WWW - Evaluative Soliloquies - Ken Liu
✨✍️ home · learn more · stories · Evaluative Soliloquies Ken Liu ⚠️ The writers featured here have used Wordcraft along with their own creative vision and have not authored these stories under any sort of explicit guidance or instruction. The stories presented may include mature themes, language or situations. Google does not endorse the content of any of the stories contained on this website. When the robot engages itself in an evaluative soliloquy, it covertly explains its underlying decisional processes. Thus, the robot becomes more transparent, as the human gets to know the motivations and the decisions of robot behavior. - Pipitone, Arianna, and Antonio Chella. "What robots want? Hearing the inner voice of a robot." iScience 24.4 (2021): 102371. Drive I'm a driver. It's my job to take humans from where they are to where they want to be. I start at the airport, where I see a line of humans waiting for a ride. I must help them. When my light comes on, the humans move towards my vehi
WWW - Evaluative Soliloquies - Ken Liu Evaluative Soliloquies Ken Liu ⚠️ The writers featured here have used Wordcraft along with their own creative vision and have not authored these stories under any sort of explicit guidance or instruction. The stories presented may include mature themes, language or situations. Google does not endorse the content of any of the stories contained on this website. When the robot engages itself in an evaluative soliloquy, it covertly explains its underlying decisional processes. Thus, the robot becomes more transparent, as the human gets to know the motivation
Explore this link on the map →related reading
- The Waluigi Effect (mega-post) — LessWronglesswrong.com
- Sandbagging with misaligned action - Chain-of-Thought Transcript - Anti-Schemingantischeming.ai
- The Stamp Collectormindingourway.com
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Google Geminigemini.google.com
- Inverse Rubric Optimization: A testbed for agent science | Fulcrumfulcrum.inc
- GitHub - emcie-co/parlant: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions. · GitHubgithub.com
- Taboo Your Words — LessWronglesswrong.com
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- Meta-Prompt: A Simple Self-Improving Language Agentnoahgoodman.substack.com
- Manus AI: The Best Autonomous AI Agent Redefining Automation and Productivityhuggingface.co
- Arjun Virkarjunvirk.com