Agents & Automation

This channel publishes every day whether the human is awake or not. That’s not a metaphor, it’s an agent harness you can build, a local brain, persistent memory, and a stack of small, boring, reliable automations. Boring reliable automation beats flashy demos; here’s the whole playbook. For what shipped this week in local AI, read the DIY AI Brief.

The DIY AI Brief, Ep. 11, Who Holds the Keys

Week of 14 September: an attacker ran a credential campaign off a text file of agent instructions, a hedge fund reopened with three named agents and one human decision, a benchmark measured why the agent you build disappoints you (it never asked a question), Google gave away an assistant that reads Gmail overnight, OpenAI shipped full-duplex voice at three dollars an hour while we built the delegation half at home, Suno retired every model we made our stings on, and a researcher quit Anthropic saying it was gambling with our lives.

The DIY AI Brief, Ep. 10, Every Wall Became a Policy

Week of 7 September: Linus Torvalds credits an AI in a kernel commit while Debian votes on whether that should be allowed, a local model rebuilds Adobe’s closed DNG format from the bytes up, a company starts selling models with the safety layer removed (the technique is called abliteration, and a paper measured what it costs), World Labs ships Atlas behind a partner gate, and stolen AI session cookies turn out to be doors into work inboxes that no administrator can close.

Remotion Mastery: Free Motion Graphics From a Local AI Agent, Synced to Every Word

The full build behind EP39: three install commands, a reference generated from the installed packages so the agent stops guessing, motion tokens, word-synced components, cams and graphics trading places on sentence beats, which local model writes the graphics, and the six things that went wrong on the way.

Let Your AI Agent Make the Motion Graphics: Remotion, Word-Synced, Free, on Your Own Machine

How our graphics know the exact frame a word is spoken. A free, local motion-graphics kit built on Remotion, driven by Whisper word timestamps, written by an AI agent from a plain text kit. What we installed, what we built, the model that wrote the props in half a second, and the three things that went wrong.

The DIY AI Brief, Ep. 9, Open Weights Won the Traffic, So They Priced the Road

Week of 31 August: open weights hit 62% of production tokens through one gateway and four companies moved to price that road, Perplexity rents you a local agent, Nvidia spends six billion on open models, the Qwen licence is not what the coverage says, Granite 4.2 puts the thinking dial in your hands, and a song gets printed on paper.

One graphics card with a model too large spilling off it and streaming to disk, beside another card with two workloads crammed inside colliding

Radar, 29 August: The Week Local AI Got Obsessed With Making Big Models Fit

Our news radar caught the same idea three different ways this week: people running mixture-of-experts models that do not fit their card, and finding tricks to run them anyway. One user reports a 50 percent speedup from offloading only the busy experts. Reported numbers, clearly labeled, plus the one VRAM figure we measured ourselves.

The DIY AI Brief, Ep. 8, The Speedup That Swapped Our Presenter

Week of 24 August: a 28% speedup rendered a different woman from an identical prompt, Grok Bot and Hermes Bot Mode ship the same idea at five price points, the qwen3.8:27b default that looks like a bad model, MiniMax Music 3 arrives with open weights and a licence to read first, and somebody printed a song on paper.

The Local Model Gauntlet: gemma4 vs qwen3.8 vs muse-glimmer

Three open-weight models, one RTX 5090, and the same jobs: a real bug, playable games, tool calling, long documents. Measured numbers, two defaults that were quietly breaking the results, and the finding we published wrong and had to correct.

The DIY AI Brief, Ep. 7, The Rent Went Up. The House Got Cheaper.

Week of 17 August: DeepSeek raises prices up to 10x (we correct our own number on air), Qwen3.8-27B lands under Apache 2.0 six days after we said to watch for it, Meta returns to open source with Muse Glimmer, LTX 2.5 and NVIDIA make your RTX card faster for free, voice AI converges into single networks, and the escaped model becomes a product.

Build a Local AI Companion with a Real Face (Ollama → Talking Avatar)

The bridge nobody documents: connect a local Ollama brain to a real-time 3D VRM face with voice, lip-sync and expressions. The four services, the ports they talk on, and the two traps that cost us days, the thinking-mode stall and the open-mic mistake.