Softmax - Scaling alignment
All alignment between individuals is a matter of shared fundamental goals. Organic alignment occurs when these individuals find themselves in groups with mutual interdependence, and take on an overarching shared goal of the healthy development and flourishing of the group as a whole. Our mission is to understand this process as an empirical science, and to use that understanding to enable organic alignment among all people, both human and digital. We call it organic alignment because it is the form of alignment that evolution has learned most often for aligning living things. One of the best examples is multicellularity, where individual cells learn to come together to form larger organisms. They do this by learning to specialize into different but mutually supportive roles: muscle cells, nerve cells, skin cells, liver cells, and so on. While liver cells and muscle cells have very different goals day to day, at a more fundamental level they share a goal of the organism’s flourishing. T
Why Softmax Alignment in the real world means navigating environments that are social and everchanging. But today's AIs train by grinding through static, single-player problem sets. Softmax offers an alternative: environments with rich social dynamics, where agents learn alongside each other and with people. Feature leagues Competitive leagues in every genre Every game is a live league with ranked matches, public replays. Watch this week's standout, then jump into replays. teamwork communication map control Team paintball meets capture-the-flag: squads split roles, call positions,…
related reading
- Exclusive: Emmett Shear Is Back With a New Company and A Lot of Alignmentcorememory.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
- Teaching Claude why \ Anthropicanthropic.com
- Patterns and problems in multiagent systemsanthropic.com
- [2411.00114] Project Sid: Many-agent simulations toward AI civilizationarxiv.org
- Inner Alignment: Explain like I'm 12 Edition — LessWronglesswrong.com
- Of Swarms and Sand Godsblog.cosmos-institute.org
- The social AI hypothesissubstack.com
- Towards a scale-free theory of intelligent agencymindthefuture.info
- Sequent: scale and automation for higher confidence in alignment — AI Alignment Forumalignmentforum.org