I’ve never used ChatGPT, so I don’t know if there’s an offline version. So I assume everything that you typed in, is in turn used to train the model. Thus, using it will probably leak sensitive information.
Also from what I read is that, the replies are convincing enough, but could sometimes be very wrong, thus if you’re using it for machineries, medical stuff, etc, it could end up fatal.
I’ve never used ChatGPT, so I don’t know if there’s an offline version.
There is no offline version of ChatGPT itself, but many competing LLMs are available to run locally, e.g. Facebook just released Llama2 and Llama.cpp is a popular way to run those models. The smaller models work reasonably well on modern consumer hardware, the bigger ones less so.
but could sometimes be very wrong
They are mostly correct when you stay within the bounds of its training material. They are completely fiction when you go out of it or try to dig to deep (e.g. summary of popular movie will be fine, asking for specific lines of dialog will be made up, summary of less popular movie might be complete fiction).
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@beehaw.org
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
https://www.techradar.com/news/samsung-workers-leaked-company-secrets-by-using-chatgpt
I’ve never used ChatGPT, so I don’t know if there’s an offline version. So I assume everything that you typed in, is in turn used to train the model. Thus, using it will probably leak sensitive information.
Also from what I read is that, the replies are convincing enough, but could sometimes be very wrong, thus if you’re using it for machineries, medical stuff, etc, it could end up fatal.
There is no offline version of ChatGPT itself, but many competing LLMs are available to run locally, e.g. Facebook just released Llama2 and Llama.cpp is a popular way to run those models. The smaller models work reasonably well on modern consumer hardware, the bigger ones less so.
They are mostly correct when you stay within the bounds of its training material. They are completely fiction when you go out of it or try to dig to deep (e.g. summary of popular movie will be fine, asking for specific lines of dialog will be made up, summary of less popular movie might be complete fiction).