Dex HunterAgents · London

Buildthebuilders.

I'm Dex, a Member of Technical Staff at Weco AI (London, UK). I build autonomous agents that do long-horizon engineering and research work. I co-authored AIDE, the tree-search ML agent OpenAI used in MLE-bench, and built the research agent that set seven records in OpenAI's Parameter Golf.

See selected work → GitHub profile
Portrait of Dex Hunter
Felix, qui potuit rerum cognoscere causas.Virgil · my GitHub bio
PathBlockchain infrastructure, then distributed ML, now research agents
  1. 2016-18XJTLUBSc; deep RL for portfolio management
  2. 2018-24HyperledgerIntern, then Fabric Python SDK maintainer
  3. 2019-20NTU · Zhejiang U.Private ML at the IoT edge
  4. 2020-21HKBUAll-reduce for distributed training
  5. 2022-24Hex TrustTrading backend in Rust and Go
  6. 2024-nowWeco AIAgents that do ML research
Languages
PythonRustGoTypeScriptC
ML & agents
PyTorchLLM agentstree searchevals
Infrastructure
KubernetesTerraformNginxHorovod
Agent tooling
HarborLangChainDeep AgentsPi
Proof

Numbers anyone can check on GitHub.

58

open-source projects with my merged code

180+

merged pull requests

7

records in OpenAI Parameter Golf

4.1k

stars on seedance2-skill

Cited, used or merged by
UK AI Security Institute
Merged my speedups into Inspect, its LLM eval framework.
inspect_ai #4714 ↗
Selected work

Agents that keep working
after I close the laptop.

Weco AI · co-author, co-maintainer

AIDE

Tree search over code: draft, run, debug, improve, keep the best. I co-authored the paper and co-maintain the repo.

  • 1.5k stars
  • top scaffold in OpenAI's MLE-bench paper
Read the paperCode
OpenAI challenge · 2026

Seven records in Parameter Golf

Best language model in 16 MB and 10 minutes of training. My research agent ran for 22 days, filed its own PRs and set twice as many records as the best human, out of 1,016 entrants.

  • 25 PRs, 7 records
  • cited 435 times by other entrants
Record trackBest entry
Agent skill · 2026

seedance2-skill

Turns a rough idea into a production prompt for the Seedance 2.0 video model.

4.1k stars · 344 forks
RepoSite
Developer tool · 2026

Vibe Clock

WakaTime for coding agents: tracks Claude Code, Codex and OpenCode, renders SVG cards for your profile.

Python · SVG · Homebrew
Repo
Linux Foundation · 2018-24

Fabric Python SDK

Maintainer of Hyperledger's Python SDK. Ran the v0.7 release and mentored two internships.

Maintainer · release manager
Maintainers file
Open source

Approved by maintainers.

Speed and correctness fixes to other people's projects. Many recent ones were written by the agents I build at Weco AI, and each went through the maintainers' normal review.

openclawopenclaw · ★ 391k AutoGPTSignificant-Gravitas · ★ 188k langchainlangchain-ai · ★ 147k OpenBBopenbq-org · ★ 74k remotionremotion-dev · ★ 62k gooseaaif-goose · ★ 55k agnoagno-agi · ★ 43k manimManimCommunity · ★ 41k pnpmpnpm · ★ 37k poetrypython-poetry · ★ 34k InvokeAIinvoke-ai · ★ 28k qwen-codeQwenLM · ★ 28k llamafilemozilla-ai · ★ 26k oxcoxc-project · ★ 23k pydantic-aipydantic · ★ 20k style2paintslllyasviel · ★ 18k

16 of 58 projects shown, by stars. Full list on my GitHub profile.

Highlights

  1. UK AI Security Institute · Inspect

    Faster clustered-stderr scoring (#4714) and linear-time media extraction (#4628).

  2. Seven agent runtimes

    Performance fixes in openclaw, AutoGPT, goose, Qwen Code, Pydantic AI, agno and BAML.

  3. Evolutionary search

    Cut redundant AST parsing in Sakana's ShinkaEvolve and bounded shutdown latency in OpenEvolve.

  4. Hyperledger

    Maintained the Fabric Python SDK and interned on Cello for the Linux Foundation.

Papers, talks, awards

Papers and talks.

Publications

  • 2026 · arXivRecursive Self-Improvement of AI Research AgentsarXiv 2609.26457
  • 2025 · arXivAIDE: AI-Driven Exploration in the Space of CodearXiv 2502.13138
  • 2020 · IEEE Internet of Things Journal · first authorLightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote InferenceDOI 10.1109/JIOT.2020.2983278
  • 2019 · ACM AIChallengeIoTChallenges of Privacy-Preserving Machine Learning in IoTDOI 10.1145/3363347.3363357
  • 2017 · arXivA Deep Reinforcement Learning Framework for the Financial Portfolio Management ProblemarXiv 1706.10059

Talks

  • 2026 · AI Engineer World's Fair, San FranciscoHands-on AutoResearch: Cracking OpenAI's Parameter GolfWorkshop with the Weco AI team
  • 2024 · Network School, first cohortAlgorithmic Trading WorkshopSlides
  • 2019Deep Learning for Power System Security AssessmentSlides

Selected awards

  • Dev bounty winner, Network School (Farcaster social-graph visualiser), 2024
  • Special Prize (US$10,000), Wanxiang Blockchain Hackathon by Qtum, 2018
  • 1st Prize, EOS Hackathon Hangzhou (team), 2018
  • 1st Prize of 70+ teams, Hack x FDU, 2017
Get in touch

Felix, qui potuit rerum cognoscere causas.

Lucky is the one who has learned the causes of things. Virgil. It's also my GitHub bio.

Write to me about agents, evals, research infrastructure or an open-source project you want faster.

i@dex.moe Read the full CV