Alec Gutmanstein - Software Engineer @ Scale AI
Joined June 2015
- Tweets20
- Following166
- Followers40
- Likes390
Check out our recent blog post detailing this RL environment!
agentenvframework.com/blog/c…
Guts 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…
AirOpsEnv live: GPT-6 Astra runs an airline control center through real storm days nitter.cf/i/broadcasts/1rGmqpMwB…
Guts retweeted
The airops environment has 3 sets of agents: air operations, crew desk, and customer desk. This is a simulation of the real world's JFK and Boston Logan Airports and it is available on hugging face huggingface.co/datasets/eara…
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.
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.
Guts retweeted
Building good RL environments is hard.
We're introducing a way to turn anything into RL-environments with REA using the open source AgentEnv framework from @ScaleAILabs
Any site, app, or game can now easily be turned into an env 😉
Guts retweeted
We collaborated with @scaleAI to build a high-fidelity port simulation RL environment where AI agents tackle real-world logistics challenges
Guts retweeted
📣Call for contributions + co-authorship!
RSI Bench is our ongoing effort to evaluate whether AI agents can develop the capabilities required to advance AI R&D.
Got a frontier AI research problem on your mind? Submit it to RSI Bench, and set the standard the whole industry uses to measure progress!
Contributors receive:
→ Co-authorship on the RSI Bench research paper
→ $2,000 per accepted task for the initial 50 tasks
→ Modal compute credits to build + iterate
→ Access to the RSI Bench research community
Register below for full requirements.
Launching rsi-benchmark.com:
The work of AI R&D has always belonged to humans. For the first time, though, it no longer seems certain that it always will.
Recursive self-improvement is within a line of sight. It may still be far, but it is close enough that we should start measuring it.
Guts retweeted
Who's ready for a #sweepstakes?! Enter here for the chance to win The Stormlight Archives Hardcover Box Set from @BrandSanderson. Just follow us, then like and retweet to enter. Best of luck, y'all! ⚔️
#StormlightSweeps
