Source Authorship Forensics

Triumviratus — human-written, or AI-generated?

A source-level read of Tors3/Triumviratus v4.2 — the most nuanced case in the series.

Author Francesco Torsello Language C++ Scope ~9,500 LoC · 116 commits over ~2.5 years Eval NNUE (Stockfish-derived; own net from v4.2) Analyzed 2026-07-10 Method source read + git history + release notes Stockfish similarity Derived →
Verdict · Human-Written (expert; AI-assisted)

Human-authored and expertly developed — with AI as a disclosed tool, not the author.

Triumviratus is the work of a serious engine developer applying rigorous empirical method over two and a half years: SPRT-verified search changes, multi-thousand-iteration SPSA parameter co-tunes, A/B NPS tests, anchored Elo gauntlets — "nothing is merged on feel." That is a human development loop of a high order, documented commit by commit.

The repository does contain a CLAUDE.md — the developer uses the Claude Code assistant (with a code-graph navigation tool) as part of their workflow. But here AI is a tool inside an expert's years-long process, not the origin of the code. Two honest caveats sit beside the verdict: the work is AI-assisted, and the engine is a Stockfish-derived lineage (see below).

Confidence: High on human authorship; the AI-assist and Stockfish-derivation are noted for full transparency.

Part of a series applying the same lens: the AI-pasted Luna, the agent-built Owen, and the human-written rudim, Crustik, Catalyst, tomitankChess and Ember.  See the index →

1The development method is unmistakably human — and rigorous

The release notes read like an experimental logbook. Each gain is measured, with confidence intervals.

EvidenceWhat it shows
116 commits over ~2.5 years (Jan 2024 → Jun 2026), one named authorSustained, long-horizon personal development
"Large SPSA co-tune (~10k iterations, 18 parameters)"; "mega-SPSA (55 parameters)"Serious automated parameter tuning on real hardware/cloud
"SPRT-verified vs 4.0 … +35.0 ± 17.9 Elo at 20+0.2 (LOS ~100%)"Statistically-disciplined testing, not vibes
clang-PGO release builds; interleaved A/B NPS tests; bench fingerprintsPerformance engineering at a competitive level
Reverts, version-banner fixes, dead-code cleanupsAn organic, human, sometimes-messy workflow
Why this settles the AI-vs-human question: a language model does not run a 10,000-iteration SPSA tune on Google Cloud, gate a change behind an SPRT at 20+0.2, and record "+35.0 ± 17.9 Elo (LOS ~100%)" across a 2.5-year history. This is a person doing empirical engine science.

2The Claude question — the opposite of Owen

Two engines in this series have Claude in the repository. They are opposite cases.

// source/CLAUDE.md — instructions for the Claude Code assistant
"This project has a knowledge graph at graphify-out/ ...
 For codebase questions, first run `graphify query ""` ...
 After modifying code, run `graphify update .` to keep the graph current."
Tool, not author. This CLAUDE.md configures an AI assistant to navigate a large existing codebase (via a code-graph tool) — it presupposes a substantial, already-built engine to reason about. Contrast Owen, where a committed claude dependency sat beside an entire engine delivered in a single 11,000-line commit. Same assistant; here it augments an expert's long-running project, there it produced the project. AI assistance of this kind is now normal and legitimate; it does not make the work machine-authored.

3Compare & contrast with Stockfish — a close relative

More than resembling Stockfish, Triumviratus is openly built on parts of it.

Shared / derived from Stockfish
Ships Stockfish's NNUE code (source/sfnnue/) and used SF's net nn-b1a57edbea57 as default until v4.2
"SF-style" LMP and depth-pruning blocks; ProbCut; singular extensions
Lazy SMP with a shared transposition table
SPRT/SPSA testing culture (the Fishtest methodology)
Where it is its own work
Original single-board NNUE bridge feeding the net from native bitboards
Bespoke 24-byte TT with 16-bit static eval; staged MovePicker; correction history
Its own large SPSA-tuned search vector (the real source of its Elo)
v4.2 "first own-lineage": begins shipping its own rubicon network

The Stockfish derivation is a question of originality, not authorship — and the developer discloses it openly (SF-net default, GPLv3 source-link notes). It remains substantial, expert human work layered on a GPL lineage.

Bottom line

Triumviratus is human-written — and among the most methodologically serious engines in this series — developed by one expert over two and a half years of SPRT- and SPSA-disciplined work. It is also the series' clearest example of legitimate AI-assisted development: a CLAUDE.md shows an AI assistant in the loop, but as a tool augmenting a person's long-running project, the polar opposite of an agent-generated dump. Two fair caveats travel with the verdict — the work is AI-assisted, and the engine is a Stockfish-derived lineage only now growing its own net — but neither moves it off the human side of the line.