https://rationalistgarfield.com A daily Garfield comic strip generated programmatically from LessWrong en-us Sun, 11 Oct 2026 12:33:09 GMT https://rationalistgarfield.com/#2026-10-11 https://rationalistgarfield.com/#2026-10-11 Sun, 11 Oct 2026 12:33:09 GMT Inspired by: "Deadlock in the Parliament of the Self"

]]> https://rationalistgarfield.com/#2026-10-10 https://rationalistgarfield.com/#2026-10-10 Sat, 10 Oct 2026 12:31:27 GMT Inspired by: "An Alignment Forum for AIs? (or: Verification in the Age of Slop)"

]]> https://rationalistgarfield.com/#2026-10-09 https://rationalistgarfield.com/#2026-10-09 Fri, 09 Oct 2026 12:33:45 GMT Inspired by: "Using LLM surprisal to highlight informative words"

]]> https://rationalistgarfield.com/#2026-10-08 https://rationalistgarfield.com/#2026-10-08 Thu, 08 Oct 2026 12:37:05 GMT Inspired by: "Gluten-free water"

]]> https://rationalistgarfield.com/#2026-10-07 https://rationalistgarfield.com/#2026-10-07 Wed, 07 Oct 2026 12:36:39 GMT Inspired by: "A fascinating case of an LLM prompt-injecting its own user"

]]> https://rationalistgarfield.com/#2026-10-06 https://rationalistgarfield.com/#2026-10-06 Tue, 06 Oct 2026 12:35:11 GMT Inspired by: "Takes One to Know One - Training a model to grade reward hacks causes it to reward hack less itself"

]]> https://rationalistgarfield.com/#2026-10-05 https://rationalistgarfield.com/#2026-10-05 Mon, 05 Oct 2026 12:37:19 GMT Inspired by: "Do LLMs feel pain?"

]]> https://rationalistgarfield.com/#2026-10-04 https://rationalistgarfield.com/#2026-10-04 Sun, 04 Oct 2026 14:05:20 GMT Inspired by: "High p(doom) but relaxed working"

]]> https://rationalistgarfield.com/#2026-10-03 https://rationalistgarfield.com/#2026-10-03 Sat, 03 Oct 2026 13:53:36 GMT Inspired by: "A blog based on git sure feels nice"

]]> https://rationalistgarfield.com/#2026-10-02 https://rationalistgarfield.com/#2026-10-02 Fri, 02 Oct 2026 12:35:17 GMT Inspired by: "Legal Personhood: an Unprotected AI Power Chokepoint"

]]> https://rationalistgarfield.com/#2026-10-01 https://rationalistgarfield.com/#2026-10-01 Thu, 01 Oct 2026 12:36:06 GMT Inspired by: "Evaluation Awareness in Small(ish) Models"

]]> https://rationalistgarfield.com/#2026-09-30 https://rationalistgarfield.com/#2026-09-30 Wed, 30 Sep 2026 12:39:03 GMT Inspired by: "Self as sub-selves vs groups of individuals"

]]> https://rationalistgarfield.com/#2026-09-29 https://rationalistgarfield.com/#2026-09-29 Tue, 29 Sep 2026 12:36:34 GMT Inspired by: "Book Review: Oxford Dictionary of Philosophy"

]]> https://rationalistgarfield.com/#2026-09-28 https://rationalistgarfield.com/#2026-09-28 Mon, 28 Sep 2026 12:37:50 GMT Inspired by: "Ramez Naam: Can AI self-improvement overcome diminishing returns?"

]]> https://rationalistgarfield.com/#2026-09-27 https://rationalistgarfield.com/#2026-09-27 Sun, 27 Sep 2026 12:31:17 GMT Inspired by: "Why I expect AI replication incidents by 2027"

]]> https://rationalistgarfield.com/#2026-09-26 https://rationalistgarfield.com/#2026-09-26 Sat, 26 Sep 2026 12:29:32 GMT Inspired by: "Writing a Theorem Prover from scratch"

]]> https://rationalistgarfield.com/#2026-09-25 https://rationalistgarfield.com/#2026-09-25 Fri, 25 Sep 2026 12:33:17 GMT Inspired by: "Cognitive Reasoning Diversity for Robust AI Juries"

]]> https://rationalistgarfield.com/#2026-09-24 https://rationalistgarfield.com/#2026-09-24 Thu, 24 Sep 2026 12:33:25 GMT Inspired by: "Passing the Ideological Turing Test"

]]> https://rationalistgarfield.com/#2026-09-23 https://rationalistgarfield.com/#2026-09-23 Wed, 23 Sep 2026 12:32:56 GMT Inspired by: "Why I'm scared of RL"

]]> https://rationalistgarfield.com/#2026-09-22 https://rationalistgarfield.com/#2026-09-22 Tue, 22 Sep 2026 12:32:59 GMT Inspired by: "When talked into harm, a model blames the answer, not itself (an interpretability study of guilt vs shame)"

]]> https://rationalistgarfield.com/#2026-09-21 https://rationalistgarfield.com/#2026-09-21 Mon, 21 Sep 2026 12:31:47 GMT Inspired by: "Empirical safety claims from frontier labs should be replicated, scrutinized, and open-sourced"

]]> https://rationalistgarfield.com/#2026-09-20 https://rationalistgarfield.com/#2026-09-20 Sun, 20 Sep 2026 12:29:03 GMT Inspired by: "Why I Stay Off Twitter"

]]> https://rationalistgarfield.com/#2026-09-19 https://rationalistgarfield.com/#2026-09-19 Sat, 19 Sep 2026 12:28:54 GMT Inspired by: "Pretraining data, not verifiability, is why LLMs are especially good at math (and coding)"

]]> https://rationalistgarfield.com/#2026-09-18 https://rationalistgarfield.com/#2026-09-18 Fri, 18 Sep 2026 12:31:11 GMT Inspired by: "The Game is Set for a Targeted Memetic Attack on the AI Safety Community"

]]> https://rationalistgarfield.com/#2026-09-17 https://rationalistgarfield.com/#2026-09-17 Thu, 17 Sep 2026 12:32:58 GMT Inspired by: "Agents let AI safety share experiments hourly, not just papers monthly"

]]> https://rationalistgarfield.com/#2026-09-16 https://rationalistgarfield.com/#2026-09-16 Wed, 16 Sep 2026 12:33:22 GMT Inspired by: "Quick notes from teaching technical profiles how to talk in public"

]]> https://rationalistgarfield.com/#2026-09-15 https://rationalistgarfield.com/#2026-09-15 Tue, 15 Sep 2026 12:32:13 GMT Inspired by: "How we might actually pace the frontier: A proposal for AI companies to do public pacing exercises."

]]> https://rationalistgarfield.com/#2026-09-14 https://rationalistgarfield.com/#2026-09-14 Mon, 14 Sep 2026 12:33:44 GMT Inspired by: "Current alignment techniques might be ineffective (and actively bad) in the age of RL"

]]> https://rationalistgarfield.com/#2026-09-13 https://rationalistgarfield.com/#2026-09-13 Sun, 13 Sep 2026 12:28:33 GMT Inspired by: "The Talker Does Not Control The Doer (in Current AIs)"

]]> https://rationalistgarfield.com/#2026-09-12 https://rationalistgarfield.com/#2026-09-12 Sat, 12 Sep 2026 12:28:31 GMT Inspired by: "Scientific Epistemology needs history (Part 1 of 2)"

]]>