Every new tool opens the door to new practices that were previously impossible, and LLMs have brought us Vibe Coding. The concept is simple: you describe an LLM what you want, and the LLM produces code. Then you play with your application, if it seems to work then you crack open a beer (or your beverage of choice); if it doesn't then you tell the LLM what the problem is and ask it to fix the code. It's a loop of refining the requirements over and over until the LLM gets it right without ever loo
  • thingsiplay ( thingsiplay@beehaw.org ) 
    3·
    1 year ago

    Edit: Looks like the tool I linked is total bogus.

    I’ve copied the text and put it into a tool that tries to find out if its written by an Ai (using an Ai model themselves off course, the irony). Here is one such: https://stealthwriter.ai/

    > About 66% of the content is likely human-written, while 34% appears AI-generated.

    The tool also has the ability trying to obfuscate or rewrite passages that should avoid being detected by such a tool themselves. So it is possible this article was written by an Ai model, a tool to obfuscate was used and them maybe a human edited and rephrased stuff. I can imagine this being part of the publishing process. Complete assumption by me here.