Alignment
Making systems that pursue what we actually intend.
Está a ver um explicador de conceito: o que este termo significa em linguagem acessível, e os registos que relaciona.
Alignment is the technical project of keeping AI goals and behavior matched to human intent — today via RLHF, constitutional AI and evaluations; tomorrow, for systems smarter than their overseers, via open research problems like scalable oversight. Failures at current scale look like sycophancy or reward hacking; the field's founding worry is that failures at higher capability may not be recoverable. Anthropic's founding thesis and OpenAI's charter both center on it.
Como este elemento se liga ao resto da stack
As ligações deste registo num relance — clique num grupo para ir diretamente até ele.
Introduzido
Fontes
Registro revisado em 2026-01-15 — ver Metodologia.