Software Engineer @ Scale AI
Joined March 2023
- Tweets437
- Following181
- Followers472
- Likes1.7K
Edgar Arakelyan retweeted
Check out our recent blog post detailing this RL environment!
agentenvframework.com/blog/c…
Edgar Arakelyan retweeted
OpenHands is now supported in @scale_AI's open-source AgentEnv framework.
Run and evaluate agents against the same tasks and environments, without locking into one agent or infrastructure provider.
More interoperability, more choice. That’s the future we’re building toward.
Details 👇
agentenvframework.com/docs/a…
Edgar Arakelyan retweeted
Daytona sandboxes are now built into AgentEnv, @scale_AI's open-source framework for RL environments.
Every environment and agent gets its own sandbox with Docker inside, so compose stacks, agent containers and image builds run unchanged.
Setup below 👇
Edgar Arakelyan retweeted
How far can a better harness take a lightweight model?
Using Agent Env Framework from @ScaleAILabs, we let Haiku's harness recursively improve across 3 games and put it head to head against Opus.
See more at: agentenvframework.com/blog/t…
Edgar Arakelyan retweeted
RL works. The problem is leaky environments.
If a rollout can see the last one's files or look the answer up online, the model learns to cheat. AgentEnv from @ScaleAILabs now gives each environment and agent its own boxd VM. It boots in 2 seconds and is deleted afterwards.
Edgar Arakelyan retweeted
@smolmachines x AgentEnv from scale.
You can leverage smol to power AgentEnv workloads now to run it on any platform, locally or remote.
open source loves open source! Thanks @earakely for partnering up on this!
agentenvframework.com/docs/s…
github.com/smol-machines/smo…
Edgar Arakelyan retweeted
You can now run AgentEnv evals from @ScaleAILabs on Vercel Sandbox.
Give your agent a task, run it in a sandbox, and check how it performed.
vercel.com/changelog/run-sca…
Edgar Arakelyan retweeted
The @scale_AI Mafia is an unreal force 🤯. Wild to see what this crew is doing—and the talent and ambition of the next generation. It’s clear this story is just getting started.
THE SCALE MAFIA
one of the most special parts of starting a company is watching the people you fought and bled with in the early days go out and change the world.
the Scale crew was supernatural. @scale_ai was one of the first companies to IOI and IMO-maxx, and the magic of Scale was that all of these geniuses gave a shit and ran through walls. it's no wonder that the Scale mafia is the first true mafia of the modern tech era. just to name a few:
- cognition founder @stevenkplus1 & president @russelljkaplan
- modal founder @akshat_b
- tech & science advisor to POTUS @mkratsios47
- claude code head of product @_catwu
- kpcb partners @LM_Braswell & @nayakkayak
- bun founder @jarredsumner
- tbd head of product @lindugong
- netic founder @melisatokmak
- cobot founder @BradPorter_
- secureframe founder @shravvmehtaa
- paramount skydance cfo @DennisKCinelli
- thinking machines gc lauren lennon
- partner at greylock @sophia_luo_
- liquid ai coo jeffrey li
- gallatin ai founder @agilemofo
- tbd safety @_julianmichael_
- center for ai safety president @devindkim
[photo courtesy the beautiful wedding of @thenateherman (who in many ways was a cofounder of Scale) and @ChristinaG325]
Edgar Arakelyan retweeted
I think this might be a first, an RL environment simulating airport operations being streamed live. 👀
AirOpsEnv live: GPT-6 Astra runs an airline control center through real storm days nitter.cf/i/broadcasts/1rGmqpMwB…
Edgar Arakelyan retweeted
AirOpsEnv live: GPT-6 Astra runs an airline control center through real storm days nitter.cf/i/broadcasts/1rGmqpMwB…
Edgar Arakelyan retweeted
With @huggingface, we made AirOpsEnv: real storm days across JetBlue's network, where an agent decides which flights to cancel or hold while FAA ground stops and lightning ramp closures hit JFK and Boston.
It's all open source and built from public FAA, BTS and NWS data: 94 storm days, each graded against the best plan possible in hindsight. On those days JetBlue cancelled 5.6% of its flights, and the hindsight plan cancels 2.2%.
AgentEnv Framework makes that easy: a whole day, with news arriving when it was actually issued and a virtual clock, is 7 steps in one task.json.
pip install agentenv-framework
Can AI agents keep an airline running through a storm? ✈️
We teamed up with @ScaleAILabs to build a high fidelity simulation RL environment grounded in real JFK + Boston flight records, FAA advisories and weather data.
Edgar Arakelyan retweeted
You can run phone use agents on real devices yourself through our open-source platform AgentEnv using the @Mobilerun plugin!
Check it out here
github.com/kaihackney-scale/…
Edgar Arakelyan retweeted
Real apps. Real phones. Real-world challenges.
Excited to see @ScaleAILabs using @mobilerun to push mobile agent evaluation beyond simulations 📱
Most phone agents are tested in simulated environments, but the real world is messier: carts persist, listings change hourly, and navigation varies.
At @ScaleAILabs, we ran agents on real phones with real apps on AgentEnv Framework.
See more at agentenvframework.com/blog/a…
Edgar Arakelyan retweeted
Most phone agents are tested in simulated environments, but the real world is messier: carts persist, listings change hourly, and navigation varies.
At @ScaleAILabs, we ran agents on real phones with real apps on AgentEnv Framework.
See more at agentenvframework.com/blog/a…
