https://lab.yeeta.org/parallax/ https://lab.yeeta.org/parallax/chronology/ https://lab.yeeta.org/parallax/encyclopedia/ https://lab.yeeta.org/parallax/sources/ https://lab.yeeta.org/parallax/concepts/https://lab.yeeta.org/parallax/papers/https://lab.yeeta.org/parallax/people/https://lab.yeeta.org/parallax/organizations/https://lab.yeeta.org/parallax/notes/ https://lab.yeeta.org/parallax/concepts/agentic-inequality/2026-10-08https://lab.yeeta.org/parallax/concepts/agentic-misalignment/2026-10-08https://lab.yeeta.org/parallax/concepts/ai-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/ai-safety-via-debate/2026-10-11https://lab.yeeta.org/parallax/concepts/alignment-faking/2026-10-08https://lab.yeeta.org/parallax/concepts/common-sense-reasoning/2026-10-10https://lab.yeeta.org/parallax/concepts/compliance-gap/2026-10-07https://lab.yeeta.org/parallax/concepts/corrigibility/2026-10-11https://lab.yeeta.org/parallax/concepts/deceptive-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/direct-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/distributional-shift/2026-10-11https://lab.yeeta.org/parallax/concepts/eliza-effect/2026-10-08https://lab.yeeta.org/parallax/concepts/embodied-cognition/2026-10-07https://lab.yeeta.org/parallax/concepts/emergent-misalignment/2026-10-10https://lab.yeeta.org/parallax/concepts/ghost-work/2026-10-07https://lab.yeeta.org/parallax/concepts/goodharts-law/2026-10-11https://lab.yeeta.org/parallax/concepts/human-model-misspecification/2026-10-10https://lab.yeeta.org/parallax/concepts/inner-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/inoculation-prompting/2026-10-10https://lab.yeeta.org/parallax/concepts/instrumental-convergence/2026-10-10https://lab.yeeta.org/parallax/concepts/machine-ethics/2026-10-10https://lab.yeeta.org/parallax/concepts/machine-intelligence/2026-10-08https://lab.yeeta.org/parallax/concepts/machine-introspection/2026-10-07https://lab.yeeta.org/parallax/concepts/meaningful-human-control/2026-10-11https://lab.yeeta.org/parallax/concepts/mesa-optimization/2026-10-11https://lab.yeeta.org/parallax/concepts/multi-agent-risks/2026-10-10https://lab.yeeta.org/parallax/concepts/outer-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/preference-aggregation/2026-10-11https://lab.yeeta.org/parallax/concepts/reward-hacking/2026-10-11https://lab.yeeta.org/parallax/concepts/safety-case/2026-10-11https://lab.yeeta.org/parallax/concepts/sandbagging/2026-10-11https://lab.yeeta.org/parallax/concepts/scalable-oversight/2026-10-11https://lab.yeeta.org/parallax/concepts/social-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/society-in-the-loop/2026-10-10https://lab.yeeta.org/parallax/concepts/stable-alignment/2026-10-11https://lab.yeeta.org/parallax/concepts/stackelberg-game/2026-10-09https://lab.yeeta.org/parallax/concepts/treaty-following-ai/2026-10-08https://lab.yeeta.org/parallax/concepts/veil-of-ignorance/2026-10-07https://lab.yeeta.org/parallax/events/aisi-cyber-evaluation-incident-2026/2026-10-10https://lab.yeeta.org/parallax/events/autonomous-weapons-open-letter-2015/2026-10-10https://lab.yeeta.org/parallax/events/beneficial-ai-open-letter-2015/2026-10-10https://lab.yeeta.org/parallax/events/coastrunners-reward-hacking/2026-10-08https://lab.yeeta.org/parallax/events/pause-giant-ai-experiments-2023/2026-10-10https://lab.yeeta.org/parallax/events/statement-on-ai-risk-2023/2026-10-10https://lab.yeeta.org/parallax/events/tay-chatbot-incident-2016/2026-10-11https://lab.yeeta.org/parallax/events/uber-tempe-crash-2018/2026-10-11https://lab.yeeta.org/parallax/notes/ai-incidents/2026-10-11https://lab.yeeta.org/parallax/notes/alignment-feedback/2026-10-11https://lab.yeeta.org/parallax/notes/book-research-agenda/2026-10-07https://lab.yeeta.org/parallax/notes/evaluation-forecast/2026-10-11https://lab.yeeta.org/parallax/notes/key-papers/2026-10-11https://lab.yeeta.org/parallax/notes/objectives-to-accountable-control/2026-10-11https://lab.yeeta.org/parallax/notes/origins-of-alignment/2026-10-11https://lab.yeeta.org/parallax/notes/research-notes/2026-10-08https://lab.yeeta.org/parallax/organizations/center-for-ai-safety/2026-10-10https://lab.yeeta.org/parallax/organizations/future-of-life-institute/2026-10-10https://lab.yeeta.org/parallax/papers/agentic-inequality/2026-10-11https://lab.yeeta.org/parallax/papers/agentic-misalignment/2026-10-08https://lab.yeeta.org/parallax/papers/ai-colonialism/2026-10-07https://lab.yeeta.org/parallax/papers/ai-inequality-challenges/2026-10-07https://lab.yeeta.org/parallax/papers/ai-safety-via-debate/2026-10-09https://lab.yeeta.org/parallax/papers/ai-sandbagging/2026-10-09https://lab.yeeta.org/parallax/papers/ai-values-alignment/2026-10-11https://lab.yeeta.org/parallax/papers/algorithms-inverse-reinforcement-learning/2026-10-10https://lab.yeeta.org/parallax/papers/aligned-with-whom/2026-10-11https://lab.yeeta.org/parallax/papers/alignment-faking/2026-10-08https://lab.yeeta.org/parallax/papers/apprenticeship-inverse-reinforcement-learning/2026-10-09https://lab.yeeta.org/parallax/papers/artificial-emotions/2026-10-07https://lab.yeeta.org/parallax/papers/attack-selection-trusted-monitoring/2026-10-10https://lab.yeeta.org/parallax/papers/attention-is-all-you-need/2026-10-11https://lab.yeeta.org/parallax/papers/automated-risky-game/2026-10-08https://lab.yeeta.org/parallax/papers/basic-ai-drives/2026-10-10https://lab.yeeta.org/parallax/papers/beginnings-ai-medicine/2026-10-07https://lab.yeeta.org/parallax/papers/challenge-value-alignment/2026-10-08https://lab.yeeta.org/parallax/papers/circumscription/2026-10-09https://lab.yeeta.org/parallax/papers/collective-good-optimization/2026-10-07https://lab.yeeta.org/parallax/papers/computing-machinery-and-intelligence/2026-10-11https://lab.yeeta.org/parallax/papers/concrete-problems/2026-10-10https://lab.yeeta.org/parallax/papers/conscious-supremacy/2026-10-07https://lab.yeeta.org/parallax/papers/consequences-of-automation/2026-10-11https://lab.yeeta.org/parallax/papers/constitutional-ai/2026-10-11https://lab.yeeta.org/parallax/papers/cooperative-inverse-reinforcement-learning/2026-10-10https://lab.yeeta.org/parallax/papers/corrigibility/2026-10-10https://lab.yeeta.org/parallax/papers/corrigible-assistance-one-round/2026-10-10https://lab.yeeta.org/parallax/papers/deception-risks-dynamics/2026-10-07https://lab.yeeta.org/parallax/papers/deep-rl-human-preferences/2026-10-11https://lab.yeeta.org/parallax/papers/dehumanizing-care/2026-10-07https://lab.yeeta.org/parallax/papers/different-history-ai/2026-10-07https://lab.yeeta.org/parallax/papers/diffuse-ai-control-fuzzy-tasks/2026-10-10https://lab.yeeta.org/parallax/papers/dynamic-value-alignment/2026-10-11https://lab.yeeta.org/parallax/papers/eliza/2026-10-08https://lab.yeeta.org/parallax/papers/emergent-misalignment-reward-hacking/2026-10-10https://lab.yeeta.org/parallax/papers/engineering-social-contract/2026-10-08https://lab.yeeta.org/parallax/papers/ensemble-monitoring-ai-control/2026-10-10https://lab.yeeta.org/parallax/papers/expert-systems-common-sense/2026-10-11https://lab.yeeta.org/parallax/papers/golem-game-automation/2026-10-07https://lab.yeeta.org/parallax/papers/goodharts-law/2026-10-11https://lab.yeeta.org/parallax/papers/illusion-rationality/2026-10-08https://lab.yeeta.org/parallax/papers/implicit-influence-monitoring/2026-10-09https://lab.yeeta.org/parallax/papers/information-access-sabotage-monitoring/2026-10-10https://lab.yeeta.org/parallax/papers/instructgpt/2026-10-11https://lab.yeeta.org/parallax/papers/john-mccarthy-memoir/2026-10-07https://lab.yeeta.org/parallax/papers/learning-designers-ai/2026-10-07https://lab.yeeta.org/parallax/papers/learning-misspecified-objective-spaces/2026-10-10https://lab.yeeta.org/parallax/papers/learning-summarize-human-feedback/2026-10-11https://lab.yeeta.org/parallax/papers/literal-or-pedagogic-human/2026-10-10https://lab.yeeta.org/parallax/papers/llm-consciousness-abstract/2026-10-07https://lab.yeeta.org/parallax/papers/longtermist-political-philosophy/2026-10-07https://lab.yeeta.org/parallax/papers/machine-ethics-ai-alignment/2026-10-08https://lab.yeeta.org/parallax/papers/manipulation-attacks/2026-10-11https://lab.yeeta.org/parallax/papers/maze-consciousness-behaviors/2026-10-07https://lab.yeeta.org/parallax/papers/mazeeval/2026-10-07https://lab.yeeta.org/parallax/papers/meaningful-human-control/2026-10-10https://lab.yeeta.org/parallax/papers/monitorability-information-theory/2026-10-09https://lab.yeeta.org/parallax/papers/moving-self/2026-10-07https://lab.yeeta.org/parallax/papers/multi-agent-risks/2026-10-08https://lab.yeeta.org/parallax/papers/near-term-ai-existential-risk-factor/2026-10-10https://lab.yeeta.org/parallax/papers/noticing-the-watcher/2026-10-09https://lab.yeeta.org/parallax/papers/off-switch-game/2026-10-11https://lab.yeeta.org/parallax/papers/optimal-learning-assistance-games/2026-10-10https://lab.yeeta.org/parallax/papers/optimal-policies-seek-power/2026-10-10https://lab.yeeta.org/parallax/papers/organizational-identity-ai/2026-10-07https://lab.yeeta.org/parallax/papers/patterns-human-language/2026-10-07https://lab.yeeta.org/parallax/papers/policy-invariance-reward-shaping/2026-10-10https://lab.yeeta.org/parallax/papers/positive-mental-health-ai/2026-10-07https://lab.yeeta.org/parallax/papers/power-seeking-ai-existential-risk/2026-10-10https://lab.yeeta.org/parallax/papers/precision-psychiatry-ml/2026-10-07https://lab.yeeta.org/parallax/papers/predicting-safety-simulated-deployment/2026-10-11https://lab.yeeta.org/parallax/papers/progress-ai-safety-via-debate/2026-10-09https://lab.yeeta.org/parallax/papers/reinforcement-learning-survey/2026-10-09https://lab.yeeta.org/parallax/papers/researcharena/2026-10-10https://lab.yeeta.org/parallax/papers/risks-from-learned-optimization/2026-10-11https://lab.yeeta.org/parallax/papers/robots-mental-states/2026-10-11https://lab.yeeta.org/parallax/papers/robust-beneficial-ai-research-priorities/2026-10-10https://lab.yeeta.org/parallax/papers/safe-learning-asking-for-help/2026-10-09https://lab.yeeta.org/parallax/papers/safeguards-misuse-safety-case/2026-10-11https://lab.yeeta.org/parallax/papers/safely-interruptible-agents/2026-10-11https://lab.yeeta.org/parallax/papers/self-fulfilling-misalignment/2026-10-08https://lab.yeeta.org/parallax/papers/should-robots-be-obedient/2026-10-10https://lab.yeeta.org/parallax/papers/shutdown-sabotage-multi-agent/2026-10-10https://lab.yeeta.org/parallax/papers/sleight-bench/2026-10-10https://lab.yeeta.org/parallax/papers/society-in-the-loop/2026-10-11https://lab.yeeta.org/parallax/papers/sta-rlhf/2026-10-09https://lab.yeeta.org/parallax/papers/structural-fidelity/2026-10-07https://lab.yeeta.org/parallax/papers/surfing-ai-waves/2026-10-07https://lab.yeeta.org/parallax/papers/talking-to-bots-tay/2026-10-10https://lab.yeeta.org/parallax/papers/training-socially-aligned-language-models/2026-10-08https://lab.yeeta.org/parallax/papers/treaty-following-ai/2026-10-08https://lab.yeeta.org/parallax/papers/veil-greater-good/2026-10-07https://lab.yeeta.org/parallax/papers/veil-of-ignorance-ai/2026-10-08https://lab.yeeta.org/parallax/papers/why-models-fake-alignment/2026-10-08https://lab.yeeta.org/parallax/people/abhay-sheshadri/2026-10-07https://lab.yeeta.org/parallax/people/aengus-lynch/2026-10-08https://lab.yeeta.org/parallax/people/ajay-vishwanath/2026-10-07https://lab.yeeta.org/parallax/people/alan-turing/2026-10-11https://lab.yeeta.org/parallax/people/andreas-schmidt/2026-10-07https://lab.yeeta.org/parallax/people/anoushka-thakkar/2026-10-07https://lab.yeeta.org/parallax/people/anton-korinek/2026-10-07https://lab.yeeta.org/parallax/people/ashish-vaswani/2026-10-11https://lab.yeeta.org/parallax/people/aslihan-canbul-yaroglu/2026-10-07https://lab.yeeta.org/parallax/people/avery-slater/2026-10-07https://lab.yeeta.org/parallax/people/avital-balwit/2026-10-07https://lab.yeeta.org/parallax/people/benjamin-wright/2026-10-08https://lab.yeeta.org/parallax/people/boyuan-chen/2026-10-07https://lab.yeeta.org/parallax/people/casimir-kulikowski/2026-10-07https://lab.yeeta.org/parallax/people/christoph-durt/2026-10-07https://lab.yeeta.org/parallax/people/daniel-kokotajlo/2026-10-11https://lab.yeeta.org/parallax/people/daniel-rigobon/2026-10-07https://lab.yeeta.org/parallax/people/dario-amodei/2026-10-07https://lab.yeeta.org/parallax/people/david-manheim/2026-10-10https://lab.yeeta.org/parallax/people/demis-hassabis/2026-10-11https://lab.yeeta.org/parallax/people/dmitrii-gusev/2026-10-07https://lab.yeeta.org/parallax/people/evan-hubinger/2026-10-08https://lab.yeeta.org/parallax/people/geoffrey-hinton/2026-10-11https://lab.yeeta.org/parallax/people/hafsteinn-einarsson/2026-10-07https://lab.yeeta.org/parallax/people/hidetoshi-komatsu/2026-10-07https://lab.yeeta.org/parallax/people/hutan-ashrafian/2026-10-07https://lab.yeeta.org/parallax/people/iason-gabriel/2026-10-11https://lab.yeeta.org/parallax/people/iyad-rahwan/2026-10-07https://lab.yeeta.org/parallax/people/jacob-makar-limanov/2026-10-07https://lab.yeeta.org/parallax/people/john-mccarthy/2026-10-09https://lab.yeeta.org/parallax/people/karen-huang/2026-10-07https://lab.yeeta.org/parallax/people/kay-harrison/2026-10-07https://lab.yeeta.org/parallax/people/ken-mogi/2026-10-07https://lab.yeeta.org/parallax/people/laura-weidinger/2026-10-11https://lab.yeeta.org/parallax/people/lewis-hammond/2026-10-07https://lab.yeeta.org/parallax/people/manuel-rios/2026-10-08https://lab.yeeta.org/parallax/people/manuel-woersdoerfer/2026-10-07https://lab.yeeta.org/parallax/people/marcin-korecki/2026-10-07https://lab.yeeta.org/parallax/people/mariana-lins-costa/2026-10-07https://lab.yeeta.org/parallax/people/marija-slavkovik/2026-10-07https://lab.yeeta.org/parallax/people/matteo-cristofaro/2026-10-07https://lab.yeeta.org/parallax/people/milad-farahani/2026-10-07https://lab.yeeta.org/parallax/people/monte-macdiarmid/2026-10-07https://lab.yeeta.org/parallax/people/norbert-wiener/2026-10-11https://lab.yeeta.org/parallax/people/paul-christiano/2026-10-10https://lab.yeeta.org/parallax/people/paul-mithun/2026-10-07https://lab.yeeta.org/parallax/people/rishane-dassanayake/2026-10-07https://lab.yeeta.org/parallax/people/rodrigo-ventura/2026-10-07https://lab.yeeta.org/parallax/people/rui-pimenta/2026-10-07https://lab.yeeta.org/parallax/people/ruibo-liu/2026-10-08https://lab.yeeta.org/parallax/people/ryan-greenblatt/2026-10-08https://lab.yeeta.org/parallax/people/salvador-regilme/2026-10-07https://lab.yeeta.org/parallax/people/scott-garrabrant/2026-10-10https://lab.yeeta.org/parallax/people/sharon-vaisvaser/2026-10-07https://lab.yeeta.org/parallax/people/shenzhe-zhu/2026-10-07https://lab.yeeta.org/parallax/people/stuart-russell/2026-10-10https://lab.yeeta.org/parallax/people/teun-van-der-weij/2026-10-07https://lab.yeeta.org/parallax/people/vafa-ghazavi/2026-10-07https://lab.yeeta.org/parallax/people/valerie-black/2026-10-07