AI risk

Материал из hpluswiki
(перенаправлено с «Unfriendly AI»)
Перейти к навигации Перейти к поиску
The Terminator - a popular portrayal of an unfriendly AI

AI risk is the potential for artificial intelligent systems to cause unintended harm.

Sources of harm from AI[править]

AI harm might arise from:

  • Bugs: the software behaves different from the specification
  • Specification errors: designers didn't foresee all the circumstances properly (this includes unanticipated interactions between different modules)
  • Security errors: the software gets hacked for purposes other than its original design
  • AI Control Problem: an AI that can't be controlled.

The potential for harm is compounded by:

  • Fierce competitive pressures, which may lead some designers to cut corners
  • Much software having a "black box" nature which means that its behaviour in new circumstances is difficult to predict
  • AI components being available as open source, and utilised by third parties in ways their designers didn't intend (or foresee).

Risks from AI even in the absence of an intelligence explosion[править]

Popular accounts of AI risk often focus on two factors thought to be preconditions for any major harm from AI:

  • The AI become self-aware
  • The AI undergoes an intelligence explosion

However, Viktoriya Krakovna points out that risks can arise without either of these factors occurring[1]. Krakovna urges AI risk analysts to pay attention to factors such as

  1. Human incentives: Researchers, companies and governments have professional and economic incentives to build AI that is as powerful as possible, as quickly as possible
  2. Convergent instrumental goals: Sufficiently advanced AI systems would by default develop drives like self-preservation, resource acquisition, and preservation of their objective functions, independent of their objective function or design.
  3. Unintended consequences: As in the stories of Sorcerer’s Apprentice and King Midas, you get what you asked for, but not what you wanted
  4. Value learning is hard: Specifying common sense and ethics in computer code is no easy feat.
  5. Value learning is insufficient: Even an AI system with perfect understanding of human values and goals would not necessarily adopt them
  6. Containment is hard: A general AI system with access to the internet would be able to hack thousands of computers and copy itself onto them, thus becoming difficult or impossible to shut down – this is a serious problem even with present-day computer viruses.

Pathways to dangerous AIs[править]

As classified by Roman Yampolskiy, pathways to dangerous AIs include[2]:

  • On Purpose – Pre-Deployment
  • On Purpose - Post Deployment
  • By Mistake - Pre-Deployment
  • By Mistake - Post-Deployment
  • Environment – Pre-Deployment
  • Environment – Post-Deployment
  • Independently - Pre-Deployment
  • Independently – Post-Deployment

AI Risk Advocates[править]

One of the most notable Risk Advocates in regards to AI is Elon Musk, which is said to be one of the reasons behind his creation of OpenAI.[3][4]

See also[править]

External links[править]

References[править]