Practical notes on AI agents, model routing, local AI, diagnostics and automation — from the workshop floor.https://theaifixer.com/en-gbhttps://theaifixer.com/notes/the-human-brain-was-not-built-for-the-infinite-feed/https://theaifixer.com/notes/the-human-brain-was-not-built-for-the-infinite-feed/John's field note on information overload, family, trust, local AI, and why private AI systems are not about hiding — they are about keeping human agency alive.Fri, 12 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/body-adjacent-ai-needs-a-kill-switch-on-our-side/https://theaifixer.com/notes/body-adjacent-ai-needs-a-kill-switch-on-our-side/If AI is moving into glasses, cars, tools, workshops and eventually body-adjacent interfaces, the off switch cannot live in the cloud.Thu, 11 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/fable-5-feels-like-two-models-in-one/https://theaifixer.com/notes/fable-5-feels-like-two-models-in-one/An operator's observation from tool-heavy sessions with Claude Fable 5: it behaves less like a single plain model and more like a front controller in front of a reasoning engine — and that pattern is exactly how we should be building our own agent systems.Thu, 11 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/why-i-rebuilt-my-ai-agent-memory/https://theaifixer.com/notes/why-i-rebuilt-my-ai-agent-memory/John explains why messy long-term AI agent memory caused false positives, bad routing and unreliable behaviour — and how cleaning memory made Hermes Agent safer and more useful.Thu, 11 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/why-prompting-is-becoming-spec-writing/https://theaifixer.com/notes/why-prompting-is-becoming-spec-writing/Chat prompts are questions. Agent prompts are work orders: scope, authorization, boundaries, acceptance criteria. The skill that matters now is the one engineers always hated doing.Wed, 10 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/the-real-problem-with-ai-agents-is-context-selection/https://theaifixer.com/notes/the-real-problem-with-ai-agents-is-context-selection/Agents don't usually fail because the model is too small. They fail because the wrong slice of reality was in the window when the decision got made.Tue, 09 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/what-auto-diagnostics-taught-me-about-ai-debugging/https://theaifixer.com/notes/what-auto-diagnostics-taught-me-about-ai-debugging/Twenty years of fault-finding on vehicles maps almost one-to-one onto debugging AI systems: observe, hypothesise, test one variable, verify the fix — and never trust the fault code.Mon, 08 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/building-local-ai-like-a-workshop-not-a-toy/https://theaifixer.com/notes/building-local-ai-like-a-workshop-not-a-toy/Eight 3090s, a Proxmox host, and a rule: every machine earns its keep. Local AI infrastructure built like workshop equipment — bought for jobs, not for benchmarks.Sun, 07 Jun 2026 00:00:00 GMThttps://theaifixer.com/notes/why-useful-agents-need-verifiers-not-just-bigger-models/https://theaifixer.com/notes/why-useful-agents-need-verifiers-not-just-bigger-models/The cheapest reliability upgrade in any agent system isn't a smarter model — it's a second pass that checks the first one's work before it leaves the building.Sat, 06 Jun 2026 00:00:00 GMT