Agents

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. 2, 10 Trillion Tokens, Apache Agents, and a Goodbye That Un-Died

Week of 13 July: GPT-5.6 lands everywhere, Shanghai AI Lab drops an Apache agent brain, the voice race goes full-duplex, LongCat posts absurd numbers, robots get free eyes, and Fable 5 dodges retirement again.

Make Your AI Assistant Remember You Between Conversations

LLMs are goldfish by default. The file-based memory pattern that gives a local assistant identity, user context, and continuity, the same architecture ours runs on.