i do engineering

PROJECTS

dún firmware

Nov 2026

Firmware that turns the dún earbud into an ear-fatigue tracker: one press checks your ear’s own echoes against a quiet-day baseline in 15 to 20 seconds. On 300 simulated ears it never called a false dip and caught 92% of 8 dB drops. Not yet run on hardware.

Zephyr RTOS
nRF52840
Embedded C
Audio DSP

sotto

Sep 2026

Slower, calmer synthetic speech without slowing the words: render each sentence once at natural speed, then lengthen only the silences the model already made. Every register hits its words-per-second target at speed 1.00.

Python
FastAPI
Kokoro TTS
Self-hosted

mote

Aug 2026

A transformer inference engine in plain C with no libraries underneath, small enough to run a real chat model offline on a phone in under 90 KB of WebAssembly. Along the way: why a smaller quantization error can make the model worse.

Embedded C
Transformer
Quantization
Open Source

ràdá

Aug 2026

A pocket 60.5 GHz radar that measures movement in micrometres by reading the phase of the returning wave, enough to count a heartbeat through still air or recover sound from a surface it never touches.

60.5 GHz radar
nRF52840
Embedded C
KiCad

àyò

Jul 2026

A research platform for systematic trading in which Claude designs strategies but never writes code. Each strategy is a frozen, hashed artifact run by a deterministic engine, so the results are reproducible even though the author is not, and every idea has to clear an out-of-sample gate that tightens as more are tried.

Python
Claude
Alpaca
pandas

dimeji

Jul 2026

A typed graph for modelling an emotional history honestly. Every claim has to declare how it is known, hypotheses are never promoted to facts, and contradictions stay open instead of being resolved.

Framework
React Flow
TypeScript
Epistemics

vibe

Jul 2026

A Claude Code skill that holds the assistant in one persona for a whole session while the code, comments and commits stay clean. One Markdown file, open source.

Claude Code
Skill
Open Source
Markdown

the scribe

LIVE SITE ↗Jun 2026

A ghostwriting studio for ministry authors where the AI editor cannot invent: every margin note must quote the manuscript verbatim, and a failed check goes back to the model so it corrects itself in the same loop.

TypeScript
Next.js
OpenAI
Postgres
Prisma

RESEARCH & PAPERS

i use agents heavily, so i hold this work to the same test as everything else here: every result was designed and checked by me.

The Verification Premium

When does generative AI narrow the gap between workers, and when does it widen it? If people pick the best of several AI drafts by a judgment that gets sharper with skill, AI widens gaps exactly when a verification premium exceeds one, and only over a bounded range of skill. I took the model to 12.3 million player-games on Lichess around Stockfish 12, and neither of its predictions survived the checks I wrote down in advance.

PUBLISHED: Nov 14, 2026Preprint

Who Are You?

How well do a few plain sentences about how someone listens to music, naming no artist or track, pick that person out from everyone else? Over three pre-registered rounds on ListenBrainz listeners, three sentences chosen together found the right person in a lineup of five 68.8% of the time, short of my 75% bar and 7.2 points ahead of the earlier rule on the same people.

PUBLISHED: Nov 6, 2026Preprint

Faster Than They Can Be Checked

Terence Tao predicted that AI-generated proofs would accumulate faster than they could be verified. This paper measures whether they do. Every public proof claim on erdosproblems.com from July to September 2026, 251 of them and 97% made with AI, was traced to see whether anyone ever checked it. Of the 224 on problems still open, 48% drew any comment, 19% reached any verdict and 4% were accepted by the site's moderators. Verdicts arrive within a day or not at all: after 60 days, 82% of claims still have none. Attaching a Lean proof made no difference, 19 people delivered every verdict, and one complete, formally verified proof was dismissed with a mistaken "already solved" that nobody corrected.

PUBLISHED: Sep 25, 2026Preprint

What Does a Change Detector Find Where Nothing Changed?

You cannot label the earth, so nobody measures how often a satellite change detector invents change. This paper runs the pipeline over ground another community has already certified as invariant, where every detection is a false alarm by construction. The field has had no way to do this, because on an empty ground truth F1 and IoU are undefined for a perfect result and zero for every imperfect one, and so cannot tell one false positive from five hundred thousand. On the six CEOS-endorsed desert sites, a threshold chosen from the data reports a median 21.41% of certified-stable ground as changed, against 0.04% with an absolute floor. Otsu calls 39% of an empty scene changed, eases only to 27% as a real signal strengthens, then falls 26.97 points across a single 0.25-sigma step, so behaviour on scenes containing change says nothing about scenes without it. Seven defects surfaced, five of them invisible in the outputs, including a pipeline that reports thirty times less change once a large real structure appears.

PUBLISHED: Sep 23, 2026Preprint

We Are All Doppelgängers of Ourselves

The doppelgänger of folklore terrifies because it is a copy of you that is not you. But the body is a pattern rebuilt from new matter, memory is re-saved each time it is opened, and everyone who knows you carries a version of you you will never meet. From Goethe's consoling double and the brain's misfiled selves to Yoruba twin figures and a chatbot built from a dead man's messages, an essay on why there was never an original, and what the copies owe each other.

PUBLISHED: Sep 25, 2026Essay

How Much of a Small Chip Actually Computes?

A synthesized netlist is pure logic, but a layout a foundry could build also carries the cells that let it survive fabrication: antenna diodes, well taps, timing buffers, fill. I took one signed int8 multiply-accumulate through the open Sky130 flow at lane counts from 1 to 64 and decomposed every placed layout. The arithmetic share of the cells falls from 59 percent to 48, below half, because the overhead grows faster than the logic and its parts scale with wiring and die area instead of gate count.

PUBLISHED: Aug 29, 2026Technical note

How Many Things Can You Finish? Two Effort Thresholds and Optimal Attempt Counts

An attempt needs two separate efforts: one to make it work and one to put it in front of anyone. The optimal number of simultaneous attempts depends on their sum, but the heuristic builders actually use depends on build cost alone. Agent assistance collapsed build cost and left shipping cost untouched, so the two prescriptions have diverged. Simulation plus a 48-repository archive where every stalled project is stalled at a step building cannot resolve.

PUBLISHED: Aug 21, 2026Preprint

How Many Strategies Did You Really Try? Effective Trial Counts for LLM-Proposed Backtests

When a language model proposes trading strategies, selection-bias corrections need to know how many independent trials were made, and the raw number of proposals overstates it. I borrow the effective-number-of-tests estimator from statistical genetics to get an effective trial count, M_eff. On the live ÀYÒ pipeline its size depends on the prompting protocol. Diverse prompts give mildly redundant proposals (M_eff about 0.72 to 0.76 of the count, moving the acceptance bar by about 0.07 Sharpe). Drawing repeatedly from one narrow angle collapses eight proposals to roughly two effective trials, raises the bar by about 0.33 Sharpe and changes real deployment decisions. Three replicates per protocol separate the two regimes without overlap.

PUBLISHED: Jul 29, 2026System report

Trials-Adjusted Out-of-Sample Gating for LLM-Proposed Trading Strategies

A validation gate for strategies proposed by a language model. Strategies arrive as frozen, content-hashed data artifacts, and a deterministic verifier trades only what survives walk-forward out-of-sample testing, a trials-adjusted acceptance bar and robustness sweeps. Run on scripted strategies over real U.S. equity data, it turned an in-sample Sharpe of 3.07 into a −4.90 rejection and showed a +0.13 out-of-sample edge to be a fluke that beat the benchmark in 0 of 12 parameter settings. It deployed nothing, which is what one should expect on efficient markets.

PUBLISHED: Jul 20, 2026System report

Cortex: A Governed Long-Term Memory Engine for LLM Agents

A memory engine for LLM agents, available as a REST API and an MCP server, that puts five governance behaviors in one running system: consolidation, salience-scaled forgetting, contradiction supersession, per-tenant isolation and an exportable audit trail. It is evaluated on those behaviors, which recall benchmarks do not measure.

PUBLISHED: Jul 19, 2026System report

EXPERIMENTS

curiosity projects. some worked, some didn't, all of them taught me something.

dún

Nov 2026

An earbud built to hear the faint sound a healthy ear makes back after a click, the echo newborn hearing screeners listen for. A rebuild of a published design on my own board, with a plastic tube as the first test. Designed, not yet built.

Otoacoustic emissions
nRF52840
Audio DSP
KiCad

rondo

Nov 2026

A small neural net reads every touch of a Barcelona move and says how likely it is to end in a goal, replayed live on the 5-0 against Real Madrid. Xavi’s opener sits under 5% for almost sixty touches, then one Iniesta ball takes it to 32%.

Neural networks
Python
NumPy
StatsBomb

gbó

Nov 2026

A model that watches an F1 stint the way a pit wall does and calls when it falls off, replayed against all 698 stops of 2025. Ten laps out it forecasts pace to within half a second on tracks it has never seen. Whether teams stop too late flips with one number lap times cannot give you: the fuel.

Machine learning
Python
scikit-learn
FastF1 timing

rán

Nov 2026

Every 2025 qualifying, its fastest sectors stitched into a lap nobody drove and run as a ghost against pole. Honestly done it is a median 0.16 s quicker; cut finer from telemetry it claims 1.7 s, which is the ruler, not the drivers. Five of Verstappen’s eight poles were beaten in pieces.

Telemetry
Signal processing
Python
NumPy

aas

Nov 2026

Show me your digital world and I will tell you who you are. Personality read from what people write, carry, wear and play, scored on people the models never saw. Writing reads thinking against feeling at AUC 0.83 once the type words are gone; Steam profiles say nothing. Three statements from half of a listener’s history pick them out of five 67.5% of the time on 333 new listeners.

Python
Statistics
Personality

vouch

hackathonBLI Legal Tech, Oct 2026Oct 2026

Checks every figure an AI cites against the SEC filing it quotes. A doctored quote with one number changed is still 99.3% similar to the filing, so a fuzzy match passes it; the check here demands every figure exactly.

Solidity
Chainlink CRE
Python
SEC EDGAR

kickflip

Oct 2026

Tesla rolled a Roadster over in mid-air on compressed air. An engine concept for it, drawn and sized on paper: ten nozzles, one trunk, a regulator per group. Then the proof that it closes: the tank holds about one second of full thrust, and one stunt drains it.

Mechanical engineering
Thermodynamics
Python
CoolProp

mpemba

Oct 2026

Does hot water freeze before cold? Sometimes, by chance, and never more than half the time unless the containers are unfair or the water remembers being hot. A race you can run in the browser, and a reading of sixty years of experiments against that ceiling.

Physics
Probability
Python
NumPy

thrum

Oct 2026

A string lab in the terminal, drawn in characters and played with your hands: pinch the air to make a particle, throw it, stretch strings between your hands. Gravity is real, scaled from the size of your palm.

MediaPipe
Python
Terminal
NumPy synth

unsaid

hackathonAssemblyAI Voice Agent, Sep 2026Sep 2026

A voice agent that hears what was almost said: turns cut off or abandoned, which every transcript records as finished. When somebody loses the floor it waits for real silence and hands it back. Precision 0.74, recall 0.48 on 200 hand-labelled turns.

Python
AssemblyAI
WebSockets
AMI corpus

ika

Sep 2026

A shadowboxing coach that names your habit a beat before you repeat it, reading punches and guard from body landmarks alone. Scored on fifteen public rounds held out by person.

MediaPipe
PyTorch
Python
On-device

node

Aug 2026

A local, always-on intelligence and the machine specified to hold it. Most requests never reach a large model, but every tier has to stay resident at once, which means 384 GB of VRAM, specified from part numbers with the power ledger written down.

Threadripper PRO
384 GB VRAM
Local inference
Hardware

mak

Aug 2026

The multiply-accumulate at the heart of mote, carried from Verilog down to a SkyWater 130nm silicon layout: eight int8 lanes, verified against a software reference, then placed and routed to the GDSII file a foundry is handed.

Verilog · RTL
Sky130
OpenLane
Silicon

jùwọ̀n

Aug 2026

How do you measure a satellite change detector's error rate without labelling anything? Point it at ground that has not moved in a century. That test found four real bugs and took false change from 7% and 39% down to 0.23% and 1.99%.

Sentinel-2 · SAR
NumPy
Python
Calibration