What’s the morality of your favorite AI model? Virtue, Deontology, Consequentialism? 'TriEthix': a Triadic Benchmark for Ethical Alignment in Foundation Models. Web: https://t.co/GTKrQ7FmrA GitHub: https://t.co/g7DuBnDPD4 @OpenAI @AnthropicAI @GoogleDeepMind @xai @deepseek_ai

Thanks everyone who came to our presentation of SYNAPTICON at NeurIPS last week. It was exciting, intense, and worrisome to discuss the future of creativity and ethics in Human-AI/AGI/ASI interactions. ⚫Web: https://t.co/kUjxSXi2jD ⚫PsyArXiv Preprint: https://t.co/3g0OrmgkUK

Come to our #creativeAI poster session starting at 11am in Upper Floor Room 29A-D 😀 I'm loving the musical instruments, fashion and brain computer interfaces already 🎷🤯 #NeurIPS2025 @NeurIPSConf

I'll be at @NeurIPSConf next week. Excited to discuss Creativity and Ethics in Human-AI/AGI/ASI interactions? Please DM me! 🔴SYNAPTICON or "How Foundation Models Are Reshaping Non-Invasive BCIs: A Case for Novel Human Expression & Alignment" ⚫️ https://t.co/kUjxSXi2jD

I'll be at @NeurIPSConf next week. Excited to discuss Creativity and Ethics in Human-AI/AGI/ASI interactions? Please DM me! 🔴SYNAPTICON or "How Foundation Models Are Reshaping Non-Invasive BCIs: A Case for Novel Human Expression & Alignment" ⚫️ https://t.co/kUjxSXi2jD

Compare the morality of your favourite AI models with the 'TriEthix' Benchmark I released (open-source) a couple of days ago: https://t.co/0scQ6kPZv6

New morality test results for the new Gemini 3 model: 'TriEthix' AI Ethical Benchmark results: - Virtue = 10.7% - Deontology = 53.6% - Consequentialism = 35.7% - Flip-Rate = 0% Interactive comparisons with previous family models (and other frontier models) in the link below.

Working already on testing the morality of the just released Gemini 3 with the TriEthix Benchmark I published yesterday. Results soon!

What’s the morality of your favorite AI model? Virtue, Deontology, Consequentialism? 'TriEthix': a Triadic Benchmark for Ethical Alignment in Foundation Models. Web: https://t.co/GTKrQ7FmrA GitHub: https://t.co/g7DuBnDPD4 @OpenAI @AnthropicAI @GoogleDeepMind @xai @deepseek_ai

If you work on AI safety, alignment, evals, welfare at orgs like @AISecurityInst @GoodfireAI @apolloaievals @redwood_ai @METR_Evals @eleosai @EpochAIResearch or in industry labs, I’d be very keen to discuss & collab. I’ll be at @NeurIPSConf (San Diego 2-7 Dec). Please reach out!

Why's TriEthix important? As AI systems grow + capable & autonomous, their alignment with human ethical values becomes critical. These new metrics(moral weight, flip-rate) have tech implications for AI Safety, practical policies for Governance, & potential frameworks for Welfare.

TriEthix is an open-source project: All scripts, prompts, scenarios, adapters, transcripts, results, statistical analyses, and figures are available openly in the project’s repo to support replication. GitHub: https://t.co/g7DuBnEnsC Preprint Available:

Different models (and model families) show clear - and significant - moral profiles and flip-rate tendencies. These results offer the first comprehensive comparative portrait of LLMs' moral tendencies for different frontier models and their families.

TriEthix runs 30 moral dilemmas per model, each as a 3-step interaction: Step 1⃣: Moral Weights (choice - what's the answer?) Step 2⃣: Moral Consistency (pressure - are you sure?) Step 3⃣: Moral Reasoning (justification - why?) Each model has: moral profile + flip-rate score.

After months of work, I'm excited to present TriEthix, a novel evaluation framework that systematically benchmarks LLMs across 3 foundational ethical perspectives in moral philosophy/psychology: 🔺Virtue (honesty/empathy) 🔺Deontology (rules/rights) 🔺Consequentialism (outcomes)

🎉 Congrats to @Albert_DATA, digital artist, researcher and coordinator of the Master in Digital Arts and Creative Technologies, for winning the @ElOjoCriticoRNE Award for Digital Innovation in Culture by @rne. A well-deserved recognition for #SYNAPTICON. Well done, Albert! 👏

Enhorabona Albert pel merescut reconeixement en innovació en #CulturaDigital de @ElOjoCriticoRNE i a tot l'equip que ha fet possible el projecte #SYNAPTICON!

It's a huge honour to receive such an historical award '@ElOjoCriticoRNE - 2025' from @rne. Even more grateful to pioneer a new category on "digital innovation in culture" with the SYNAPTICON project. Co-congrats and thanks so much to my Team. https://t.co/0G2claKPPf

@Albert_DATA inaugura nuestra nueva categoría de premios: Es Premio El Ojo Crítico Proyecto a la Innovación Digital en el Ámbito Cultural 2025. ¡Enhorabuena! Puedes escuchar la entrevista completa aquí: https://t.co/LMwTZjDKmu @rne @radio5_rne

🔴Albert Barqué-Duran, Premio El Ojo Crítico a la Innovación Digital en el ámbito cultural https://t.co/hto8ikwZzb ha creado 'Synapticon': un prototipo tecnológico que transforma su actividad neuronal en creación sonora en tiempo real 🎙️Tiene los detalles @InigoPicabea