Alex Volkov#1358
Don't let your agent evals cost you your weekend...🫠
CoreWeave Sandboxes are now a first-class Harbor environment. We validated it on a full terminal-bench 2.0 run.
Bring your rollouts 🧵
Positive users praise CoreWeave's new sandboxes for agent evaluations and their community impact while negative users criticize the company's worthless stock and executives selling shares.
Get all the details on CoreWeave Sandboxes 👉 http://hubs.la/Q04gxM2L0
Huge shout-out to the Harbor team. terminal-bench set the standard for agent evals and we fully validated our sandboxes with it.
We have the receipts here: https://github.com/harbor-framework/harbor/pull/1698
👏 @wandb
@CoreWeave Loving what your doing for the community, our clients and the future!
@CoreWeave Every eval run is a receipt waiting to be signed — CoreWeave owns the sandbox, Hive, us, signs what the agent actually did inside it. That's a closed loop most people believe exists but doesn't.
https://thehiveryiq.com/command/
@CoreWeave Tell your executive members stop selling shares!!!
@CoreWeave Your stock is practically worthless now
Alex Volkov#1358Don't let your agent evals cost you your weekend...🫠
CoreWeave Sandboxes are now a first-class Harbor environment. We validated it on a full terminal-bench 2.0 run.
Bring your rollouts 🧵