will brown
@willccbb
Followers
38K
Following
73K
Media
1K
Statuses
12K
reward hacking @primeintellect
(sf) | nyc
Joined February 2015
and we’re live! been a very long time in the making, huge thanks to everyone who’s made it possible along the way. can’t wait to see what you guys all build here. we’re just getting started :)
Introducing the Environments Hub RL environments are the key bottleneck to the next wave of AI progress, but big labs are locking them down We built a community platform for crowdsourcing open environments, so anyone can contribute to open-source AGI
44
45
723
they should make a functional web browser for people with more than one email account
12
0
52
Quickly and easily evaluate borrowers' income with our award-winning Income Calculator. Let our technology work harder for you, so you can do great work for your borrowers. Learn more.
2
11
114
i like how it’s not even Zoom-Agent-235B-1 from Zoom Research. it’s just Zoom the meeting app
Zoom achieved a new state-of-the-art (SOTA) result on Humanity’s Last Exam (HLE): 48.1% — outperforming other AI models with a 2.3% jump over the previous SOTA. ✨ HLE is one of the most rigorous tests in AI, built to measure real expert-level knowledge and deep reasoning across
4
0
37
We’re releasing pre-anneal checkpoints for our Nano/Mini base models. Still plenty of math + code exposure, but easier to CPT and customize than our post-anneal checkpoints. Have fun exploring.
8
18
102
Put a calendar hold for a meeting** on Friday. (**Playing pickleball)
0
2
44
with tools, but still. also it’s 30 Qs, models have been at ~95 for a while
0
0
15
first AI app for vibe coding
5
0
112
can’t wait for you guys to see what @jackminong and @ameen_ml and @jannik_stra and @manveerxyz have been cooking 🙏
3
1
63
crazy how fast open-source RL agent finetuning went from being a fairly fringe speculative idea to like the Main Thing
7
6
220
3
5
50
Your Jeep deserves more than just a traditional lift kit — it deserves an AccuAir Dynamic Lift Kit.
2
10
98
we gotta be one of the only neoclouds making 3-4 distinct research bets on effective approaches towards continual learning
7
3
152
🆕 We're back with a trio of RL talks! @willhang_ and @cathyzbn on OpenAI RFT: https://t.co/HsHlsx4kjz
@willccbb on RL Envs at Scale: https://t.co/3fyK2nQqp5
@rhythmrg and @lindensli giving @AppliedCompute's first ever public talk https://t.co/LFva4Ddruj Our RL track at AIE
0
5
33
📣 New for the agentic cloud: Azure Copilot—an immersive, full-screen command center powered by GPT-5 reasoning and a collection of agents to help you migrate, operate, and optimize your entire IT estate.
0
1
7
you can just call things “first”. doesn’t mean anything anymore
Introducing Orchids, the world's first vibe coding IDE. Orchids can build, watch, and listen on par with a human developer. Orchids ranks #1 on App Bench, the most rigorous benchmark for end-to-end software development. An agent, IDE, built-in browser, Supabase, and Stripe all
65
15
1K