Adam Noonan
mad scientist working on calibrated uncertainty — models that know what they don’t know
Research
Calibration is a property of outputs: when you say 85%, does 85% happen? i work on earning that property honestly, auditing that it holds, and acting on it.
Preprint. Split conformal’s coverage law assumes i.i.d. calibration data. Generalises it to correlated families — beam branches, resampled particles — and shows the design effect this literature reports is the wrong quantity, not just an imprecise one.
Preprint, near submission. The consumer picks the coverage level; the oracle returns the band that empirically delivers it, with a receipt anyone can re-derive from public data. 12 years of weekend and overnight gaps. Shipped as soothsayer.
In draft. When calibration-set membership depends on the score being calibrated, the correction weighted conformal applies to covariate shift doesn’t exist. What replaces it is a sharp interval.
Fine-tuning a model to carry a person’s idiolect while it learns none of their private facts — measured with extraction canaries on one side and authorship embeddings on the other.
Models represent internally that their evidence doesn’t cover a question, and answer anyway. Reading that signal so every answer is grounded or escalated, under an error budget you set instead of hope for.
Writings
Occasional posts on what i’m building and why.
A joke ASR benchmark for fast rap — and the discovery that the models had memorized the answers.
Ditching a dictation subscription for Hex + Yapper — voice in, voice out, nothing leaves the machine.
About
Director of Data & AI at Digital Locke — individualized digital twins, and the calibration research that keeps one honest.
Technical founder with 2x profitable exits.
Previously solutions architecture at Celonis/Lenses.io and NetApp.
Taught AI engineering at Immune Technology Institute, Madrid.
Into meditation, centering prayer, kettlebells, ML & quant research, hiking, camping & SUP.
Walked the Camino de Santiago. Speaks English and Spanish.
Background
Education
UT Austin MS · ECU BBA
Side Projects
Experiments i’m building in public.
Calibration-transparent fair-value oracle for tokenized RWAs on Solana, with per-regime audit receipts.
Manifest-driven Rust data platform feeding soothsayer — versioned, deduped parquet for crypto, oracle, and market-data research.
Personal AI ops center — realtime voice PWA over WebRTC, async research workers, and a synced Obsidian vault on Convex.
Elixir + Kafka durable coordination runtime for self-healing infrastructure swarms, with replayable event fabric and bounded remediation.
Open-source autonomous docking stack for single-engine sailboats — simulation, control, and retrofit hardware design.
Opinionated operating playbook and bootstrapper for new software products — phase-gated defaults for repos, CI/CD, ops, and agent harnesses.
Open Source
Codebases i maintain & put out in the open — some are libraries i needed and didn’t exist, others are forks i carry forward with enhanced/additional features.
Embeddable, transactional key-value storage engine in Rust — maintained fork of fjall-rs/fjall with deadlock fixes, custom sequence generators, and zstd compression.
Log-structured merge-tree engine in Rust — fork of fjall-rs/lsm-tree with zstd dictionary compression, batch multi-get, zero-copy reads, and intra-L0 compaction.
Pure-Rust, no-RPC swap math for Raydium’s concentrated-liquidity AMM — the missing Solana analogue of uniswap_v3_math.
Pure-Rust, no-RPC swap math for Meteora’s bin-based DLMM — closing the last math-crate gap among Solana’s major liquidity models.
Elixir SDK for Restate’s durable execution runtime, targeting protocol V3.