https://mutatingfunc.github.io/tags/agents/Recent content in Agents on MutatingFuncHugo -- gohugo.ioen-ukSat, 07 Mar 2026 00:00:00 +0000https://mutatingfunc.github.io/blog/2026-03-07-a-sceptical-look-at-llms/Sat, 07 Mar 2026 00:00:00 +0000https://mutatingfunc.github.io/blog/2026-03-07-a-sceptical-look-at-llms/I’m an LLM sceptic. LLMs controlling the computer is a security nightmare, misinformation is to be avoided. Most modern agent clients build in some level of security, turning repetitive input tasks into a series of outputs & permissions dialogs. Permission dialogs suck, but output review is still faster than extended inputs. There’s a workflow here: Give a request. The LLM builds a small code-based tool to carry it out. Human reviews, tweaks, approves the tool.