High-fidelity trajectories and environments for frontier AI research

Brooklyn, NY
Thanks for featuring our work @immutablejacob, @MessariCrypto, and team! Better datasets & environments => better models
Despite the incoming drought of public text, we're nowhere close to using up the world's data. The world's total data is ~200 ZBs and doubles every ~2 years. The valuable modalities and sources that can be drawn from include: > Audio (@psdnai, @silencioNetwork, @Meet_Perle) > Video (@grass, @playonshaga, @chakra_ai) > Sensor (@375ai_, @frodobots, @Hivemapper) > Synthetic (@PrimeIntellect, @SynthdataCo, @driaforall) > Personal (@vana, @getoro_xyz, @CudisWellness)
33
14
159
14,536
Update: Dojo now supports the OpenEnv spec.
19
27
136
25,030
Ex: access our Amazon clone using familiar Gymnasium style APIs.
7
8
44
6,196
To get started, check out our docs and code examples below. docs.trydojo.ai/integrations…
4
7
43
4,865
Chakra Labs retweeted
You can now run tasks in @chakra_ai's RL environments using Browserbase as the runtime. Get task concurrency, isolated contexts, and enhanced observability.
Update: Dojo now supports @browserbase
19
13
83
9,973
Update: Dojo now supports @browserbase
8
15
78
15,269
We're excited to announce support for Browserbase, which allows researchers to quickly spin up 1000's of browser tasks concurrently using their serverless hosted infrastructure. Researchers now benefit from: - Hyper-scalable browser infra - Secure SOC II instances - Native observability and session recordings
2
5
40
3,063
To get started with this custom run-time, check out the Dojo engine docs below: docs.trydojo.ai/engines/brow…
2
3
27
2,533
Chakra Labs retweeted
these ppl just keep cooking 🔥
Another fun Dojo we published: Gmail We have a first party clone of Gmail inbox + email sending available free to use - with verifiable state and tasks
2
3
31
4,122
Chakra Labs retweeted
An interesting design decisions we made with dojo: - All of our dojos inherit the following state pattern
2
3
32
3,875
Chakra Labs retweeted
so we did this :)
if i was running Linear, and i wanted every AI ever to become very good at using Linear, i would make an RL environment version of Linear and open-source it for free, with a curated set of realistic sample data. every lab would train with it. who else can compete with that?
5
10
417
128,787
Chakra Labs retweeted
This is awesome... This is how we craft the future of CUAs, by actually open-sourcing the RL env suites...
Today, we’re excited to announce Dojo, a collaborative RL environment suite for computer use agents (CUA).
1
1
24
3,404