Shtetl-Optimized » Blog Archive » LLMs and self-referentiality
I woke up yesterday with the following thoughts, which are probably either obvious or dumb. A central thesis that many readers, including me, took from Douglas Hofstadter’s Gödel Escher Bach when y…
I woke up yesterday with the following thoughts, which are probably either obvious or dumb. A central thesis that many readers, including me, took from Douglas Hofstadter’s Gödel Escher Bach when young was that the secret of intelligence (and therefore, of AI) was going to have a lot to do with self-referentiality and “strange loops.” Even Roger Penrose’s The Emperor’s New Mind, which in some ways was the anti-GEB, ironically agreed with GEB about the fundamental importance of self-reference to the success or failure of the whole AI project. It claimed (incorrectly, in my view and in most…
saved by
related reading
- Can LLMs Introspect? A Reality Checkarxiv.org
- [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
- Lil'Loglilianweng.github.io
- Simulators — LessWronglesswrong.com
- LLM Daydreaming · Gwern.netgwern.net
- A Workaphile’s Apologymoalquraishi.wordpress.com
- Writing for LLMs So They Listen · Gwern.netgwern.net
- Can LLMs Critique and Iterate on Their Own Outputs? | Eric Jangevjang.com
- The Future of Everything is Lies, I Guessaphyr.com
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com