Il prossimoProssima guida
Sintonizzazione delle istruzioni
Intelligenza artificiale linguistica
GUIDA ALL'AI linguistica
The original Constitutional AI research uses written principles to guide self-critique, response revision, and AI preference judgments during training.
Ascolta questa guidaNarrato dall'IA · ~3 min
It reduces reliance on human harmlessness labels in the studied setup, while leaving human choices and evaluation important.
Constitutional AI: Harmlessness from AI Feedback presents a training method with supervised and reinforcement-learning phases. The constitution is written normative guidance used to evaluate responses, rather than a legal contract or the model’s architecture. In the supervised phase, the system generates responses, produces critiques under selected principles, and revises those responses. The model is then fine-tuned on the revised answers. Critiquing a draft and training from revisions are different operations: the former creates examples, while the latter changes model parameters. In the reinforcement-learning phase, a model compares response pairs according to principles and creates AI preference data. A learned preference model then supplies a reward signal for reinforcement learning. This is the RLAIF component of the stated method, not an instruction to replace every possible human training signal. The original experiments retain human helpfulness comparisons while replacing human harmlessness labels with AI-generated feedback. People also choose principles and assess results. Written guidance can make intended values easier to inspect, but cannot expose every learned internal preference or prove that every output follows those values. Editing the document alone does not retroactively retrain an already saved model; a relevant training or runtime process must actually use the changed guidance. Anthropic’s later specific-versus-general principles study compares broad and detailed guidance in particular dialogue-model experiments. Its findings do not imply that one short rule reliably resolves every normative conflict. Historical methods and principles should be identified by their version rather than treated as a complete description of every current Claude model.
Comparing a draft response with a revision guided by a stated principle.
Inspecting AI-generated preference judgments used to train a preference model.
Testing whether a trained model follows a principle on held-out examples.
Comparing broad and specific principles under a defined research evaluation.
Principle-based training experiments can compare broad guidance, detailed rules, conflicting priorities, and the quality of generated feedback. Their reports should identify the constitution version, model, training procedure, and evaluation population. Public input or expert review could help choose principles, while disagreement and ambiguity still need explicit treatment. AI-generated judgments can reduce some annotation work but remain fallible and may inherit model biases. Evaluating actual behavior and retained human oversight is more informative than assuming that a written rulebook guarantees harmlessness or fully explains every learned decision.
Newsletter gratuita
Tre storie verificate sull'IA ogni mattina nei giorni feriali, scritte in un inglese semplice. Gratuito per sempre, senza pubblicità.
Un'email ogni giorno feriale. Disiscriviti con un clic. Non vendiamo né condividiamo mai il tuo indirizzo.
Mettiti alla prova
Feedback immediato su ogni risposta e un certificato condivisibile con un ID verificabile una volta superato un corso.
Sostieni l'istruzione gratuita sull'IA. AI Understanding è un'organizzazione non profit 501(c)(3) — nessun annuncio, nessun paywall, mai. Fai una donazione
The original Constitutional AI research uses written principles to guide self-critique, response revision, and AI preference judgments during training. It reduces reliance on human harmlessness labels in the studied setup, while leaving human choices and evaluation important.
La Costituzione è un insieme trasparente di principi scritti, tratti da fonti come i documenti sui diritti umani, che il modello utilizza per valutare e migliorare le sue risposte.
The original setup replaces harmlessness labels with AI feedback while retaining other human input.
Il modello esegue un ciclo di critica e revisione: identifica i punti in cui la sua bozza viola un principio campionato, quindi riscrive la risposta, creando dati di addestramento auto-migliorati.
RLAIF significa apprendimento per rinforzo dal feedback dell’intelligenza artificiale: un modello classifica le risposte in base alla costituzione, producendo dati sulle preferenze generati dall’intelligenza artificiale anziché etichette umane.
Readable principles expose intended guidance; adherence and learned behavior still require evaluation.
Continua a imparare
Altre guide selezionate per questo argomento
Il prossimoProssima guida
Sintonizzazione delle istruzioni
Intelligenza artificiale linguistica