https://humancompatible.ai/https://humancompatible.ai/about/https://humancompatible.ai/bibliography/https://humancompatible.ai/blog/https://humancompatible.ai/blog/2022/02/09/how-platform-recommenders-work/https://humancompatible.ai/blog/2022/08/10/designing-societally-beneficial-reinforcement-learning-systems/https://humancompatible.ai/blog/2022/10/05/for-learning-in-symmetric-teams-local-optima-are-global-nash-equilibria/https://humancompatible.ai/blog/2023/07/28/even-superhuman-go-ais-have-surprising-failures-modes/https://humancompatible.ai/blog/2023/09/11/ai-regulation-stuart-russells-opening-statement-at-u-s-senate-hearing/https://humancompatible.ai/blog/2023/09/11/stuart-russell-testifies-on-ai-regulation-at-u-s-senate-hearing/https://humancompatible.ai/chai-internship-mentor-profiles/https://humancompatible.ai/chai2023/https://humancompatible.ai/chai2024/https://humancompatible.ai/contact/https://humancompatible.ai/donate/https://humancompatible.ai/jobs/https://humancompatible.ai/news/https://humancompatible.ai/news/2016/06/06/cooking_cats/https://humancompatible.ai/news/2016/08/29/chai/https://humancompatible.ai/news/2016/08/29/chai2/https://humancompatible.ai/news/2016/08/30/ai_risk/https://humancompatible.ai/news/2016/09/28/industry/https://humancompatible.ai/news/2016/11/01/ethics_ai/https://humancompatible.ai/news/2016/11/02/existenial_risk/https://humancompatible.ai/news/2017/02/11/anca_communicating_objectives/https://humancompatible.ai/news/2017/03/06/ai_with_people/https://humancompatible.ai/news/2017/03/11/montreal_declaration/https://humancompatible.ai/news/2017/05/17/ted_2017/https://humancompatible.ai/news/2017/08/08/anca_courteous_car/https://humancompatible.ai/news/2017/10/12/weird_working_robots/https://humancompatible.ai/news/2017/10/19/think_like_humans/https://humancompatible.ai/news/2017/11/12/slaughterbots/https://humancompatible.ai/news/2017/11/16/anca_robot_objectives/https://humancompatible.ai/news/2017/12/10/chai_openai_collab/https://humancompatible.ai/news/2017/12/12/bipartisan_ai_bill/https://humancompatible.ai/news/2018/01/06/schroeder_trusting_machines/https://humancompatible.ai/news/2018/02/01/ai_new_wmds/https://humancompatible.ai/news/2018/02/01/halpern_noisy_environment/https://humancompatible.ai/news/2018/02/05/anca_human_guidance/https://humancompatible.ai/news/2018/02/07/anca_human_values/https://humancompatible.ai/news/2018/02/26/anca_expressing_incapability/https://humancompatible.ai/news/2018/03/08/anca_robots_behaves/https://humancompatible.ai/news/2018/03/27/robots_express_fail/https://humancompatible.ai/news/2018/04/05/halpern_formal_blame/https://humancompatible.ai/news/2018/04/23/rohin_shah/https://humancompatible.ai/news/2018/05/31/anca_safe_robot/https://humancompatible.ai/news/2018/06/01/henry_kissenger/https://humancompatible.ai/news/2018/06/10/mech_transparency/https://humancompatible.ai/news/2018/07/02/thomas_automated-decisions/https://humancompatible.ai/news/2018/07/13/anca_model_explanations/https://humancompatible.ai/news/2018/07/13/daniel_hiearchy_rl/https://humancompatible.ai/news/2018/07/14/adam_rohin_inverse_reward/https://humancompatible.ai/news/2018/07/14/chai_goalsrl/https://humancompatible.ai/news/2018/07/15/adam_causal_entropy/https://humancompatible.ai/news/2018/07/16/bellman_curve/https://humancompatible.ai/news/2018/07/17/facebook_robots/https://humancompatible.ai/news/2018/07/25/halpern_cog_mech_culture/https://humancompatible.ai/news/2018/08/26/chai_miri_workshop/https://humancompatible.ai/news/2018/09/03/anca_achievements/https://humancompatible.ai/news/2018/09/03/anca_around_world/https://humancompatible.ai/news/2018/09/04/filan_teach/https://humancompatible.ai/news/2018/09/04/fisac_talks_conference/https://humancompatible.ai/news/2018/09/04/halpern_causal_judgements/https://humancompatible.ai/news/2018/09/04/halpern_past_talks/https://humancompatible.ai/news/2018/09/12/macaskill_ted_talk/https://humancompatible.ai/news/2018/09/21/eu_laws/https://humancompatible.ai/news/2018/10/09/privacy_policy_update/https://humancompatible.ai/news/2018/10/11/edward_felten/https://humancompatible.ai/news/2018/10/31/chai_conference_october_2018/https://humancompatible.ai/news/2018/10/31/chai_twitter/https://humancompatible.ai/news/2018/10/31/rosie_women_ai/https://humancompatible.ai/news/2018/12/07/wellman_ethicaltrading/https://humancompatible.ai/news/2018/12/08/neurips2018/https://humancompatible.ai/news/2018/12/09/russel_mit/https://humancompatible.ai/news/2018/12/16/halpern_causality/https://humancompatible.ai/news/2018/12/17/rohin_podcast/https://humancompatible.ai/news/2018/12/21/chai_vox/https://humancompatible.ai/news/2019/01/01/chai_interns-2/https://humancompatible.ai/news/2019/01/01/chai_interns/https://humancompatible.ai/news/2019/01/08/rosie_demystify/https://humancompatible.ai/news/2019/01/15/anca_workshop/https://humancompatible.ai/news/2019/01/15/russel_prize/https://humancompatible.ai/news/2019/01/17/chai_aaai2019/https://humancompatible.ai/news/2019/01/20/turner_prize/https://humancompatible.ai/news/2019/01/21/russell_netherlands/https://humancompatible.ai/news/2019/01/29/chai_fat2019/https://humancompatible.ai/news/2019/02/13/daniel_blogpost/https://humancompatible.ai/news/2019/02/13/halpern_nae_award/https://humancompatible.ai/news/2019/02/14/rohin_blogposts/https://humancompatible.ai/news/2019/03/13/wellman_futureai/https://humancompatible.ai/news/2019/03/20/halpern_caltech/https://humancompatible.ai/news/2019/03/20/uai_2019/https://humancompatible.ai/news/2019/04/15/sam_harris/https://humancompatible.ai/news/2019/04/19/rohin_oneyear/https://humancompatible.ai/news/2019/04/21/aamas/https://humancompatible.ai/news/2019/04/21/iclr_2019/https://humancompatible.ai/news/2019/05/15/rohin_qa/https://humancompatible.ai/news/2019/05/20/stuart_book/https://humancompatible.ai/news/2019/05/20/stuart_carnegie/https://humancompatible.ai/news/2019/05/24/icml_2019/https://humancompatible.ai/news/2019/05/24/neurips_2019/https://humancompatible.ai/news/2019/05/30/vincent_visiting/https://humancompatible.ai/news/2019/06/07/cognitive_models/https://humancompatible.ai/news/2019/06/12/founders_pledge/https://humancompatible.ai/news/2019/06/12/reward_design_talk/https://humancompatible.ai/news/2019/06/14/adversarial_policies_talk/https://humancompatible.ai/news/2019/06/15/talks_icml_2019/https://humancompatible.ai/news/2019/07/01/new_scientist_article/https://humancompatible.ai/news/2019/07/05/imitation_learning_library/https://humancompatible.ai/news/2019/07/05/learning-bias_reward/https://humancompatible.ai/news/2019/08/15/algorithm_fda/https://humancompatible.ai/news/2019/08/16/wellman_market_stability/https://humancompatible.ai/news/2019/08/17/siddharth_hal_paper/https://humancompatible.ai/news/2019/08/27/rohin_clarifying_hypothesis/https://humancompatible.ai/news/2019/08/28/thomas_passions/https://humancompatible.ai/news/2019/09/13/siddharth_nsf_award/https://humancompatible.ai/news/2019/09/28/alignment_newsletter_professionalization/https://humancompatible.ai/news/2019/09/28/utility_learning/https://humancompatible.ai/news/2019/10/08/stuartbook/https://humancompatible.ai/news/2019/11/02/collaborating-with-humans-requires-understanding-them/https://humancompatible.ai/news/2019/12/06/adversarial-policies/https://humancompatible.ai/news/2020/01/18/ai-alignment-review/https://humancompatible.ai/news/2020/01/28/new-class-foundations-for-beneficial-ai/https://humancompatible.ai/news/2020/02/21/hard-choices-in-artificial-intelligence-paper/https://humancompatible.ai/news/2020/03/05/anca-dragan-podcast/https://humancompatible.ai/news/2020/04/19/inaugural-virtal-workshop/https://humancompatible.ai/news/2020/04/30/human-compatible-has-been-reissued-in-the-uk/https://humancompatible.ai/news/2020/05/05/how-to-be-helpful-to-multiple-people-at-once/https://humancompatible.ai/news/2020/05/30/arches/https://humancompatible.ai/news/2020/06/01/first-virtual-workshop/https://humancompatible.ai/news/2020/06/15/hertz-foundation-fellowship/https://humancompatible.ai/news/2020/07/15/students-accept-jobs-deepmind-mit/https://humancompatible.ai/news/2020/08/03/bounded-rationality-in-las-vegas-published/https://humancompatible.ai/news/2020/08/07/thomas-gilbert-receives-simons-institute-fellowship/https://humancompatible.ai/news/2020/08/20/new-affiliates/https://humancompatible.ai/news/2020/09/01/six-new-phd-students-join-chai/https://humancompatible.ai/news/2020/09/03/summer-2020-interns/https://humancompatible.ai/news/2020/09/10/michael-wellman-paper-ijcai-copy/https://humancompatible.ai/news/2020/09/10/rachel-freedman-papers-ijcai/https://humancompatible.ai/news/2020/09/10/stuart-russell-recent-media-appearances/https://humancompatible.ai/news/2020/09/20/thomas-gilbert-subjectifying-objectivity/https://humancompatible.ai/news/2020/09/29/chai-researchers-cognitive-science/https://humancompatible.ai/news/2020/09/29/joseph-halpern-conference-on-uncertainty/https://humancompatible.ai/news/2020/10/05/neurips-seven-papers/https://humancompatible.ai/news/2020/10/10/alignment-problem-published/https://humancompatible.ai/news/2020/10/20/chai-progress-report-2/https://humancompatible.ai/news/2020/11/05/alignment-problem-recording/https://humancompatible.ai/news/2020/11/12/internship-applications/https://humancompatible.ai/news/2020/12/05/stuart-russell-gobdt/https://humancompatible.ai/news/2020/12/12/caroline-jeanmaire-100-brilliant-women-ai-ethics/https://humancompatible.ai/news/2020/12/20/chai-beri-donations/https://humancompatible.ai/news/2020/12/28/neurips-accepts-four-more-chai-papers/https://humancompatible.ai/news/2020/12/30/iclr-2021-accepts-papers-from-chai-researchers/https://humancompatible.ai/news/2021/01/01/rohin-shah-publishes-dissertation/https://humancompatible.ai/news/2021/01/06/daniel-filan-launches-ai-x-risk-research-podcast/https://humancompatible.ai/news/2021/01/15/rachel-freedman-speaks-at-bhs-steminist-club/https://humancompatible.ai/news/2021/02/05/thomas-gilbert-published-in-ieee-istas20/https://humancompatible.ai/news/2021/02/05/tom-gilbert-publishes-simons-institute-white-paper/https://humancompatible.ai/news/2021/02/09/stuart-russell-on-the-munk-debates/https://humancompatible.ai/news/2021/02/14/prof-tom-lenaerts-joins-chai-as-visiting-scholar/https://humancompatible.ai/news/2021/03/01/chai-research-on-self-teaching-ai-featured-in-science/https://humancompatible.ai/news/2021/03/04/michael-dennis-on-talkrl-podcast/https://humancompatible.ai/news/2021/03/18/chai-faculty-and-affiliates-publish-at-aaai-2021/https://humancompatible.ai/news/2021/03/25/la-times-names-the-alignment-problem-best-science-technology-book-finalist/https://humancompatible.ai/news/2021/03/31/listen-to-the-robot-brains-pieter-abbeels-new-podcast/https://humancompatible.ai/news/2021/04/11/stuart-russell-in-wef-dialogue-on-technology-governance/https://humancompatible.ai/news/2021/04/13/chai-researchers-publish-clusterability-in-neural-networks/https://humancompatible.ai/news/2021/04/14/new-papers-on-arxiv/https://humancompatible.ai/news/2021/05/02/brian-christian-publishes-watch-and-learn-offline-reinforcement-learning/https://humancompatible.ai/news/2021/05/05/chai-researchers-publish-in-gaiw-2021/https://humancompatible.ai/news/2021/05/05/chai-welcomes-new-collaborators-and-interns/https://humancompatible.ai/news/2021/05/23/spring-donations/https://humancompatible.ai/news/2021/05/25/thomas-krendl-gilbert-on-talkrl/https://humancompatible.ai/news/2021/05/28/chai-graduates-accept-positions-at-cornell-stanford/https://humancompatible.ai/news/2021/06/01/jonathan-stray-joins-chai-as-visiting-scholar/https://humancompatible.ai/news/2021/06/08/brian-christian-on-the-ezra-klein-show/https://humancompatible.ai/news/2021/06/13/two-new-axrp-episodes/https://humancompatible.ai/news/2021/06/15/stuart-russell-in-robotics-debates/https://humancompatible.ai/news/2021/06/16/fifth-annual-chai-workshop/https://humancompatible.ai/news/2021/07/09/neurips-minerl-basalt-competition-launches/https://humancompatible.ai/news/2021/07/10/icml-2021-accepts-chai-papers/https://humancompatible.ai/news/2021/08/02/jonathan-stray-interviewed-on-the-sunday-show/https://humancompatible.ai/news/2021/08/04/tom-gilbert-article-to-appear-in-artificial-intelligence/https://humancompatible.ai/news/2021/08/07/stuart-russell-named-officer-of-the-order-of-the-british-empire/https://humancompatible.ai/news/2021/08/28/stuart-russell-publishes-articles-on-lethal-autonomous-weapons/https://humancompatible.ai/news/2021/09/02/chai-members-publish-new-papers/https://humancompatible.ai/news/2021/09/04/new-translations-of-human-compatible/https://humancompatible.ai/news/2021/09/06/alison-gopnik-wins-carl-sagan-prize-for-science-popularization/https://humancompatible.ai/news/2021/09/07/chai-congratulates-new-alumni/https://humancompatible.ai/news/2021/09/23/future-of-life-fellowships-announcement/https://humancompatible.ai/news/2021/10/15/stuart-russell-chosen-as-2021-bbc-reith-lecturer/https://humancompatible.ai/news/2021/11/05/brian-christian-delivered-linux-foundation-member-summit-keynote-11-3/https://humancompatible.ai/news/2021/11/10/neurips-paper-replay-guided-adversarial-environment-design-12-6/https://humancompatible.ai/news/2021/11/18/neurips-paper-scalable-online-planning-via-reinforcement-learning-fine-tuning-12-6/https://humancompatible.ai/news/2021/12/01/future-of-life-institute-slaughterbots-2-if-human-kill-and-panel-discussion-featuring-stuart-russell/https://humancompatible.ai/news/2021/12/04/stuart-russell-the-biggest-event-in-human-history/https://humancompatible.ai/news/2021/12/14/stuart-russell-has-been-selected-as-inaugural-director-of-kavli-center-for-ethics-science-and-the-public/https://humancompatible.ai/news/2022/01/18/new-papers-published/https://humancompatible.ai/news/2022/02/17/schmidt-futures-launches-ai2050-to-protect-our-human-future-in-the-age-of-artificial-intelligence/https://humancompatible.ai/news/2022/02/24/brian-christian-is-a-panelist-for-the-prince-mahidol-award-conference-2022/https://humancompatible.ai/news/2022/03/03/uc-berkeley-ai-value-alignment-speaker-series/https://humancompatible.ai/news/2022/03/12/what-does-it-mean-to-give-someone-what-they-want-the-nature-of-preferences-in-recommender-systems/https://humancompatible.ai/news/2022/03/31/how-to-ensure-safe-development-in-a-dynamic-technology-race-the-difficulty-of-hitting-the-target/https://humancompatible.ai/news/2022/04/10/facing-existential-risks-through-ai-proxies/https://humancompatible.ai/news/2022/04/29/pieter-abbeel-receives-2021-acm-prize-in-computing/https://humancompatible.ai/news/2022/05/02/blog-post-whats-right-and-whats-wrong-with-optimizing-for-engagement/https://humancompatible.ai/news/2022/05/12/evolving-curricula-with-regret-based-environment-design/https://humancompatible.ai/news/2022/06/04/chai-papers-published/https://humancompatible.ai/news/2022/06/08/sixth-annual-chai-workshop/https://humancompatible.ai/news/2022/07/16/simons-institute-ai-and-humanity-workshop-at-uc-berkeley/https://humancompatible.ai/news/2022/07/28/rl-as-a-model-of-agency-workshop-at-rldm-2022/https://humancompatible.ai/news/2022/08/10/four-new-phd-students-at-chai/https://humancompatible.ai/news/2022/08/24/discovering-user-interpretable-capabilities-of-black-box-planning-agents/https://humancompatible.ai/news/2022/09/09/discovering-user-interpretable-capabilities-of-black-box-planning-agents-2/https://humancompatible.ai/news/2022/09/26/building-human-values-into-recommender-systems-an-interdisciplinary-synthesis/https://humancompatible.ai/news/2022/10/03/relational-abstractions-for-generalized-reinforcement-learning-on-symbolic-problems/https://humancompatible.ai/news/2022/10/10/social-media-is-polluting-society-content-moderation-alone-wont-fix-the-problem/https://humancompatible.ai/news/2022/10/14/the-shard-theory-of-human-values/https://humancompatible.ai/news/2022/11/01/brian-christians-the-alignment-problem-wins-the-excellence-in-science-communication-award-from-eric-wendy-schmidt-and-the-national-academies/https://humancompatible.ai/news/2022/11/18/time-efficient-reward-learning-via-visually-assisted-cluster-ranking/https://humancompatible.ai/news/2022/12/05/trade-regulation-rule-on-commercial-surveillance-and-data-security-rulemaking/https://humancompatible.ai/news/2022/12/12/competence-aware-systems/https://humancompatible.ai/news/2022/12/29/fast-deliberation-is-related-to-unconditional-behaviour-in-iterated-prisoners-dilemma-experiments-scientific-reports-121-1-10/https://humancompatible.ai/news/2023/01/03/inner-and-outer-alignment-decompose-one-hard-problem-into-two-extremely-hard-problems/https://humancompatible.ai/news/2023/01/10/how-to-use-chatgpt-and-still-be-a-good-person/https://humancompatible.ai/news/2023/01/16/active-reward-learning-from-multiple-teachers/https://humancompatible.ai/news/2023/01/31/fairness-and-sequential-decision-making-limits-lessons-and-opportunities/https://humancompatible.ai/news/2023/02/17/brief-of-center-for-democracy-and-technology-and-6-technologies-as-amici-curiae-in-support-of-respondent/https://humancompatible.ai/news/2023/03/01/a-research-agenda-for-assessing-the-economic-impacts-of-code-generation-models/https://humancompatible.ai/news/2023/03/14/can-a-i-treat-mental-illness/https://humancompatible.ai/news/2023/04/04/distinguished-lecture-on-the-status-and-future-of-al/https://humancompatible.ai/news/2023/04/05/ai-has-much-to-offer-humanity-it-could-also-wreak-terrible-harm-it-must-be-controlled/https://humancompatible.ai/news/2023/04/11/keynote-at-the-value-connection-workshop/https://humancompatible.ai/news/2023/05/02/dealing-with-expert-bias-in-collective-decision-making/https://humancompatible.ai/news/2023/05/29/harms-from-increasingly-agentic-algorithmic-systems/https://humancompatible.ai/news/2023/06/20/seven-annual-chai-workshop/https://humancompatible.ai/news/2023/07/07/who-needs-to-know-minimal-knowledge-for-optimal-coordination/https://humancompatible.ai/news/2023/07/12/dealing-with-expert-bias-in-collective-decision-making-2/https://humancompatible.ai/news/2023/07/21/smcp3-sequential-monte-carlo-with-probabilistic-program-proposals/https://humancompatible.ai/news/2023/08/17/who-needs-to-know-minimal-knowledge-for-optimal-coordination-2/https://humancompatible.ai/news/2023/08/31/conditional-abstraction-trees-for-sample-efficient-reinforcement-learning/https://humancompatible.ai/news/2023/09/18/100-most-influential-people-in-ai/https://humancompatible.ai/news/2023/09/26/acrocpolis-a-descriptive-framework-for-making-sense-of-fairness/https://humancompatible.ai/news/2023/10/03/announcement-of-working-group-on-ai/https://humancompatible.ai/news/2023/10/12/expertise-trees-resolve-knowledge-limitations-in-collective-decision-making/https://humancompatible.ai/news/2023/10/24/managing-ai-risks-in-an-era-of-rapid-progress/https://humancompatible.ai/news/2023/10/26/ai-safety-summit-by-uk-government/https://humancompatible.ai/news/2023/10/31/prominent-ai-scientists-from-china-and-the-west-propose-joint-strategy-to-mitigate-risks-from-ai/https://humancompatible.ai/news/2023/11/06/cs-student-at-uc-berkeley-develops-tech-to-combat-social-media-harms/https://humancompatible.ai/news/2023/11/15/human-compatible-has-been-reissued-in-the-uk-in-2023/https://humancompatible.ai/news/2023/11/21/orienting-ai-toward-peace/https://humancompatible.ai/news/2023/12/04/mitigating-generative-agent-social-dilemmas/https://humancompatible.ai/news/2023/12/11/ai-heralds-a-fourth-industrial-revolution-why-isnt-america-regulating-it/https://humancompatible.ai/news/2023/12/16/what-can-ai-learn-from-human-exploration-intrinsically-motivated-humans-and-agents-in-open-world-exploration/https://humancompatible.ai/news/2023/12/20/almanacs-a-simulatability-benchmark-for-language-model-explainability/https://humancompatible.ai/news/2024/01/16/autonomous-assessment-of-demonstration-sufficiency-via-bayesian-inverse-reinforcement-learning/https://humancompatible.ai/news/2024/01/18/the-prosocial-ranking-challenge-60000-in-prizes-for-better-social-media-algorithms/https://humancompatible.ai/news/2024/03/05/when-your-ais-deceive-you-challenges-with-partial-observability-of-human-evaluators-in-reward-learning/https://humancompatible.ai/news/2024/03/28/embracing-ai-that-reflects-human-values-insights-from-brian-christians-journey/https://humancompatible.ai/news/2024/04/02/chai-policy-internship/https://humancompatible.ai/news/2024/04/06/regulating-advanced-artificial-agents/https://humancompatible.ai/news/2024/04/15/reinforcement-learning-safety-workshop-rlsw-rlc-2024/https://humancompatible.ai/news/2024/04/30/reinforcement-learning-with-human-feedback-and-active-teacher-selection-rlhf-and-ats/https://humancompatible.ai/news/2024/05/13/committing-to-the-wrong-artificial-delegate-in-a-collective-risk-dilemma-is-better-than-directly-committing-mistakes/https://humancompatible.ai/news/2024/06/05/when-code-isnt-law-rethinking-regulation-for-artificial-intelligence/https://humancompatible.ai/news/2024/06/18/8th-annual-chai-workshop/https://humancompatible.ai/news/2024/06/28/mitigating-partial-observability-in-decision-processes-via-the-lambda-discrepancy/https://humancompatible.ai/news/2024/07/08/forget-deepfake-videos-text-and-voice-are-this-elections-true-ai-threat/https://humancompatible.ai/news/2024/07/23/ai-alignment-with-changing-and-influenceable-reward-functions/https://humancompatible.ai/news/2024/08/07/social-choice-should-guide-ai-alignment-in-dealing-with-diverse-human-feedback/https://humancompatible.ai/news/2024/08/29/the-alignment-problem-wins-xingdu-book-award/https://humancompatible.ai/news/2024/09/18/language-guided-world-models-a-model-based-approach-to-ai-control/https://humancompatible.ai/news/2024/10/10/getting-by-goal-misgeneralization-with-a-little-help-from-a-mentor/https://humancompatible.ai/news/2024/11/12/representative-social-choice-from-learning-theory-to-ai-alignment/https://humancompatible.ai/news/2024/11/30/rachel-freedman-selected-as-inaugural-cooperative-ai-fellow/https://humancompatible.ai/news/2024/12/14/linear-probe-penalties-reduce-llm-sycophancy/https://humancompatible.ai/news/2024/12/25/getting-by-goal-misgeneralization-with-a-little-help-from-a-mentor-2/https://humancompatible.ai/news/2025/01/18/rvs-what-is-essential-for-offline-rl-via-supervised-learning/https://humancompatible.ai/news/2025/02/04/a-practical-definition-of-political-neutrality-for-ai/https://humancompatible.ai/news/2025/02/20/computational-frameworksfor-human-care/https://humancompatible.ai/news/2025/03/07/learning-to-coordinate-with-experts/https://humancompatible.ai/news/page/2/https://humancompatible.ai/news/page/3/https://humancompatible.ai/news/page/4/https://humancompatible.ai/news/page/5/https://humancompatible.ai/news/page/6/https://humancompatible.ai/news/page/7/https://humancompatible.ai/news/page/8/https://humancompatible.ai/news/page/9/https://humancompatible.ai/news/page/10/https://humancompatible.ai/news/page/11/https://humancompatible.ai/news/page/12/https://humancompatible.ai/news/page/13/https://humancompatible.ai/news/page/14/https://humancompatible.ai/news/page/15/https://humancompatible.ai/news/page/16/https://humancompatible.ai/news/page/17/https://humancompatible.ai/news/page/18/https://humancompatible.ai/news/page/19/https://humancompatible.ai/news/page/20/https://humancompatible.ai/news/page/21/https://humancompatible.ai/news/page/22/https://humancompatible.ai/news/page/23/https://humancompatible.ai/news/page/24/https://humancompatible.ai/news/page/25/https://humancompatible.ai/news/page/26/https://humancompatible.ai/news/page/27/https://humancompatible.ai/newsletter/https://humancompatible.ai/people/https://humancompatible.ai/people/adam-gleave/https://humancompatible.ai/people/alaa-tamam/https://humancompatible.ai/people/alex-turner-2/https://humancompatible.ai/people/alex-turner/https://humancompatible.ai/people/alexandra-souly/https://humancompatible.ai/people/alexis-wan/https://humancompatible.ai/people/alina-yang/https://humancompatible.ai/people/alison-gopnik/https://humancompatible.ai/people/aly-lidayan/https://humancompatible.ai/people/anand-siththaranjan/https://humancompatible.ai/people/anca-dragan/https://humancompatible.ai/people/andrew-critch/https://humancompatible.ai/people/andrew-garber/https://humancompatible.ai/people/antoni-lorente-martinez/https://humancompatible.ai/people/arnaud-fickinger/https://humancompatible.ai/people/austin-tripp/https://humancompatible.ai/people/aymane-el-gadarri/https://humancompatible.ai/people/bart-selman/https://humancompatible.ai/people/ben-plaut/https://humancompatible.ai/people/beth-barnes/https://humancompatible.ai/people/bhaskar-mishra/https://humancompatible.ai/people/brandie-nonnecke/https://humancompatible.ai/people/brian-christian/https://humancompatible.ai/people/brian-judge/https://humancompatible.ai/people/cameron-allen/https://humancompatible.ai/people/carlo-attubato/https://humancompatible.ai/people/caroline-jeanmaire/https://humancompatible.ai/people/cassidy-laidlaw/https://humancompatible.ai/people/charis-thompson/https://humancompatible.ai/people/charlie-griffin/https://humancompatible.ai/people/charlotte-roman/https://humancompatible.ai/people/chris-cundy/https://humancompatible.ai/people/cody-wild/https://humancompatible.ai/people/cynthia-chen/https://humancompatible.ai/people/dan-hendryks/https://humancompatible.ai/people/daniel-filan/https://humancompatible.ai/people/david-foote/https://humancompatible.ai/people/david-krueger/https://humancompatible.ai/people/david-lindner/https://humancompatible.ai/people/dawn-song/https://humancompatible.ai/people/demian-pouzo/https://humancompatible.ai/people/dillon-sandhu/https://humancompatible.ai/people/dmitrii-krasheninnikov/https://humancompatible.ai/people/dorsa-sadigh/https://humancompatible.ai/people/dylan-cope/https://humancompatible.ai/people/dylan-hadfield-menell/https://humancompatible.ai/people/edmund-mills/https://humancompatible.ai/people/emma-pierson/https://humancompatible.ai/people/erdem-biyik/https://humancompatible.ai/people/eric-michaud/https://humancompatible.ai/people/erik-jenner-2/https://humancompatible.ai/people/erik-jenner/https://humancompatible.ai/people/ethan-mendes/https://humancompatible.ai/people/euan-ong/https://humancompatible.ai/people/george-matheos/https://humancompatible.ai/people/george-obaido/https://humancompatible.ai/people/gillian-hadfield/https://humancompatible.ai/people/hanlin-zhu/https://humancompatible.ai/people/harry-giles/https://humancompatible.ai/people/henry-papadatos/https://humancompatible.ai/people/ian-baker/https://humancompatible.ai/people/j-p-gonzales/https://humancompatible.ai/people/jacob-steinhardt/https://humancompatible.ai/people/jacy-reese-anthis/https://humancompatible.ai/people/jaime-fernandez-fisac/https://humancompatible.ai/people/jakob-foerster/https://humancompatible.ai/people/jakub-grudzien-kuba/https://humancompatible.ai/people/jess-reidel/https://humancompatible.ai/people/jessy-lin/https://humancompatible.ai/people/jiahai-feng/https://humancompatible.ai/people/joar-skalse/https://humancompatible.ai/people/joe-benton/https://humancompatible.ai/people/johannes-treutlein-2/https://humancompatible.ai/people/johannes-treutlein/https://humancompatible.ai/people/john-zysman/https://humancompatible.ai/people/jonathan-colaco-carr/https://humancompatible.ai/people/jonathan-stray/https://humancompatible.ai/people/joseph-halpern/https://humancompatible.ai/people/juan-lievano/https://humancompatible.ai/people/julia-morris/https://humancompatible.ai/people/julian-yocum-2/https://humancompatible.ai/people/julian-yocum/https://humancompatible.ai/people/juliana-schroeder/https://humancompatible.ai/people/jun-shern-chan/https://humancompatible.ai/people/justin-svegliato/https://humancompatible.ai/people/karim-abdel-sadek/https://humancompatible.ai/people/karthika-mohan/https://humancompatible.ai/people/katie-lu/https://humancompatible.ai/people/ken-goldberg/https://humancompatible.ai/people/khanh-nguyen/https://humancompatible.ai/people/lara-buchak/https://humancompatible.ai/people/lauro-langosco/https://humancompatible.ai/people/lawrence-chan/https://humancompatible.ai/people/leon-lang/https://humancompatible.ai/people/lev-mckinney/https://humancompatible.ai/people/lijie-chen/https://humancompatible.ai/people/livia-morris/https://humancompatible.ai/people/lukas-berglund/https://humancompatible.ai/people/luke-bailey/https://humancompatible.ai/people/mariano-florentino-cuellar/https://humancompatible.ai/people/marion-fourcade/https://humancompatible.ai/people/mark-bedaywi/https://humancompatible.ai/people/mark-nitzberg/https://humancompatible.ai/people/martin-soto/https://humancompatible.ai/people/mason-nakamura-2/https://humancompatible.ai/people/matthew-farrugia-roberts/https://humancompatible.ai/people/matthew-rahtz/https://humancompatible.ai/people/max-kaufmann/https://humancompatible.ai/people/micah-carroll/https://humancompatible.ai/people/michael-chen/https://humancompatible.ai/people/michael-cohen/https://humancompatible.ai/people/michael-dennis/https://humancompatible.ai/people/michael-littman/https://humancompatible.ai/people/michael-mcdonald/https://humancompatible.ai/people/michael-wellman/https://humancompatible.ai/people/michal-mgeladze-arciuch/https://humancompatible.ai/people/michelle-li/https://humancompatible.ai/people/mohamad-danesh/https://humancompatible.ai/people/moritz-hardt/https://humancompatible.ai/people/nathan-miller/https://humancompatible.ai/people/neel-alex/https://humancompatible.ai/people/neel-nanda/https://humancompatible.ai/people/nika-haghtalab/https://humancompatible.ai/people/niklas-lauffer/https://humancompatible.ai/people/niko-kolodny/https://humancompatible.ai/people/nitish-dashora/https://humancompatible.ai/people/oliver-daniels-koch/https://humancompatible.ai/people/oliver-richardson/https://humancompatible.ai/people/olivia-watkins/https://humancompatible.ai/people/owain-evans/https://humancompatible.ai/people/paria-rashidinejad/https://humancompatible.ai/people/pavel-czempin-2/https://humancompatible.ai/people/pavel-czempin/https://humancompatible.ai/people/pedro-freire/https://humancompatible.ai/people/pieter-abbeel/https://humancompatible.ai/people/pulkit-verma/https://humancompatible.ai/people/rachel-freedman/https://humancompatible.ai/people/rafael-albert/https://humancompatible.ai/people/ram-rachum/https://humancompatible.ai/people/rediet-abebe/https://humancompatible.ai/people/rohin-shah/https://humancompatible.ai/people/rosie-campbell/https://humancompatible.ai/people/sam-toyer/https://humancompatible.ai/people/sana-pandey/https://humancompatible.ai/people/sandy-tanwisuth/https://humancompatible.ai/people/sarah-otis/https://humancompatible.ai/people/satinder-singh-baveja/https://humancompatible.ai/people/scott-emmons/https://humancompatible.ai/people/sergei-volodin/https://humancompatible.ai/people/serina-chang/https://humancompatible.ai/people/shivam-singhal/https://humancompatible.ai/people/shlomi-hod/https://humancompatible.ai/people/shreyas-kapur/https://humancompatible.ai/people/siddharth-srivastava/https://humancompatible.ai/people/smitha-milli/https://humancompatible.ai/people/soren-mindermann/https://humancompatible.ai/people/stephen-casper/https://humancompatible.ai/people/steven-wang/https://humancompatible.ai/people/stuart-russell/https://humancompatible.ai/people/tania-lombrozo/https://humancompatible.ai/people/thanard-kurutach/https://humancompatible.ai/people/thomas-gilbert/https://humancompatible.ai/people/thomas-woodside/https://humancompatible.ai/people/tom-griffiths/https://humancompatible.ai/people/tom-lenaerts/https://humancompatible.ai/people/tu-alina-trinh/https://humancompatible.ai/people/vael-gates/https://humancompatible.ai/people/vincent-corruble/https://humancompatible.ai/people/wesley-holliday/https://humancompatible.ai/people/yawen-duan/https://humancompatible.ai/people/yijin-hua/https://humancompatible.ai/people/yulong-lin/https://humancompatible.ai/people/yuxi-liu/https://humancompatible.ai/people/zeno-marquis/https://humancompatible.ai/people/zhijing-jin/https://humancompatible.ai/privacypolicy/https://humancompatible.ai/progress-report/https://humancompatible.ai/psbai-workshop-2022/https://humancompatible.ai/research/https://humancompatible.ai/spotlights/