AI Isn't Coming for Your Mind. It's Coming Through It.
aletteraday.substack.com · 7,849 words · saved by 1 readers
Last week, I saw the following tweet from Anthropic:
Last week, I saw the following tweet from Anthropic: The tweet was part of a thread sharing a study Anthropic had conducted on agentic misalignment (specifically with regards to blackmail) and the new post-training methods they had used to address it. But what stuck out to me was a broader observation I have been thinking about for the past few years: If a specific harmful behavior can be traced to specific patterns in the training corpus, then less specific things, such as a model’s default narrative structure, are likely also corpus-shaped. The less specific something is, the harder it is…
saved by
related reading
- The Artificiality of Alignmentjoinreboot.org
- AI Friends Too Cheap To Meterjasmi.news
- Doomprompting Is the New Doomscrolling.workingtheorys.com
- Deep Deceptiveness — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Why You Should Almost Never Use AI to Write Anything Substantiveerichgrunewald.com
- Your AI Use Is Breaking My Brain404media.co
- How AI Is Learning to Think in Secretnickandresen.substack.com
- God Help Us, Let's Try To Understand The Paper On AI Monosemanticityastralcodexten.com
- the post-literate societyjasmi.news
- Dario Amodei — The Urgency of Interpretabilitydarioamodei.com