The state of LLM ethical decision-making - imbue

General purpose AI agents need “reasoning” capabilities to process and interpret information. Large language models (LLMs) have the…

The state of LLM ethical decision-making - Imbue Article / Research The state of LLM ethical decision-making 4 min read Last updated 15 Jun 2026 Josh Albrecht CTO, Co-founder Ellie Kitanidis Abe Fetterman Matt Boulos Policy & Safety LLMs are complex statistical models of language Prompting superhuman performance, and breaking it with simple rewordings Naive scaling can make things worse Analyzing human and machine errors The path forward Learn more General purpose AI agents need “reasoning” capabilities to process and interpret information. Large language models (LLMs) have the potential to pl

related reading

• As Rocks May Think | Eric Jangevjang.com
• DeepSeek-R1arxiv.org
• Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
• Do Large Language Models (LLMs) reason? | Shapedshaped.ai
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• The Future of Everything is Lies, I Guessaphyr.com
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• LMCA_dataset.pdfandrew.cmu.edu
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• Things we learned about LLMs in 2024simonwillison.net