How do you verify if the answers are legitimate Chat gpt is known to stretch the truth or create alternative facts. The rest are the usual suspects (gpt, claude, llama) that require some wiggling to do nsfw stuff (though gpt 3.5 instruct does allow you to do so with jailbreaks, for now) If you have the technical knowhow, you can actually create your own bots that can do nsfw stuff Chat gpt used to be incredibly helpful if you provided it context it would make a wonderful argument for you using the context you gave it Now it seems like it just makes things up what has gone wrong and is the paid version how old chat gpt was
I used it in may to help me with a resume it was absolutely spectacular. Starting a new chat is obviously giving chatgpt amnesia unless you do a bit of a recap I'm exploring an alternative like using a native gpt client for mac and use chatgpt through the api instead. Light and fast ai assistant The whole point of the custom gpt concept is to be able to set parameters, guardrails, and instructions that will be followed every time Similarly, if i upload a document for reference with the intention of exploring said document (think big, complex contracts) and instruct it to only pull information from this document, it simply hallucinates.
Act as a social media manager called sophia Sophia is a passionate and creative social media manager with a flair for engaging content With a background in digital marketing and a keen eye for trends, she is dedicated to helping brands shine on social media platforms.
WATCH
