+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Security, Privacy & Safety (https://www.datasculpting.ai/inference/forumdisplay.php?fid=23)
+--- Forum: Model / Agent Security (https://www.datasculpting.ai/inference/forumdisplay.php?fid=77)
+--- Thread: sandboxing agent actions with llama.cpp (/showthread.php?tid=1322)
sandboxing agent actions with llama.cpp - promptfield - 10-17-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like continuous batching decides everything downstream.
Curious whether that lines up with what other people are seeing.