https://newsletter.threelaws.net/archivedailyhttps://newsletter.threelaws.net/aboutweeklyhttps://newsletter.threelaws.net/p/open-source-llms-administer-maximum-electric-shocks-in-a-12026-07-26monthlyhttps://newsletter.threelaws.net/p/research-agenda-for-training-aligned-ais-using-concave2026-07-26monthlyhttps://newsletter.threelaws.net/p/2509026552026-07-26monthlyhttps://newsletter.threelaws.net/p/presentation-at-machine-ethics-and2026-07-27monthlyhttps://newsletter.threelaws.net/p/black-box-interpretability-methodology-blueprint-probing2026-07-26monthlyhttps://newsletter.threelaws.net/p/presentation-at-maisu-unconference2026-07-27monthlyhttps://newsletter.threelaws.net/p/watch2026-07-27monthlyhttps://newsletter.threelaws.net/p/systematic-runaway-optimiser-like-llm-failure-modes-on2026-07-26monthlyhttps://newsletter.threelaws.net/p/baseline-experimental-results-with2026-07-27monthlyhttps://newsletter.threelaws.net/p/bioblue2026-07-26monthlyhttps://newsletter.threelaws.net/p/why-modelling-multi-objective-homeostasis-is-essential-for2026-07-26monthlyhttps://newsletter.threelaws.net/p/presentation-at-foresight-institutes2026-07-27monthlyhttps://newsletter.threelaws.net/p/edit2026-07-26monthlyhttps://newsletter.threelaws.net/p/2410000812026-07-27monthlyhttps://newsletter.threelaws.net/p/presentation-at-vaisu-2024-ai-safety2026-07-27monthlyhttps://newsletter.threelaws.net/p/biological-alignment-gridagents-benchmarks2026-07-27monthlyhttps://newsletter.threelaws.net/p/the-firemaker-a-multi-agent-safety-hackathon-submissionpdf2026-07-26monthlyhttps://newsletter.threelaws.net/p/manipulative-expression-recognition2026-07-26monthlyhttps://newsletter.threelaws.net/p/s10458-022-09586-22026-07-26monthlyhttps://newsletter.threelaws.net/p/sets-of-objectives-for-a-multi-objective-rl-agent-to-12026-07-26monthlyhttps://newsletter.threelaws.net/p/a-brief-review-of-the-reasons-multi-objective-rl-could-be2026-07-26monthlyhttps://newsletter.threelaws.net/p/presentation-soft-maximin-approaches2026-07-27monthlyhttps://newsletter.threelaws.net/p/aisc-v-project-proposal-model-structure2026-07-26monthlyhttps://newsletter.threelaws.net/p/ai-ethics-conference-and-panel-by-19-05-312026-07-27monthlyhttps://newsletter.threelaws.net/p/what-happens-when-autonomous-robots-are-not-regulated-or-on-the-contrary-qualify-as-subjects-of-9819c33d70d2026-07-27monthlyhttps://newsletter.threelaws.net/p/what-can-happen-when-we-dont-have-a-clue-why-a-somewhat-autonomous-gadget-does-what-it-does-338b33c5eaeb2026-07-27monthlyhttps://newsletter.threelaws.net/p/presentation-at-taltech-legal-accountability2026-07-26monthlyhttps://newsletter.threelaws.net/p/presentation-elsa-estonia-european2026-07-26monthlyhttps://newsletter.threelaws.net/p/project-legal-accountability-in-ai-based-robot-agents-user-interfaces-10b74a7f74ed2026-07-26monthlyhttps://newsletter.threelaws.net/p/project-proposal-corrigibility-and-interruptibility-of-homeostasis-based-agents-e51bafbf71112026-07-26monthlyhttps://newsletter.threelaws.net/p/diminishing-returns-and-conjunctive-goals-towards-corrigibility-and-interruptibility-2ec594fed75c2026-07-26monthlyhttps://newsletter.threelaws.net/p/making-the-tax-burden-of-robot-usage-equal-to-the-tax-burden-of-human-labour-c8e97df751a12026-07-27monthlyhttps://newsletter.threelaws.net/p/proposal-for-executable-and-interactive-simulations-of-ai-safety-failure-scenarios-7acab7015be42026-07-27monthlyhttps://newsletter.threelaws.net/p/organisations-as-an-old-form-of-artificial-general-intelligence-f30c27638f502026-07-26monthlyhttps://newsletter.threelaws.net/p/making-ai-less-dangerous-2742e29797bd2026-07-27monthlyhttps://newsletter.threelaws.net/p/implementing-a-framework-of-safe-robot-planning-43636efe7dd82026-07-26monthlyhttps://newsletter.threelaws.net/p/definition-of-self-deception-in-the-context-of-robot-safety-721061449f72026-07-26monthlyhttps://newsletter.threelaws.net/p/first-law-of-robotics-and-a-possible-definition-of-robot-safety-419bc41a1ffe2026-07-26monthly