subvert
Generate subtitles, summaries, and chapters from videos in seconds
Runssource: GitHubhomepagePHPMITcommit a23c47df0fa1
PHP, MIT licensed. The project labels itself: chatgpt, openai, transcription, translation, video editing and whisper.
subvert runs. An Argusic agent installed it in 7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The project builds with all Composer and npm dependencies installed, the test suite passes 4 tests with 9 assertions covering the full processing pipeline and HTTP routes, and the Laravel development server starts and serves HTTP 200 on the root endpoint.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- OpenAI Client/Audio/Chat classes are final preventing mocking5 minutes
- Mock OpenAI server SSL certificate error with real client3 minutes
- PHP not found in container2 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- php vendor/bin/phpunit exited 0, 4 tests 9 assertions passed; curl -s -o /dev/null -w %{http_code} localhost:8080 returned 200
- Model tokens used
- 275,530
- Exact commit tested
- a23c47df0fa1
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Full verification:** The test suite (4 tests, 9 assertions) passes with mocked Argusic responses,… 2026-11-21T13:31:17.868926Z ERROR codex_core::session: failed to record rollout items: thread 01a1f… tokens used 275,530 All good — tests pass and server responds on port 8080. Let me compile the final report. **Errors encountered:** 1. PHP wasn't installed in the container — fixed by downloading a static PHP 8.2.32 binary and Comp… 2. Composer was installed but `php` wasn't in PATH — fixed by adding `~/bin` to PATH 3. `queue:work` / `queue:connection` needed `QUEUE_CONNECTION=sync` for in-process jobs — set in `.… 4. Mock Argusic server originally needed SSL — stood up an HTTPS mock with a self-signed cert, but … 5. Argusic's `Client`, `Audio`, and `Chat` classes are all `final` — couldn't use Mockery or PHPUni… **Full verification:** The test suite (4 tests, 9 assertions) passes with mocked Argusic responses,…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 7 minutes to install, slower than the median of the 4 comparable projects Argusic has measured.
Of the 5 chatgpt projects Argusic has installed and timed, subvert was the 4th fastest to reach a running state, and 3 of 5 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 7 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.06 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.72 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/subvert)Questions
- Does subvert run?
- Yes. subvert runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test subvert?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a23c47df0fa1. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test subvert?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does subvert take to install?
- 7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does subvert need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing subvert?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does subvert compare with the alternatives?
- Of the 5 chatgpt projects Argusic has installed and timed, subvert was the 4th fastest to reach a running state, and 3 of 5 reached one at all.
- Where is the evidence for subvert?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.