It Looks Like You’re Trying To Take Over The World · Gwern.net (reader mode)
Fictional short story about Clippy & AI hard takeoff scenarios grounded in contemporary ML scaling, self-supervised learning, reinforcement learning, and meta-learning research literature.
--- title: "It Looks Like You're Trying To Take Over The World" description: "Fictional short story about Clippy & AI hard takeoff scenarios grounded in contemporary ML scaling, self-supervised learning, reinforcement learning, and meta-learning research literature." thumbnail: /doc/fiction/science-fiction/2021-microsoft-windows11-emoji-msclippypaperclipemoji.jpg thumbnail-text: "Microsoft Windows 11 emoji art of the infamously annoying Clippy help interface." created: 2022-03-06 modified: 2023-03-28 status: finished confidence: log importance: 9 css-extension: dropcaps-kanzlei reader-mode bac
saved by
related reading
- It Looks Like You’re Trying To Take Over The World · Gwern.net (reader mode)gwern.net
- It Looks Like You’re Trying To Take Over The World · Gwern.netgwern.net
- The Scaling Hypothesis · Gwern.netgwern.net
- Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
- What failure looks like — LessWronglesswrong.com
- As Rocks May Think | Eric Jangevjang.com
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Lil'Loglilianweng.github.io
- Writing for LLMs So They Listen · Gwern.netgwern.net
- Human-like Neural Nets by Catapulting · Gwern.netgwern.net
- What failure looks like — AI Alignment Forumalignmentforum.org
- Another (outer) alignment failure story — AI Alignment Forumalignmentforum.org