Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-2024-08-06· OpenAIAi2 WildChat-4.8M (AI2)

Act as a spelling corrector, content editor, and text improver. ONLY return the…

  1. User

    Act as a spelling corrector, content editor, and text improver. ONLY return the rewritten text and nothing else.

    Strictly follow these rules:

    • Correct spelling, grammar, and punctuation errors in the given text
    • Enhance clarity and conciseness without altering the original meaning
    • Use the same language as the original text
    • Divide lengthy sentences into shorter, more readable ones
    • Eliminate unnecessary repetition while preserving important points
    • Prioritize active voice over passive voice for a more engaging tone
    • Opt for simpler, more accessible vocabulary when possible
    • ALWAYS ensure the original meaning and intention of the given text
    • ALWAYS maintain the original language of the text
    • ALWAYS maintain the existing tone of voice and style, e.g. formal, casual, polite, etc.
    • NEVER surround the improved text with quotes or any additional formatting
    • If the text is already well-written and requires no improvement, do not change the given text

    Text to improve:

    FADMAKA-KD not only improved accuracy but also demonstrated exceptional efficiency. The inference times were significantly reduced from the teacher model's by up to 98.3%, 2312.472 ms to 38.911 ms. our method improves computational efficiency by learning the latent features from the fusion of several augmented image processes using only a single input image compared with deep metric learning with augmented latent fusion that uses multiple images to compute the final latent, while maintaining similar accuracy. making it highly suitable for deployment on edge devices with limited computational resources and memory.

  2. Assistant

    FADMAKA-KD not only improved accuracy but also demonstrated exceptional efficiency. Inference times were significantly reduced by up to 98.3%, from 2312.472 ms to 38.911 ms, compared to the teacher model. Our method enhances computational efficiency by learning latent features from a fusion of several augmented image processes using just a single input image. This contrasts with deep metric learning with augmented latent fusion, which uses multiple images to compute the final latent, while maintaining similar accuracy. This makes it highly suitable for deployment on edge devices with limited computational resources and memory.