https://aisafety.tokyo/benkyoukai daily 0.75 2026-03-15 https://aisafety.tokyo/benkyoukai/ai-lab-commitments monthly 0.5 2026-03-15 https://aisafety.tokyo/benkyoukai/ai-control monthly 0.5 2026-03-04 https://aisafety.tokyo/benkyoukai/japan-ai-safety-institute monthly 0.5 2025-12-31 https://aisafety.tokyo/benkyoukai/emergent-misalignment-from-reward-hacking monthly 0.5 2025-12-31 https://aisafety.tokyo/benkyoukai/emergent-introspective-awareness monthly 0.5 2025-12-02 https://aisafety.tokyo/benkyoukai/if-anyone-builds-it monthly 0.5 2025-11-07 https://aisafety.tokyo/benkyoukai/best-of-n-jailbreaking monthly 0.5 2025-10-05 https://aisafety.tokyo/benkyoukai/japan-ai-promotion-act monthly 0.5 2025-08-07 https://aisafety.tokyo/benkyoukai/recursive-self-improvement monthly 0.5 2025-08-07 https://aisafety.tokyo/benkyoukai/gradual-disempowerment monthly 0.5 2025-07-06 https://aisafety.tokyo/benkyoukai/ai-2027 monthly 0.5 2025-06-05 https://aisafety.tokyo/benkyoukai/tracing-the-thoughts-of-a-large-language-model monthly 0.5 2025-05-03 https://aisafety.tokyo/benkyoukai/universal-ai-maximizes-variational-empowerment monthly 0.5 2025-04-07 https://aisafety.tokyo/benkyoukai/measuring-feature-sensitivity-using-dataset-filtering monthly 0.5 2025-03-02 https://aisafety.tokyo/benkyoukai/alignment-faking-in-large-language-models monthly 0.5 2025-02-07 https://aisafety.tokyo/benkyoukai/evaluating-the-world-model-implicit-in-a-generative-model monthly 0.5 2025-01-01 https://aisafety.tokyo/benkyoukai/against-almost-every-theory-of-impact-of-interpretability monthly 0.5 2024-12-05 https://aisafety.tokyo/benkyoukai/technical-research-and-talent-is-needed-for-effective-ai-governance monthly 0.5 2024-09-25 https://aisafety.tokyo/benkyoukai/ai-alignment-with-changing-and-influenceable-reward-functions monthly 0.5 2024-08-09 https://aisafety.tokyo/benkyoukai/scaling-and-evaluating-sparse-autoencoders monthly 0.5 2024-08-01 https://aisafety.tokyo/benkyoukai/situational-awareness monthly 0.5 2024-07-10 https://aisafety.tokyo/benkyoukai/japan-ai-frontier monthly 0.5 2024-06-24 https://aisafety.tokyo/benkyoukai/is-gpt-conscious monthly 0.5 2024-06-20 https://aisafety.tokyo/benkyoukai/llm-emergent-abilities monthly 0.5 2024-06-17 https://aisafety.tokyo/benkyoukai/aiif-masterclass-bpmn monthly 0.5 2024-06-09 https://aisafety.tokyo/benkyoukai/data-governance monthly 0.5 2024-05-27 https://aisafety.tokyo/benkyoukai/ai-and-copyright monthly 0.5 2024-05-21 https://aisafety.tokyo/benkyoukai/aiif-masterclass-synthetic-data monthly 0.5 2024-05-14 https://aisafety.tokyo/benkyoukai/aiif-masterclass-ai-capabilities-and-evaluations monthly 0.5 2024-05-08 https://aisafety.tokyo/benkyoukai/guest-ram-rachum-presents monthly 0.5 2024-05-08 https://aisafety.tokyo/benkyoukai/ml-benkyoukai-kolmogorov-arnold-networks monthly 0.5 2024-05-08 https://aisafety.tokyo/benkyoukai/aiif-masterclass-ai-use-2 monthly 0.5 2024-05-01 https://aisafety.tokyo/benkyoukai/on-the-conversational-persuasiveness-of-llms monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif-masterclass-business-landscape monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/ml-benkyoukai-more-agents-is-all-you-need monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/the-gladstone-ai-reports-drafted-ai-bill-and-ai-trajectories monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif-masterclass-ai-inside monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/structured-world-representations-in-maze-solving-transformers monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/a-hormetic-approach-to-the-value-loading-problem monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/language-models-can-explain-neurons-in-language-models monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/humans-who-are-not-concentrating-are-not-general-intelligences monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif-masterclass-ai-rules monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif-weekly-masterclass-ai-use monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/aiif-weekly-masterclass-ai-landscapes monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/elon-musk-vs-open-ai monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/fundamental-limitations-of-reinforcement-learning-from-human-feedback monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/the-nist-crada-agreement monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/cyborgism monthly 0.5 2024-04-18 https://aisafety.tokyo/benkyoukai/ml-benkyoukai-direct-preference-optimization monthly 0.5 2024-03-21 https://aisafety.tokyo/benkyoukai/pinemaqjvtqzb28q6ttanxf437rx8d monthly 0.5 2024-02-13 https://aisafety.tokyo/benkyoukai/why-agent-foundations monthly 0.5 2024-02-13 https://aisafety.tokyo/benkyoukai/benkyoukai-special-event-mamba monthly 0.5 2024-01-18 https://aisafety.tokyo/benkyoukai/m3tbqck79w5ajyc2bprfe4j82v1ffx monthly 0.5 2024-01-18 https://aisafety.tokyo/benkyoukai/6eeplofdwv6wa7fz5ap7opko2qwahh monthly 0.5 2024-01-11 https://aisafety.tokyo/benkyoukai/22ug1rfvfvldr1uhlnhqt7pb8t88a2 monthly 0.5 2024-01-05 https://aisafety.tokyo/benkyoukai/the-gemini-report monthly 0.5 2023-12-26 https://aisafety.tokyo/benkyoukai/aiokrnqc8bfhy75vj378xun153sc3y monthly 0.5 2023-12-26 https://aisafety.tokyo/benkyoukai/7ft4xh7pv0ewn3e63xkij1db6kbgqj monthly 0.5 2023-12-01 https://aisafety.tokyo/benkyoukai/the-openai-debacle-the-implications-and-future-impact-on-agi-development monthly 0.5 2024-02-13 https://aisafety.tokyo/benkyoukai/2urmanimcsu9yj56twpscdi3x16ucj monthly 0.5 2023-11-16 https://aisafety.tokyo/benkyoukai/what-is-bayesian-machine-learning monthly 0.5 2023-11-16 https://aisafety.tokyo/benkyoukai/the-executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence monthly 0.5 2023-11-05 https://aisafety.tokyo/benkyoukai/process-supervision monthly 0.5 2023-10-31 https://aisafety.tokyo/benkyoukai/887kjr6mkxeabvof2pr6typz8xilry monthly 0.5 2023-10-23 https://aisafety.tokyo/benkyoukai/representation-engineering monthly 0.5 2023-10-15 https://aisafety.tokyo/benkyoukai/towards-monosemanticity monthly 0.5 2023-10-10 https://aisafety.tokyo/benkyoukai/toy-models-of-superposition monthly 0.5 2023-10-02 https://aisafety.tokyo/benkyoukai/developmental-interpretability monthly 0.5 2023-09-22 https://aisafety.tokyo/benkyoukai/reasoning-or-reciting monthly 0.5 2023-09-19 https://aisafety.tokyo/benkyoukai/i7fvjrv3jc0ncbieqj0cdwlk2h8zua monthly 0.5 2023-09-11 https://aisafety.tokyo/benkyoukai/introduction-to-neuromorphic-computing monthly 0.5 2023-09-01 https://aisafety.tokyo/benkyoukai/corrigibility monthly 0.5 2023-08-14 https://aisafety.tokyo/benkyoukai/any-deep-relu-network-is-shallow monthly 0.5 2023-08-04 https://aisafety.tokyo/benkyoukai/the-limit-is-not-the-sequence monthly 0.5 2023-08-02 https://aisafety.tokyo/benkyoukai/putting-numbers-to-pdoom monthly 0.5 2023-07-20 https://aisafety.tokyo/benkyoukai/symbolic-distillation monthly 0.5 2023-07-17 https://aisafety.tokyo/benkyoukai/are-we-missing-the-forest-for-the-gptrees monthly 0.5 2023-07-11 https://aisafety.tokyo/benkyoukai/editing-activations-for-fun-and-profit monthly 0.5 2023-07-03 https://aisafety.tokyo/benkyoukai/xr8d6rfm1v3xi84tqyu0nv8dqjlr58 monthly 0.5 2023-06-22 https://aisafety.tokyo/benkyoukai/lora-why-does-fine-tuning-work monthly 0.5 2023-06-16 https://aisafety.tokyo/benkyoukai/wgwjkml2r2s0m46uh2ab156ylu0qgr monthly 0.5 2023-06-08 https://aisafety.tokyo/benkyoukai/natural-selection-favours-ais-over-humans monthly 0.5 2023-06-05 https://aisafety.tokyo/benkyoukai/causal-scrubbing monthly 0.5 2023-05-25 https://aisafety.tokyo/benkyoukai/diplomacy monthly 0.5 2023-05-23 https://aisafety.tokyo/benkyoukai/shard-theory monthly 0.5 2023-05-23 https://aisafety.tokyo/benkyoukai/are-emergent-abilities-of-large-language-models-a-mirage monthly 0.5 2023-05-10 https://aisafety.tokyo/benkyoukai/othello-transformers-have-emergent-world-models monthly 0.5 2023-04-24 https://aisafety.tokyo/benkyoukai/transformer-feedforward-layers-are-key-value-memories monthly 0.5 2023-04-18 https://aisafety.tokyo/benkyoukai/safety-for-lawyers monthly 0.5 2023-04-11 https://aisafety.tokyo/benkyoukai/simulators monthly 0.5 2023-04-03 https://aisafety.tokyo/benkyoukai/6sxxe99wgbs6vq87y6hyv70rkk1jz3 monthly 0.5 2023-03-28 https://aisafety.tokyo/benkyoukai/induction-heads monthly 0.5 2023-03-17 https://aisafety.tokyo/benkyoukai/functional-decision-theory monthly 0.5 2023-03-15 https://aisafety.tokyo/benkyoukai/revisiting-the-aia monthly 0.5 2023-03-04 https://aisafety.tokyo/benkyoukai/asymmetric-shapley-values-incorporating-causal-knowledge-into-model-agnostic-explainability monthly 0.5 2023-02-27 https://aisafety.tokyo/benkyoukai/transformers-learn-in-context-by-gradient-descent monthly 0.5 2023-02-26 https://aisafety.tokyo/benkyoukai/097mt265ppy3urnu60j1b1h9uskugm monthly 0.5 2023-05-23 https://aisafety.tokyo/benkyoukai/the-eu-ai-act monthly 0.5 2023-02-01 https://aisafety.tokyo/benkyoukai/what-everyone-in-technical-alignment-is-doing-and-why-chai-cais-sam-bowman-and-miri monthly 0.5 2023-01-30 https://aisafety.tokyo/benkyoukai/what-everyone-in-technical-alignment-is-doing-and-why monthly 0.5 2023-01-30 https://aisafety.tokyo/benkyoukai/discovering-agents-etfzl monthly 0.5 2023-02-26 https://aisafety.tokyo/benkyoukai/discovering-agents monthly 0.5 2023-01-30 https://aisafety.tokyo/events daily 0.75 2025-12-27 https://aisafety.tokyo/events/tais-2025 monthly 0.5 2025-01-15 https://aisafety.tokyo/events/acx-tokyo-the-extinction-tournament monthly 0.5 2023-11-06 https://aisafety.tokyo/events/tais-2024 monthly 0.5 2024-05-01 https://aisafety.tokyo/events/alife-2023-human-values-and-artificial-agency monthly 0.5 2024-05-01 https://aisafety.tokyo/events/conversational-ai-safety-is-ai-as-dangerous-as-pandemics monthly 0.5 2023-06-16 https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/d57a884c-8ff3-44c3-9df0-895156dd969e/craiyon_213049_a_robot_fighting_a_giant_bacterium__comic_book.png Events - Conversational AI Safety: Is AI as dangerous as pandemics? AIはパンデミックと同じくらい危険なのか？ - Make it stand out イメージはcraiyon.comに起こされました https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/97283d35-3400-41c5-af13-d981b91aea35/craiyon_212832_a_robot_fighting_a_giant_bacterium__comic_book.png Events - Conversational AI Safety: Is AI as dangerous as pandemics? AIはパンデミックと同じくらい危険なのか？ - Make it stand out Image generated by craiyon.com https://aisafety.tokyo/events/conversational-ai-safety-gpt-4 monthly 0.5 2023-04-10 https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/bea41a68-3d16-48c9-bd43-d6edcc211721/111032354_a_misaligned_super_intelligence__a_robot_playing_chess__digital_art.jpg Events - Conversational AI Safety: GPT-4 - Make it stand out イメージはDreamStudio betaで起こしました https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/0e20b749-0b8f-49e0-8266-d9c9ad3c21eb/4147202664_a_human_shaped_colossus_made_of_books__a_book_golem_towering_in_the_sky__fear__uncertainty__digital_.jpg Events - Conversational AI Safety: GPT-4 - Make it stand out Image generated using DreamStudio beta https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/d95b5f57-d3f8-4aab-898d-1131189bfa9d/no25.jpg Events - Conversational AI Safety: GPT-4 - Make it stand out Access instructions for the venue. https://aisafety.tokyo/events/tedx-otemachi monthly 0.5 2023-03-04 https://aisafety.tokyo/benkyoukai-jp daily 0.75 2026-02-01 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course-unit2 monthly 0.5 2026-01-19 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course-unit4 monthly 0.5 2026-01-27 https://aisafety.tokyo/benkyoukai-jp/life30--pw2rn monthly 0.5 2026-01-06 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course-unit1-imagining-a-better-future-pzmwa-kb5wg monthly 0.5 2026-01-06 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course-unit1-imagining-a-better-future-pzmwa monthly 0.5 2025-12-30 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course-unit1-imagining-a-better-future monthly 0.5 2025-12-30 https://aisafety.tokyo/benkyoukai-jp/agi-strategy-course monthly 0.5 2025-12-30 https://aisafety.tokyo/benkyoukai-jp/wk9krgocy0ird8e0dakllf9j099tr5 monthly 0.5 2025-12-30 https://aisafety.tokyo/benkyoukai-jp/iabied monthly 0.5 2026-01-13 https://aisafety.tokyo/home daily 1.0 2024-08-07 https://aisafety.tokyo/about daily 0.75 2025-10-11 https://images.squarespace-cdn.com/content/v1/63d759621ec3d51b882e956f/44313854-92e7-4814-8877-e5edbd98192f/benkyoukai.jpg