You may remember my post on artificial intelligence and how it fit into art. Recently, the company behind DALL-E 2, OpenAI, launched ChatGPT.
Described as a language model, it’s essentially a chatbot that you type to and it answers with human-like responses.
As I already had an account with OpenAI from my days exploring the talents of DALL-E 2, I didn’t have to sign up for or register a new account. I simply logged into the site and started a conversation. If it’s anything like the art-creating AI, it may just take a few days to approve your account.
Something different than DALL-E is you aren’t limited to a number of credits per month. As far as I can tell, it is fully free with no restrictions. Well, there are a few restrictions:
- It has limited knowledge of events after 2021, so it can’t give you the latest news.
- It was only launched in November of 2022 so its still learning and may produce some inaccurate information.
- Still learning, it may provide occasionally harmful or biased content.
The more people use it, the more it learns, adapts, and provides scary good replies.
I enjoyed talking with it about visa requirements in obscure countries, recipes for French dishes I wanted to try, and the future of AI.
I asked the ‘Assistant’ as it asked to be called to answer a question for me:
“What does the future of AI language models look like?”
Within a few seconds, I had a response typed out in front of me. This was it:
It is difficult to predict exactly what the future of AI language models will look like, as the field is constantly evolving and advancing. However, there are a few trends and developments that are likely to shape the future of these models: Increased capabilities: As AI language models become more powerful and sophisticated, they will be able to perform a wider range of tasks and generate more human-like text. This could include things like improved machine translation, more realistic virtual assistants, and the ability to generate text that is more coherent and nuanced. Greater efficiency: One of the challenges with current AI language models is that they require a lot of computational resources to run. In the future, it is likely that these models will become more efficient, allowing them to run on a wider range of devices and potentially even in real-time applications. Broader applications: As AI language models become more advanced, they will likely find their way into an increasing number of industries and applications. This could include areas like healthcare, finance, and education, where the ability to process and understand natural language could be particularly useful. Overall, the future of AI language models looks bright, and it will be exciting to see the new and innovative ways in which these models will be used in the coming years.
As it seems to reflect the content that it has learned from, I don’t (yet) see it developing critical thoughts and ideas, but it can certainly replicate others that have been posted. It’s a great starting point and I have zero doubt in my mind that we will continue to see AI growth in our lives.
*Featured image made using NightCafe*
Kelton Goes 