Small correction, ExploitGym is not an OpenAI evaluation harness but a cybersecurity benchmark developed by Dawn Song’s team at Berkeley RDI.
Matt White
matthew-d-white
AI & ML interests
Global CTO of AI, Linux Foundation. CTO, PyTorch. CTO, LF AI & Data. Director, Generative AI Commons.
--- I love simulations, especially the one we are living in!
Recent Activity
commentedon an article 3 days ago
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident upvoted an article 2 months ago
AI, Physical AI, World Models, VLA, VLM, and Other Terms We Should Stop Mixing Together published an article 2 months ago
Eight Days in China: What I Learned from the AI Labs, Robotics Startups and AcademiaOrganizations
commented on Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident 3 days ago
upvoted an article 2 months ago
Article
AI, Physical AI, World Models, VLA, VLM, and Other Terms We Should Stop Mixing Together
barakor
• • 5 published an article 2 months ago
Article
Eight Days in China: What I Learned from the AI Labs, Robotics Startups and Academia
matthew-d-white
• • 5 upvoted a paper 11 months ago
liked a
model about 1 year ago
upvoted an article about 1 year ago
Article
Why We Built the OpenMDW License: A Comprehensive License for ML Models
linuxfoundation
• • 27 published an article about 1 year ago
Article
Why We Built the OpenMDW License: A Comprehensive License for ML Models
linuxfoundation
• • 27 upvoted an article about 1 year ago
Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
- +5
ariG23498, lusxvr, andito, sergiopaniego, merve, pcuenq, reach-vb
• • 263 upvoted an article over 1 year ago
Article
Introducing the Open FinLLM Leaderboard
- +11
QianqianXie1994, jiminHuang, Effoula, yanglet, alejandroll10, Benyou, ldruth, xiangr, Me1oy, ShirleyY, mirageco, blitzionic, clefourrier
• • 80