Here Is Google’s List of Fears About Artificial Intelligence

Here Is Google's List of Fears About Artificial Intelligence  #ai

  • Unlike software a robot that’s trying new things may actually cause humans harm.
  • Robots will learn the same way as AI algorithms, through repetition and exploration.
  • For example, the robot should experiment with mopping strategies, but putting a wet mop in an electrical outlet is a very bad idea.
  • Of the five main concerns outlined in the paper, avoiding negative side effects is top of the list.
  • So if your future robot starts tearing down doors because it thinks it’s more efficient, just make sure you put it on the naughty step for 10 minutes to cool down.

Read the full article, click here.


@RickKing16: “Here Is Google’s List of Fears About Artificial Intelligence #ai”


​At least somebody’s preparing for the robopocalypse.​


Here Is Google’s List of Fears About Artificial Intelligence

Concrete AI safety problems

Concrete #AI safety problems

  • Advancing AI requires making AI systems smarter, but it also requires preventing accidents – that is, ensuring that AI systems do what people actually want them to do.
  • We think that broad AI safety collaborations will enable everyone to build better machine learning systems.
  • We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety .
  • Many of the problems are not new, but the paper explores them in the context of cutting-edge systems.
  • The paper explores many research problems around ensuring that modern machine learning systems operate as intended.

Read the full article, click here.


@RickKing16: “Concrete #AI safety problems”


We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as intended. (The problems are very practical, and we’ve already seen some being integrated into OpenAI Gym.)


Concrete AI safety problems