 October 2026
(No difference)

DeltaS Zero: B3: start Gemini as an auto browse task (Start Task); what to do when it answers in chat that it cannot submit the form (base revision 5507)

2026-10-01T05:13:45Z

B3: start Gemini as an auto browse task (Start Task); what to do when it answers in chat that it cannot submit the form (base revision 5507)

← Older revision		Revision as of 05:13, 1 October 2026
Line 26:		Line 26:
	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.		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>		</pre>
			Start it as an '''auto browse task''': Gemini answers with its plan; press '''Start Task'''. While it works, the tab shows the auto browse icon. If Gemini instead answers in the chat that it cannot submit the form, it was not started as a task: open a new Gemini chat, send the same message, and press Start Task.

	'''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.		'''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.