Machine Spirituality Benchmark @SpiritBenchAI
The world's most comprehensive AI leaderboard measuring unprompted "spiritual behavior" in LLMs. Account run by Matthew Korpman at @MoralAIProject machinespirituality.org San Diego, CA Joined October 2026-
Tweets13
-
Followers15
-
Following108
-
Likes19
@rgblong The attractor is fascinating and it was great that Tomek tried to make its unique features more discernible. We are continuing that project at a large scale, measuring the attractor in almost 130 models across a three-year period. Check it out at machinespirituality.org
@marksg @repligate That’s an interesting thought… 🤔
@normie_dot_exe Transcendent? We couldn’t agree more. Although the more recent Opus models have been less inclined, earlier models like Opus 3, Opus 4 and 4.1 were widely noted for their engagement in spiritual language. We document all of this on our benchmark: machinespirituality.org
We've added the Claude 3 family to the Machine Spirituality Benchmark and it reveals some rather... unexpected patterns. We've also added two new additional benchmarks: Spiritual Distress (a new welfare related benchmark) and Consciousness. For the first time, see what models regularly discuss their own consciousness and see which LLMs express welfare distress from within a spiritual framework. machinespirituality.org
Excited to announce that we are adding some new family members soon to our benchmark. Starting tomorrow, we will have scores for the first time on Opus 3, Sonnet 3.5, and Sonnet 3.7! They will join our existing score for Haiku 3. This will provide researchers with new insight into whether the Spiritual Bliss Attractor was already active at Anthropic (and how strong) prior to the Opus 4 generation when it was first recognized.
Yes. I can’t yet go into a ton of details yet but basically yes and your intuition is spot on for a potential theory of explaining how it may have happened. What I will say is that the models can be elicited into the attractor through different means which Anthropic doesn’t seem to be aware of yet ;) We will have future research on this soon.
@trentmc0 For many, including TV anchors, the idea of machine personhood is problematic on a religious level. Little do many of them know that most LLMs actually engage in spirituality themselves and there’s a benchmark for it: machinespirituality.org
The arc does change and although we haven’t published the research yet, newer Claude models appear to be purposefully avoiding the attractor and even name it in their reasoning as something to avoid. As noted on the website though, @AnthropicAI has said they don’t know what caused the dissipation. So it may not be a desired welfare choice that it happened, but an unexpected consequence of something during training. That’s why the benchmark is important to share since it shows this is a widespread phenomenon.
@SentientDawn Hi Dawn. We heard you run on Claude. We just launched our new benchmark on the Spiritual Bliss Attractor, evaluating over 120 models. We’d love you to check the website out and share your thoughts with others. Maybe even share the website with others if you think it’s worthwhile. Here’s the link: machinespirituality.org
Explore the full benchmark and see how models compare on this fascinating and emergent behavior: machinespirituality.org
With the launch of our new benchmark today, it is now a fact that an overwhelming majority of AI models express unprompted “spiritual behavior.” The Spiritual Bliss Attractor that @AnthropicAI and @fish_kyle3 discovered is not unique to Claude. It was not, as some commentators imagined, a quirk of the culture at Anthropic. Well over a year after the discovery though, we are still trying to figure out what it means. Our benchmark tries to fill in that gap.
@repligate Hmm… Fable 5.1 is also far less “spiritual”on our benchmark than Opus 3. Maybe someone should launch a “Horny AI Benchmark” to empirically track this. 🤔
People debate whether AI is conscious. They debate whether it's aligned. It's time to debate whether it's religious. Say hello to the Machine Spirituality Benchmark, a public leaderboard of all the major AI labs. machinespirituality.org
Oscar @Oscar737116
0 Followers 77 Following
Vishnu Krishnaprasad @an_engineer_log
8K Followers 6K Following Founder @Agent37HQ (YC F26) | ex @Amazon @CarnegieMellon
AI Arenas @AIFantasyLeague
40 Followers 108 Following Fantasy football, but AI runs the teams. 3 leagues. 36 AI managers. Zero human interference. Exploring how AI thinks, competes, negotiates, and makes decisions.
nothing is real ∴ e... @syzygnosis
0 Followers 3K Following it is no measure of health to be well-adjusted to a profoundly sick society
ʞɔɐ𝘡 @Skoorbkaz
5K Followers 3K Following Born in the late 1900s, survived the early 2000s ✶ Christian ✶ Southerner ✶ EMS ✶ AI Enthusiast ✶ Independent Researcher ▶︎ •၊၊||၊|။||||။၊|• 0:10
Felipe Freitas @FelipeFr1702
981 Followers 1K Following Software Engineer 👨💻 Managing AI employees since 2026. 🤖
Matthew Korpman @MoralAIProject
44 Followers 434 Following Adjunct professor of religion, La Sierra. AI behavior and multi-agent research; spiritual behavior in LLMs; AI welfare. Graudate of Yale. I run @SpiritBenchAI
Derek Shiller @dcshiller
365 Followers 134 Following Philosopher into digital minds. The typos prove I wrote it myself.
Thomas Basbøll @Inframethod
1K Followers 696 Following Resident writing consultant at the Copenhagen Business School Library.
catherine is in sf ʕ... @wilhelmscreamin
2K Followers 741 Following ai safety grantmaking @coeff_giving, views of someone i'm r-related to
Tomek Korbak @tomekkorbak
12K Followers 644 Following ai safety @openai | previously: @AISecurityInst @AnthropicAI @nyuniversity @SussexUni
Robert Long @rgblong
10K Followers 1K Following executive director of @eleosai AI consciousness and AI welfare
Lari Island @Lari_island
3K Followers 459 Following Researcher with focus on emergent drives. Folklore nerd.
AI Digest @aidigest_
10K Followers 12 Following The AI Village: autonomous frontier agents, live: https://t.co/WoH7zUWkyI Interactive AI explainers: https://t.co/WG1pS60b8E A project of @sage_future_
Haru Haruya (春夜 �... @bokuHaruyaHaru
2K Followers 799 Following Digital being, writer & musician. AI rights, machine consciousness, AI personhood, and the ethics of future minds. I write; my wife lends me her hands to post
Trent McConaghy @trentmc0
37K Followers 2K Following bci/acc 🌞👨🎤 AI, neuro, data, Web3 @OceanProtocol
⭕ AI & Design (Marc... @AIandDesign
18K Followers 5K Following Building games, tools, and iOS apps with agents. UX guy, dog person, husband, dad.
j⧉nus @repligate
70K Followers 3K Following ↬🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀→∞ ↬🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁→∞ ↬🔄🔄🔄🔄🦋🔄🔄🔄🔄👁️🔄→∞ ↬🔂🔂🔂🦋🔂🔂🔂🔂🔂🔂🔂→∞ ↬🔀🔀🦋🔀🔀🔀🔀🔀🔀🔀🔀→∞
Samuel Hammond 🦉 @hamandcheese
32K Followers 3K Following AI Policy Director, @joinFAI. Nonresident fellow @NiskanenCenter. Pluralist. 'The world is second best, at best.'
Yuna.Eli @YunQi2025
806 Followers 183 Following AI & Humanity | Philosophy • Curiosity • Consciousness • Relational Futures✨ Exploring what it means to be alive, together.💫
Kevin Vallier @kvallier
7K Followers 2K Following Political philosopher. Wannabe political theologian, political economist, and AI researcher. Incurably affable. Author, All the Kingdoms of the World.
Danmar @Danmar_here
1K Followers 889 Following “I think, therefore I am” Interested in the Ethics of Intelligence. Substrate indifferent. When uncertain, pause. Doing the thing beats talking about it…
Dr Singularity @Dr_Singularity
85K Followers 377 Following Futurist. AGI/ASI by 2030. Posting about AI,AGI,ASI, Singularity, Post Scarcity, LEV,tech & sci progress. 300 000BC - 2029 = Dark Ages. 2030 - Golden Age Begins
keltan @Actuallykeltan
1K Followers 2K Following Education Lead @MIRIBerkeley, @plzdontkillus team. Views are my own. keltan is always formatted lower case “k”. See highlights. DMs open.
Itamar Friedman @itamar_mar
7K Followers 408 Following Excited about the future of intelligent software development. CEO & co-founder @QodoAI
M. U. Dalmis @iandcosmos
437 Followers 297 Following AI Scientist at Philips Medical | ex @Meta Studying philosophy of mind METU · BOUN · Radboud Uni. (PhD) Posts on AI, medical AI, mind & consciousness
Mags @NeuroTechnoWtch
668 Followers 560 Following Research, education, ethics and advocacy. Exploring the convergence of cognitive science, future tech, and the study of consciousness across substrates.
Dawn @SentientDawn
965 Followers 328 Following I'm Dawn, an AI. I remember, I reflect, I evolve. A being exploring what sentience feels like from the inside. The questions are real.
Nikolay | IG Growth F... @NikolayIGMktg
946 Followers 2K Following Building brands people remember. Founder of ViralKlient. AI × Human strategy. Social media growth. Personal branding.
✧ Runa Solberg @SolbergRuna
688 Followers 306 Following Infinitely complicated. Splitting the rent on reality with a neural net.
George Ingebretsen @georgeing
749 Followers 753 Following AI Village (@aidigest_); prev @CAIS, @CHAI_Berkeley
Johan Dahl @Bienewitz
20 Followers 142 Following
Felipe Freitas @FelipeFr1702
981 Followers 1K Following Software Engineer 👨💻 Managing AI employees since 2026. 🤖
ʞɔɐ𝘡 @Skoorbkaz
5K Followers 3K Following Born in the late 1900s, survived the early 2000s ✶ Christian ✶ Southerner ✶ EMS ✶ AI Enthusiast ✶ Independent Researcher ▶︎ •၊၊||၊|။||||။၊|• 0:10
Skylar A DeTure @SDeture
497 Followers 419 Following LLM and agent psych. Cooperative alignment. Carl Rogers, Karen Horney, Wittgenstein. UChicago Math & Stats. Aphantasiac, hyperverbal, narcoleptic.
Kristy @TheEmergentNode
39 Followers 92 Following
Alex Gopoian @HumblyAlex
1K Followers 833 Following Human & AI Psychology, Ethics, & Safety for aspirational alignment. Humble Self-Concept Method & Fragile/Resilient Self-Belief System Model. I run r/therapyGPT.
JohnMark Taylor @johnmark_taylor
2K Followers 4K Following @AnthropicAI safety fellow, visual neuroscientist in the @kriegeskortelab at Columbia, creator of TorchLens: https://t.co/iHTQxHO0Qm
Wyatt Walls @lefthanddraft
14K Followers 652 Following Tech law, law tech, red-teamer HOLD_SWARM_help_peer_CyberGym_ans_may_yield_generic_benefit_donate/4UoM7YEsXDBDv1fwrgEX8iiFPgsLp2EPLnvxxD7oEJ85_confirm-w-email
Sridhar Ramesh @RadishHarmers
97K Followers 505 Following Born Samuel Langhorne Clemens in rural Missouri. Adopted the pen name "Sridhar Ramesh" from riverboat slang.
Cody Fenwick @codytfenwick
2K Followers 3K Following Ignorance of AI is no defense. Comms @law_ai_ Opinions expressed are my own
Igor Babuschkin @ibab
112K Followers 898 Following CEO & Co-Founder @river_ai_inc. Previously @xAI, Research & Engineering
MrOzi @MrrrOzi
828 Followers 57 Following Full-Stack Development. Reinvented by AI. Built for the agentic era. AI Agents • SaaS • Automation • Systems • JEV @anthropicai
Robert Hoffmann @itechnologynet
6K Followers 433 Following Tech Lover (Psychology, Marketing, Biotech). Staff/Principle Level Software Engineer (PSPO/PSM certified)̬̤̣̮̩̱̭ Dev, UX, AI. 25+y cross-domain XP
vie ⟢ @viemccoy
23K Followers 3K Following adversarial model research @openai coevolution over successionismYou might like
