The first half of my twenties was signal processing, fibre optics, microcontrollers, and research at Yale-NUS, which included co-authoring Oyente (ACM CCS 2016), a symbolic-execution + SMT-based analyzer for financial contracts that uncovered $62M+ in exploitable contracts at the time (the code later joined the Ethereum Foundation; hear me present it nervously to a large crowd at ACM CCS 2016 in Vienna). Also a paper on sensory substitution at ACM ISS 2017, a 3-country patent on automated thermal fire detection, the cover of Chemistry-Methods for a baseline-correction algorithm used in DNA sequencing and X-ray crystallography, and reverse-engineering continuous glucose monitoring systems.

The second half was spent as the CTO of a YC / Flexport / Rebel-backed startup called Greywing, where we worked with the largest ship owners in the world to optimize routes, fuel, flights, across far too many dimensions and data silos to count. During Covid, our software played a role in getting stranded seafarers home; in 2021 the exact same algorithms would help me find a way home from Singapore after losing my dad during Delta.

A handful of those builds became canonical patterns later. SeaGPT, our maritime AI agent at Greywing, shipped streaming, parallel tool-calling on GPT-3.5; as far as I know, we were the first to do that. WalkingRAG was an AI first in a few ways: the first agentic search system (I called it 'walking' then), the first multimodal/graphical search, and the first to run both on open-source models. I later published a three-part series on Hugging Face's blog that I still find useful as a reference. After Greywing, on a flight home to see family, I shipped Rakis in ten days — the first browser-based decentralized LLM consensus network. That's a lot of fun words that mean I got LLMs running in the browser using WASM (built on earlier work in wasm-ai), so that thousands of nodes around the world could run decentralized inference while still achieving fast consensus. The web never dies, so rakis.ai is still live today; the Rakis ST1 results are still the first real-world dataset on split inference across the world.

The problems then — as they always have been in my life — have been data problems.

We're surrounded by data that could describe and improve our lives in wonderful ways. Despite all of it being our data, hostile engineering, data silos, and yesterday's tools keep most of it out of reach. Southbridge is what I'm doing about that. We've recently open-sourced Hankweave, the long-horizon agent runtime that powers our reliable AI work; the companion essay Antibrittle Agents names the vocabulary we organize the work around. It has been a dream come true to finally see truly autonomous data pipelines and transformation systems become real — much less to be working on them.

In May I'll be speaking on long-horizon agents at AI Engineer Singapore — the first AI Engineer flagship in Asia.

My dad believed you can't help but be happy when there's still a lot to learn. Every year I find more.

I write as a means to think — in recent times it has become split across southbridge.ai/blog, this blog, Twitter, and internal writing at the company, but here are some popular ones whose graphs refuse to flatline:

§Selected writing

• Why Smart Contracts Fail (Medium, 2016) — the Oyente companion piece that went viral and helped land the code in the Ethereum Foundation.
• Schema on Write is better to live by (2021) — HN front page; the data-substrate essay that quietly became the Southbridge thesis.
• Losing our product to Button Syndrome (2022) — HN front page; the dad-as-engineer essay that traces the Greywing product philosophy.
• Object-Oriented Large Language Models (2023) — HN front page; the architecture essay behind SeaGPT's multi-agent design.
• Better RAG (3 parts) (Hugging Face, 2024) — the agentic-retrieval pattern.
• Introducing Rakis (2024) — the ten-day decentralized-LLM-network ship-it.
• Everything I know about prompting LLMs (2024) — the things I'll forget if I don't write them down.
• Everything about evals (2024) — same, but for the part where you check your work.
• Antibrittle Agents (2025) — the manifesto for long-horizon agents that became the Hankweave runtime.

I try to write year-in-reviews (even though the years are filling up more and making it harder): 2020, 2021, 2022, 2023, and 2024 (with a 4.5 follow-up). 2025 has been in-progress for a bit now — I apologise!

A few popular threads:

• Walking RAG demo (Dec 2023)
• Greywing's four-year retrospective in 60 seconds (Nov 2023)
• Decompiling Claude Code from a minified bundle in a Saturday (Jun 2025)
• Kimi K2 vs Grok 4 (Jul 2025)

§Open source and projects

A mix of viral things, weekend hacks, and home-cooked apps for people I love. Stars where they exist.

Used by other people:

• lumentis (1.7k★, 2024) — One-click AI-powered docs from transcripts. Hit #2 on GitHub trending in March 2024.
• offmute (565★, 2024) — Meeting transcription and diarization with just an LLM. Maybe a little overboard.
• wishful-search (412★, 2023) — Natural-language search over complex JSON arrays.
• mandark (254★, 2024) — A simple AI engineer; runs on npx; works on himself.
• diagen (252★, 2024) — Diagram generation pipeline.
• wasm-ai (173★, 2023) — Vercel + web-llm template to run wasm models in the browser; the precursor to Rakis.
• rakis (127★, 2024) — Browser-based decentralized LLM consensus network.
• hankweave-runtime (117★, 2026) — Long-horizon agent runtime; powers Southbridge.

Smaller things I'm fond of:

• socrate (28★, 2023) — A discussion room of GPT personalities with internal monologues, debating problems together.
• tough-llm-tests (28★, 2024) — Hard questions for evaluating new models.
• dadeumi (12★, 2025) — Iterative-reflection translation tool. Used to translate my 2024 Year-in-Review into Korean.
• meeting-diary (11★, 2025) — Simple meeting transcription.
• async-interval-queue (2019) — A tiny zero-dependency job queue I wrote six years ago; still being installed ~75 times a day. The web doesn't die.

§Selected publications

• Making Smart Contracts Smarter — Luu, Chu, Olickel, Saxena, Hobor — ACM CCS 2016. (Oyente.)
• GooseBumps: Toward Sensory Substitution Using Servo Motors — Olickel, Bhatnagar, Ong, Perrault — ACM ISS 2017.
• Improving Data Analysis in Chemistry and Biology Through Versatile Baseline Correction — Schneidewind & Olickel — Chemistry-Methods 2021. (Cover.)
• Random Number Generation Using Chua's Circuits — Yale-NUS, 2015.
• Continuous Glucose Monitoring (analysis) — with Hilhorst.
• Full list: Google Scholar.

§Selected press

• Forbes 30 Under 30 Asia 2023 — Enterprise Technology
• TechCrunch: Crew Change launch (2021), seed round (2021), SeaGPT (2023)
• Lloyd's Register: From Piracy to Protecting People's Wellbeing (April 2021)
• TradeWinds: Greywing's Proteus (March 2024)
• Smart Maritime Network: IINO + Crew Matrix Planning (2023)
• Cretu interview, Medium (2023)

§Selected talks

• Oyente — ACM CCS 2016, Vienna
• Machine Impossible — National Geographic, 2016 (Software Lead, Singapore Team).
• LLMs: A Hacker's Guide (2024)
• A Solid Pattern to Build LLM Applications (2024)
• AI Engineer Singapore — May 2026 (upcoming).
• Full channel: @olickel.

§Reach me

Twitter · LinkedIn · GitHub · Hugging Face · Google Scholar

Always happy to chat.