← Back to context Comment by mrob 1 month ago The original post claimed they were "running hundreds of concurrent agents":https://cursor.com/blog/scaling-agents 3 comments mrob Reply simonw 1 month ago It was 2,000 concurrent agents at peak.I'd still be surprised if that added up to "trillions" of tokens. A trillion is a very big number. mikkupikku 1 month ago 16 million a second across 2000 agents would be 8000 tokens per second per agent. This doesn't seem right to me. Snuggly73 1 month ago I mean, its right there in their blog - https://cursor.com/blog/scaling-agents"We've deployed trillions of tokens across these agents toward a single goal. The system isn't perfectly efficient, but it's far more effective than we expected."
simonw 1 month ago It was 2,000 concurrent agents at peak.I'd still be surprised if that added up to "trillions" of tokens. A trillion is a very big number. mikkupikku 1 month ago 16 million a second across 2000 agents would be 8000 tokens per second per agent. This doesn't seem right to me. Snuggly73 1 month ago I mean, its right there in their blog - https://cursor.com/blog/scaling-agents"We've deployed trillions of tokens across these agents toward a single goal. The system isn't perfectly efficient, but it's far more effective than we expected."
mikkupikku 1 month ago 16 million a second across 2000 agents would be 8000 tokens per second per agent. This doesn't seem right to me.
Snuggly73 1 month ago I mean, its right there in their blog - https://cursor.com/blog/scaling-agents"We've deployed trillions of tokens across these agents toward a single goal. The system isn't perfectly efficient, but it's far more effective than we expected."
It was 2,000 concurrent agents at peak.
I'd still be surprised if that added up to "trillions" of tokens. A trillion is a very big number.
16 million a second across 2000 agents would be 8000 tokens per second per agent. This doesn't seem right to me.
I mean, its right there in their blog - https://cursor.com/blog/scaling-agents
"We've deployed trillions of tokens across these agents toward a single goal. The system isn't perfectly efficient, but it's far more effective than we expected."