The unix terminal is the natural interface for agents to get work done on a computer but how well can agents actually use unix?
Claude Code. Codex. Devin. Every frontier agent ships as a terminal tool.
With unix-ctf, Vmax is using setters and solvers to measure Unix competence.
Vmax is building an open-ended learning system that generates and optimizes itself on tasks that it creates, avoiding human bias that may corrupt optimal learning curricula.
In PopuLoRA, we instantiate this as co-evolving populations of LLMs performing asymmetric self-play.
@VmaxAI is excited to have @creus_roger joining us as a research fellow!
Roger is joining us from @Mila_Quebec where he works with @pcastr and @GlenBerseth.
Roger Creus Castanyer is a brilliant RL researcher working on exploration, credit assignment, and skill discovery.
He is also fresh off of a NeurIPS spotlight and a recently accepted paper to ICLR, you can find more of his research in the comments.
Roger is significantly accelerating our research on automated environment design - looking forward to sharing what he is cooking!
We are releasing a sneak peak (1k tasks) that we are generating for Ares. These are available to run now in Ares and also on the harbor registry
https://t.co/VrdP07VbRL
RL progress is bottlenecked by infra for training and evaluation. @VmaxAI is excited to be partnering @withmartian, generating environments for the Agentic Research and Evaluation (ARES) framework
The RL event @VmaxAI and @southpkcommons are organizing has a stacked panel of amazing researchers, whose work I have admired since my PhD, when RL was not as much of a hot topic as it is today.
Here's a thread on our panelists 👇
How do you maximize the value of Reinforcement Learning? We're co-hosting an off-the-record panel event on December 11th with @VmaxAI@danijarh@ashvinair to find out.
RSVP 🔽
RL for LLMs focuses on policy-gradient methods and doesn't fully utilize RL innovations like value functions and model-based planning.
Join @southpkcommons+@VmaxAI on Dec 11 for a panel w/ @danijarh and others on which pre-LLM ideas will matter most in the LLM era. Link below.
At Vmax, we are automating the construction of RL environments and the post-training of agents. We are hiring members of technical staff and research fellows. Come join us in SF! (link to apply in comments).
Hello #MedTwitter!
I’m Valberto — IMG (🇬🇼 / 🇧🇷) and Research Fellow at Cleveland Clinic @CCFSurgery.
#GeneralSurgery Applicant | #Match2026 | #ERAS
Grateful for this journey and excited to connect, learn, and share experiences!
📌 AAMC ID: 15244773
@ProjectImg
Introducing Bunny - world's first curiosity device for kids
It’s screenfree..it’s portable..
We raised $1M from @southpkcommons to reimagine how kids thrive in the age of AI, safely.
Comment 'Bunny'. Our nephew will pick 50 families that get it for free this holiday season…
Deeply honored to receive the Young Investigator Award at the upcoming WTC in August. This project has been truly impactful in my career, and I’m immensely grateful to @ChaseWehrle for guiding me, as well as to our outstanding PIs, Dr. Schlegel and Dr. Esfeh @CCFSurgery