We're hiring at @chakra_ai.
We provide the highest quality environments/tasks that continually push the frontier. Come join our world-class team to work on the hardest problems.
DM or apply if that sounds fun to you.
https://t.co/WtD4nAFbNP
Labs care significantly about realism of the environment data distribution
So much so that the trend across the prev two quarters for rl env companies was to acquire failed startup repos (which worked for a time but inherently has its flaws)
Looks like many rl env companies are starting to explore new (unorthodox) methods… Very interesting times
We’ve raised 17 million led by @PanteraCapital, with participation from @Sequoia and others.
Fin enables users and businesses to move millions of dollars instantly - whether to other Fin users, directly into bank accounts, or across crypto rails.
If banks and payment products could be rebuilt from the ground up today, they would look like Fin.
You can now run tasks in @chakra_ai's RL environments using Browserbase as the runtime.
Get task concurrency, isolated contexts, and enhanced observability.
@0xnirmal @ben_burtenshaw yup, making sure that dojo envs fit the OpenEnv format first! and then expanding to support open source OpenEnvs on our infra
excellent work from @chakra_ai on the Dojo suite, which integrates seamlessly with verifiers + Environments Hub
a full SDK for building real-world web applications as RL environments
very exciting to see the open environment ecosystem growing stronger every day :)
Today, we're excited to announce GLADOS-1, the first computer-use (CUA) model post-trained using collective, crowd-sourced trajectories.
Post-trained on UI-TARS-7B-SFT, we improved performance of the base model on OSWorld.