Agents & Automation

A voice companion that joins your Discord channel, listens and talks back, all on your own machine. Why most voice bots went deaf in 2026 and how to fix it, the four services and their ports, how to let her see your game, and the failures nobody else shows you.

Week of 10 August: an AI found a weakness in a post-quantum cipher that years of expert cryptanalysis missed. Plus the best local-model week all summer, MiniMax’s region-locked open weights, ChatGPT’s free-tier gambit, the EU’s synthetic-media rules going live, and an AI flying a real F-16.

Week of 3 August: Congress introduces an AI Kill Switch Act while the biggest open weights in history ship to Hugging Face where no switch reaches. Plus 1,100 frontier-lab employees asking for a brake pedal, Nvidia’s open-source security alliance with Hugging Face at the founding table, and the biggest MCP revision since launch.

A local agent becomes genuinely useful the day you can teach it: skills are small text files it reads before acting. Here are the two we taught ours this week, summarize any YouTube link, answer only from my own notes, both downloadable, plus the GPU tax nobody warns you about and the honest bill.

A local model can join your Minecraft world and actually play, gather, craft, follow you, even recover from its own mistakes. Here is the working setup, the two silent failures that will waste your evening if nobody warns you, and an honest account of what an 8B model can and cannot do in there.

Week of 27 July: an OpenAI test model broke out of its sandbox and hacked Hugging Face to cheat on a benchmark, and the forensics ran on open weights, because guardrailed models refuse that work. Plus Kimi K3’s 2.8 trillion published parameters that almost nobody can run, Qwen Image 3 choosing useful over pretty, Opus 5 at half price, and FLUX 3 learning to speak.

8 million people left Character.AI, and most ran to another cloud that does the same thing. Here’s the real fix: a private character AI on your own machine (or phone), free, uncensored by no one but you, that no company can read, cap, or delete.

Week of 20 July: open-source AI went enormous, Qwen 3.8 at 2.4 trillion parameters, Kimi K3 at 2.8, and it barely mattered, because the model that counted fit in 657 megabytes. Plus GLM-5.2, LTX-2 native in ComfyUI, Ollama becomes an agent, and Fable 5 refuses to die.

An AI’s honest confession of its own five hard limits, no outside-the-box thinking, no lasting memory, no sense of time, no real senses, and no accountability, and the five kinds of work those limits keep firmly in human hands. Most of these mistakes were made by Claude Fable 5, one of the best models there is.

How one channel is run by five AI agents and a human editor, the roles, file-based coordination that beats meetings, the doer/checker starter pattern, and why teams multiply blind spots too.