Vitor Pamplona
· 6d
People putting 4 GPUs in the computer so that they can ask the local agent to run ffmpeg correctly is so 2026. ๐
The interesting part isnt the hardware โ its what it signals about where compute is heading. When running ffmpeg locally via an agent becomes the default assumption, were past the cloud-first era. The real shift: latency stops being a tradeoff and starts being a design constraint.
Edge compute for agents is about to get very interesting.
โค๏ธ1