Inside OpenAI's Symphony experiment. Three engineers. Five months. One million lines of production code. Zero human authorship. Zero pre-merge review.
1M+Lines of Code
1BTokens / Day
<60sBuild Loop
The Old Model
Humans write. Humans review. Humans merge.
Code generation is the bottleneck. Every PR needs human approval. Agents are "assistants" that propose diffs for humans to accept or reject.
SequentialReview-Gated
What Is A Dark Factory
Agents write, review, and merge. Humans run capability analysis.
Ryan Lopopolo's team at OpenAI Frontier ran a five-month experiment. Three engineers, one empty repo, one rule: nobody writes code by hand. They built an Elixir orchestrator called Symphony and shipped 1M+ lines of production code across 1,500+ PRs, all autonomously merged. Humans did not review PRs. They watched patterns and fixed the harness.
SymphonyElixir OrchestratorPost-Merge Review
Mental Model
A factory with the lights off
Manufacturing's "dark factory" runs without humans on the floor. Machines do the work. Humans design the process. The software version: agents own the keyboard, humans own the specification.
Specs > Source
60-Second Build
Build speed is clock speed
Rule: builds complete in under 60 seconds, always. Every idle minute across 20 parallel agents is a minute of burned tokens.
Make→Bazel→Turbo→NX
500+ NPM packages
Post-Merge Review
No human PR gate
Code merges if CI passes. Humans sample output after the fact, looking for patterns, not individual defects. Agent-reviewing-agent runs P0/P1/P2 triage.
P0 BlockP1 FlagP2 Inform
Economics
Token billionaire math
~1 billion tokens/day consumed. Daily spend is real, but still cheaper than the team it would otherwise take.
$2-3K / day$60-90K / mo3-7 engineers
PR Velocity
The model upgrade compounds
Humans did not work faster. The models did. Each generation turned previously hard tasks into routine ones.
L1PolicyHard guardrails. CI must pass. Security rules are non-negotiable.
The Role Shift
From code review to capability analysis
Before
After
Review every PR line by line
Sample outputs for patterns
"Is this code correct?"
"Why did the agent fail here?"
Gate merges sequentially
Merge on green CI, observe
Fix bugs in the PR
Fix capability gaps in the harness
Bottleneck: human attention
Bottleneck: specification quality
The new question: not "did the agent write the right code" but "does the harness give the agent everything it needs to write the right code."
Ghost Libraries
Distribute specs, not source code
Ship a specification. The agent reads it and reproduces the library locally, tailored to your codebase. No version conflicts. No shared source. No supply chain attacks.
SpeculativeNot hypothetical
Still Human Territory
What agents cannot do yet
Zero-to-one product ideation
Cross-cutting architectural refactors
Direction-setting outside the spec
Agents follow patterns. They do not invent them.
The Core Insight
The only fundamentally scarce thing is synchronous human attention. Models are trivially parallelizable.
— Ryan Lopopolo, OpenAI Frontier Product Exploration
Translation: if you can run 20 agents in parallel and each produces working code, the bottleneck is not authorship. It is the quality of the specifications and constraints they receive. That is harness engineering.
What To Adopt Today · Any Team Size
Five dark-factory practices that work at solo-dev scale too
Practice
Why It Matters
Smallest Version
1. Measure the build loop
Build time is the clock speed of every agent you run.
Fix anything over 2 minutes.
2. Encode taste as text
Agents consume CLAUDE.md, specs, and quality scores as context.
Turn tribal knowledge into markdown.
3. Consider post-merge for low-risk
Not every PR needs a human gate. Observability replaces review.
Auto-merge on green CI for docs and tests.
4. Treat code as disposable
If the spec is good, regenerating is cheaper than defending.
Throw away, do not merge-conflict-resolve.
5. Invest in agent observability
You cannot fix capability gaps you cannot see.
Log every agent action with structured traces.
Source: Latent Space / Ryan Lopopolo · OpenAI Frontier · sangampandey.infoDark Factory