Intel

Privacy Terms Submit Map API for Agents

Open engineering challenges: cost, latency, sim-to-real gap — Intel — VibeLeaderboard

← All Intel

Clip / AI Agents

Open engineering challenges: cost, latency, sim-to-real gap

From Emulated: The Data for Fully Autonomous Software Engineers and Companies — Joseph Wang · ≈12:16

“Like, for example, spinning up the entire stack for something like AWS Lambda takes hours.”

“You still have to have live customer traffic.”

What’s in it

Flags that spinning up a full AWS Lambda stack takes hours, complicating training loops
Surfaces unsolved cost and infrastructure problems in post-training rollout for RL agents
Argues sim-to-real gap persists even with real resources due to scale-specific bugs

Watch this moment ↗

Clip transcript

challenges with you uh in case you're interested in working on them as well. As you can imagine, there's a lot of different problems that we haven't touched on here. Like, for example, spinning up the entire stack for something like AWS Lambda takes hours. Um how do you fit that into a post training rollout? Uh and then there's cost as well. How do you efficiently manage this? How do you make sure the sim-to-real gap, even with real resources, it still exists, right? You still have to have live customer traffic. You still have to have uh problems that only appear at a certain scale.