Practice makes perfect. Agentic AI pro-social behavior as a missing alignment corpus. by Alex Novikau

·Nuno Sempere··

As AI sys­tems are be­com­ing in­creas­ingly use­ful and used, they gain iden­tities, au­thor­ity to act, in­clud­ing con­trol of re­sources, and ac­cess to in­creas­ingly com­plex tool­ing. This de­ploy­ment layer which AI op­er­ates, and not just the mod­els them­selves, are also in­creas­ingly be­com­ing a fo­cus of al­ign­ment. Cur­rently this layer is mostly pro­duc­tion-ori­ented and, more re­cently, com­mer­cial. Agents write soft­ware, con­duct re­search, man­age work­flows and now also ...

Read full article →

Related Articles

Will I solve an unsolved math problem with AI in September?
Bayesian · Manifold Markets · 1d ago
Claude Fable 5.1+ (Anthropic) release date
Bayesian · Manifold Markets · 2d ago
Openai Astra publically available before September 7th 2026
winged_one · Manifold Markets · 3d ago
September 2026 AI model releases
prismatic · Manifold Markets · 3d ago
Will any model at least as good as Claude Fable 5 and 10x cheaper be released by the end of March 2027?
Ben · Manifold Markets · 3d ago