Taking LLMs Seriously (As Language Models) — LessWrong
This is my attempt to write down what I would be researching, if I were working directly with LLMs rather than doing Agent Foundations. (I'm open to collaboration on these ideas.) Machine Learning research can occupy different points on a spectrum between science and engineering: science-like research seeks to understand phenomena deeply, explain what's happening, provide models which predict results, etc. Engineering-like research focuses more on getting things to work, achieving impressive results, optimizing performance, etc. I think the scientific style is very important. However, the research threads here are more engineering-flavored: I'd like to see systems which get these ideas to work, because I think they'd be marginally safer, saving a few more worlds along the alignment difficulty spectrum. I think the forefront of AI capabilities research is currently quite focused on RL, which is an inherently more dangerous technology; part of what I hope to illustrate here is that there
x Taking LLMs Seriously (As Language Models) — LessWrong AI Frontpage 58 Taking LLMs Seriously (As Language Models) by abramdemski 9th Jan 2026 20 min read 9 58 This is my attempt to write down what I would be researching, if I were working directly with LLMs rather than doing Agent Foundations. (I'm open to collaboration on these ideas.) Machine Learning research can occupy different points on a spectrum between science and engineering: science-like research seeks to understand phenomena deeply, explain what's happening, provide models which predict results, etc. Engineering-like research foc
saved by
related reading
- I am worried about near-term non-LLM AI developments — LessWronglesswrong.com
- Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
- Writing for LLMs So They Listen · Gwern.netgwern.net
- LLM Daydreaming · Gwern.netgwern.net
- A Mechanistic Explanation of Prompt Injection (and why you should study roles) — LessWronglesswrong.com
- Against LLM Reductionism — LessWronglesswrong.com
- Thoughts on AI in academiatheinfinitesimal.substack.com
- Is Prosaic Alignment Research Useful If the First Takeover-Capable AI Is Not an LLM? — RedWronglw.shlegeris.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
- Productizing Large Language Modelsblog.replit.com
- LLMs for Alignment Research: a safety priority? — AI Alignment Forumalignmentforum.org