News for hackers. Stuff that matters.
Re:YC's Garry Tan uses AI agents so much, he spends up to $2... by plusfour on Wednesday November 04, 2026 @11:29AM (#50367964)
> would burn £2.5k worth of tokens over the course of a few hours

details please

Re:YC's Garry Tan uses AI agents so much, he spends up to $2... by hparadiz on Wednesday November 04, 2026 @11:54AM (#50368340)
Any 3D work in blender can burn that easily. Add video editing to that mix in any capacity.
Re:YC's Garry Tan uses AI agents so much, he spends up to $2... by deadnomore on Wednesday November 04, 2026 @12:13PM (#50368577)
Evaluation loops do this easily. You have to run hundreds of reasoning jobs in parallel and very quickly you can torch thousands of dollars.
Re:YC's Garry Tan uses AI agents so much, he spends up to $2... by sixtyj on Wednesday November 04, 2026 @01:15PM (#50369405)
Yup, run multiple agents on expensive model in loop via API.

You can do it if your employer has endless pockets.

Example: $30/1M input tokens (I don’t count output or cache, for simplification), you have several daily agents for everything => 3M tokens daily per agent * 10 agents ~> $900/day => $328k/year (API spending)

Re:YC's Garry Tan uses AI agents so much, he spends up to $2... by bartread on Wednesday November 04, 2026 @02:55PM (#50370665)
Yeah, it was basically this, and running a whole lot of agents concurrently to churn through the dataset faster.