[HN Gopher] Implementing GPTZero from scratch - Reverse engineer...
       ___________________________________________________________________
        
       Implementing GPTZero from scratch - Reverse engineering GPTZero
        
       Author : burhanultayyab
       Score  : 81 points
       Date   : 2023-01-28 13:24 UTC (9 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | sdrg822 wrote:
       | Given that GPTZero was an undergrad's side project it's not that
       | surprising?
        
         | bablawexler wrote:
         | where can I see your code if that's so easy
        
       | rvz wrote:
       | Good. A detector should have been written and open-sourced
       | _before_ releasing GPT in the first place, especially by OpenAI
       | themselves. A shame that someone else had to do the work other
       | than them.
       | 
       | Better late than never to open source it now, unlike the original
       | creator of GPT Zero or OpenAI doing it.
        
         | cwmoore wrote:
         | They would be in a position to log hashes of generated
         | substrings, multiple of which in a document would indicate a
         | high likelihood indicator of the source. Solving for the Turing
         | Test appears to have been a poorly chosen goal.
        
           | burhanultayyab wrote:
           | You are correct, that's why we're working on a version 2 of
           | it where we're using LLM Transformers fighting adverserially
           | to make it better.
        
       | burhanultayyab wrote:
       | We've gone through the original implementation of GPTZero and
       | successfully reverse engineer it. (it gives the same results as
       | original GPTZero). We've also recorded the implementation process
       | which can be found below.
       | 
       | Youtube Implementation Video: https://youtu.be/x9H-aY5sCDA
       | 
       | Github: https://github.com/BurhanUlTayyab/GPTZero
       | 
       | Website: https://gptzero.sg
       | 
       | Discord: https://discord.com/invite/F3kFan28vH
       | 
       | We're also working on a GPTZerov2 (inspired by LLM based
       | transformers and GANs), which would be more accurate, and can
       | detect lines changed by humans.
       | 
       | Please give some feedback on our work.
       | 
       | Thanks
        
       | forgotpwd16 wrote:
       | >our implementation gets the exact same results
       | 
       | Considering https://news.ycombinator.com/item?id=34556681 that
       | isn't really a good thing to have.
       | 
       | That said, good work replicating it.
        
         | burhanultayyab wrote:
         | Thanks for the complement. We would be more cautious in the
         | future.
        
       | nicholaswork wrote:
       | Interesting and the website is more responsive than the original.
        
         | burhanultayyab wrote:
         | Thanks for the complement.
        
           | nacs wrote:
           | Do you/your dev-partner give each other compliments like this
           | while developing too or just at the end?
        
         | forgotpwd16 wrote:
         | Complementing the project in which you're one of the two devs
         | is a bit strange imo.
         | 
         | https://github.com/BurhanUlTayyab/GPTZero/commits/main
        
           | dboreham wrote:
           | Why?
        
             | Bootvis wrote:
             | It's disingenuous to pretend to be an ordinary commenter
             | while praising your own work.
        
             | ausudhz wrote:
             | Conflict of interest
        
       ___________________________________________________________________
       (page generated 2023-01-28 23:01 UTC)