您现在的位置是:Generative AI can't find its own errors. Do we need better prompts? >>正文

Generative AI can't find its own errors. Do we need better prompts?

后花园论坛社区|2024夜上海论坛网|爱上海419论坛 -- Back garden8人已围观

简介MR.Cole_Photographer/Getty ImagesThe field of deep learning artificial intelligence, especially the ...

MR.Cole_Photographer/Getty Images

The field of deep learning artificial intelligence, especially the area of "large language models," is trying to determine why the programs notoriously lapse into inaccuracies, often referred to as "hallucinations."

Google's DeepMind unit tackles the question in a recent report, framing the matter as a paradox: If a large language model can conceivably "self-correct," meaning, figure out where it has erred, why doesn't it just give the right answer to begin with?

futuristic conceptAI in 2023: A year of breakthroughs that left no human thing unchanged Abstract people silhouettes against glass, 3D generated image.These are the jobs most likely to be taken over by AI 5G in cityAI at the edge: 5G and the Internet of Things see fast times ahead Outline of brain with geometric shapes insideAlmost half of tech executives say their organizations aren't ready for AI or other advanced initiatives futuristic conceptAI in 2023: A year of breakthroughs that left no human thing unchanged
  • Abstract people silhouettes against glass, 3D generated image.These are the jobs most likely to be taken over by AI
  • 5G in cityAI at the edge: 5G and the Internet of Things see fast times ahead
  • Outline of brain with geometric shapes insideAlmost half of tech executives say their organizations aren't ready for AI or other advanced initiatives
  • Editorial standards Show Comments

    Tags:

    相关文章

    

    友情链接