This experiment shows how an AI reconstructed the local engine of OpenAI's Codex from its installed files, observable requests, and targeted binary inspection. It also demonstrates why hidden behavioral tests and exact constants—not superficial similarity—were essential to raising the clone from 75% to about 98% fidelity.
SoftsWebWatchTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from SoftsWeb; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to reverse-engineer an open-source program by combining black-box observation, precommitted behavioral tests, and narrowly targeted inspection of its installed binary.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
1,527 cleaned transcript words reviewed across 450 timed caption segments.
Thesis
I Used REA to Clone OpenAI's Codex teaches a practical coding-agent workflow move: This experiment shows how an AI reconstructed the local engine of OpenAI's Codex from its installed files, observable requests, and targeted binary inspection. It also demonstrates why hidden behavioral tests and exact constants—not superficial similarity—were essential to raising the clone from 75% to about 98% fidelity.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:00
Define the boundary
“This is OpenAI's Codex, the coding agent that got downloaded more than 24 million times just last week. And this one next to it is a copy that an AI built using Ria, the open-source reverse engineering tool...”
Codex consists of a server-hosted AI model and a local program, and only the local program was copied. The experiment deliberately used the Apache-licensed Codex rather than products whose terms forbid reverse engineering, while judging success by whether the clone's behavior could be distinguished from the original. Write a two-column scope for a reverse-engineering exercise: what is legally and technically available to inspect, and what remains outside the boundary.
3:05
Test before cloning
“showed how Codex reports results back with a wall time, an exit code, and the output, where one wrong character gives the copy away. Then, I tried to break it on purpose with tools that don't exist and...”
A fake AI server exposed Codex's long system instructions, command-result schema, exact error messages, output truncation, and request details. The creator froze a hidden test first, then ran the original and clone through identical scripted tasks so that every lost point represented a measurable behavioral difference. Design three hidden black-box checks for a command-line program, including one normal response, one malformed tool call, and one large-output truncation case.
5:10
Inspect smaller slices
“environment variables, headers, and server errors. The copy dropped to 75% and every known model failed because the real program sends different instructions and tools for each model name. That knowledge isn't something you can see with a...”
The first clone reached 99% on an easy test but fell to 75% when a harder suite covered model-specific behavior and other admitted gaps. When Ghidra repeatedly timed out on the 294 MB program, extracting the constants section revealed the hidden model catalog, sandbox warning, and JSON event names needed to reach 98.5% on the hard test. List the gaps that black-box observation cannot resolve, then identify the smallest binary region or constant table that could answer one of them.
01
Inspect context
Start with this video's job: This experiment shows how an AI reconstructed the local engine of OpenAI's Codex from its installed files, observable requests, and targeted binary inspection. It also demonstrates why hidden behavioral tests and exact constants—not superficial similarity—were essential to raising the clone from 75% to about 98% fidelity. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “This is OpenAI's Codex, the coding agent that got downloaded more than 24 million times just last week. And this one next to it is a copy that an AI built using Ria, the open-source reverse engineering tool...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:05, where the video says: “showed how Codex reports results back with a wall time, an exit code, and the output, where one wrong character gives the copy away. Then, I tried to break it on purpose with tools that don't exist and...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Verify behavior
Use "Verify behavior" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This experiment shows how an AI reconstructed the local engine of OpenAI's Codex from its installed files, observable requests, and targeted binary inspection. It also demonstrates why hidden behavioral tests and exact constants—not superficial similarity—were essential to raising the clone from 75% to about 98% fidelity.
02
Explain the practical stakes without hype: New playlist item from SoftsWeb; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: I Used REA to Clone OpenAI's Codex
- URL: https://www.youtube.com/watch?v=pX8Sy8Rd44U
- Topic: Codex + Claude Workflows
- My current learning frame: Choose a small open-source CLI, record its behavior through a fake dependency, create a hidden comparison suite, and use targeted file inspection only for differences that observation cannot explain.
- Why this matters: New playlist item from SoftsWeb; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "This is OpenAI's Codex, the coding agent that got downloaded more than 24 million times just last week. And this one next to it is a copy that an AI built using Ria, the open-source reverse engineering tool..."
- 1:32 / Evidence 2: "Here's the rule of the game. If you can't tell the two programs apart, the copy wins. The AI only gets the installed files, and the test stays hidden from it until the very end. So, let's start..."
- 3:05 / Evidence 3: "showed how Codex reports results back with a wall time, an exit code, and the output, where one wrong character gives the copy away. Then, I tried to break it on purpose with tools that don't exist and..."
- 5:10 / Evidence 4: "environment variables, headers, and server errors. The copy dropped to 75% and every known model failed because the real program sends different instructions and tools for each model name. That knowledge isn't something you can see with a..."
- 6:50 / Evidence 5: "from 75% to 98.5% and across both tests, it passed 416 of 422 checks. On the hard test, every one of the 11 model names now behaves exactly like the real Codex. The copy still loses a few..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "I Used REA to Clone OpenAI's Codex", not a generic Codex + Claude Workflows essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
Which part of Codex could the experiment copy, and why was that target acceptable?
Why was the hidden test written before the AI began rebuilding Codex?
How did the AI recover useful constants after full Ghidra analysis repeatedly timed out?
Source shelf
Use the video as a doorway, then verify with primary sources.
