while working on agentick (to be presented at NeurIPS'26), @creus_roger found that ASCII inputs seemed to really help LLMs
during his internship at @VmaxAI he pushed on this idea and came up with GlyphBench, which serves as a benchmark, a research tool, & post-training suite!
1/ 🎮 Can training on games improve LLM reasoning?
Introducing GlyphBench: 360+ game tasks for language-model RL.
We use it as a benchmark, a research tool, and a post-training suite.
🧵⬇️
Congrats @natolambert ! I agree the community needs this type of work and investment, and you're one of the best people I can think of to lead it.
Love the name and its explanation as well!
Today we're unveiling Trillium Labs @trillium_labs, a new non-profit to foster the open science of frontier AI. We're building open post-training recipes and will expand into open infra to study RSI, reward-hacking, multi-agent systems, and whatever comes next.
We're built
In 2012 I thought I had left ML research forever, until @hugo_larochelle brought me into Google brain in Montreal.
I remain forever grateful for him believing in me and for guiding me during his time at Google. I feel honoured to call him a friend and colleague!
Very happy to see this profile of @hugo_larochelle
Before I join Google Brain, I watched all his lectures from Sheffield. You have to remember at the time, all of the knowledge for deep learning belong to less then 100 people. He made it available to many more.
He became my
TL;DR: This is one of the most important and exciting opportunities in AI on the planet - please read on.
The British Open-ended Learning & Discovery Lab is creating the perfect place for paradigm breaking AI research in the name of open-source and open-science. We have agency,