Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cya AI

Ongera usuzume ibyiciro byambere byamahugurwa ya AI, hamwe namahame yanditse, kunegura no gusubiramo, ibyifuzo bya AI, kandi ugumane amakuru afasha abantu.

Inzira zijyanye no kuyoboraAI
Ikibazo 1 Bya 8

'Itegekonshinga' ni iki muri AI?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. 'Itegekonshinga' ni iki muri AI?
    • Amasezerano yemewe hagati yumukoresha nisosiyete
    • Icyitegererezo cyimyubakire yububiko
    • Urutonde rwamahame rwanditse rwerekana uburyo bwo kunegura no kuyobora ibisubizo byabwo
    • Urutonde rwamagambo yabujijwe
  2. What annotation burden does the original Constitutional AI study aim to reduce?
    • Every possible source of human judgment or training data
    • All model memory during inference
    • The need to evaluate any model behavior
    • Reliance on human labels identifying harmful outputs
  3. Mu cyiciro gikurikiranwa na AI Itegekonshinga, icyitegererezo gikora iki kumusaruro wacyo?
    • Gusiba nta bisobanuro
    • Kunegura binyuranyije n'ihame hanyuma bikavugurura kugirango bibe byiza
    • Ihindure mu rundi rurimi
    • Shishoza kubwumutekano
  4. RLAIF igereranya iki murwego rwo gushimangira-kwiga?
    • Gushimangira Kwiga Biturutse kuri AI
    • Kwiga Kwisubiramo Mubikorwa Byimbere
    • Kugabanya Ubukererwe bwa AI
    • Umukoro Wibisanzwe Umukoro Muburyo bwiza
  5. What transparency benefit can written constitutional principles provide?
    • A complete display of every learned internal preference
    • Proof that every future response follows all principles
    • Automatic elimination of the preference model
    • An inspectable statement of intended guidance used in the process
  6. Which broader research idea does using AI-generated supervision support?
    • Eliminating every evaluation by definition
    • Exploring how AI can help supervise other AI systems
    • Guaranteeing zero cost for all future training
    • Automatically increasing every model’s vocabulary
  7. Does editing a constitution document alone retroactively change the weights of an already saved trained model?
    • No; a training or runtime process must use the changed guidance
    • Yes; all saved checkpoints instantly rewrite themselves
    • Yes; written words directly become new neural weights without execution
    • No model process can ever consume written principles
  8. Which human comparison data did the original Constitutional AI RL experiments retain alongside AI harmlessness preferences?
    • Only human GPU-temperature measurements
    • No human comparison data of any kind
    • Human helpfulness comparisons
    • A mandatory human label for every harmlessness pair