OpenAI recently introduced a new language model called ChatGPT that has the potential to revolutionize the way we interact with machines.
So much so, that he himself wrote the introduction to the article.
Because I worried that this bold move would make me question my usefulness as a real-life human reporter, I decided to commission the world’s most popular new chatbot to help write a story about itself.
I do mean the new favorite of the world: ChatGPT has amassed over 1 million users in less than a week after its public release.
While previous chatbots have been fairly restrained in their stated ambitions (Google’s LaMDA operates within extremely limited parameters), or quickly manipulated to become extremely aggressive (Microsoft’s infamous Tay says hello, or maybe it’s not very polite), ChatGPT shows incredible range.
ChatGPT is a large-scale language model trained on large amounts of text data to generate human-like text from given cues.
It also wrote that paragraph as part of the introduction I asked it to write a news article about the potential of ChatGPT (and from this point, let’s italicize its contribution).
One of the main features of ChatGPT is its ability to generate long-form text.
Unlike some other language models that are limited to generating short phrases or sentences, ChatGPT can generate several long paragraphs of text.
This makes it ideal for tasks like generating news articles, stories, or even entire books.
Bold claim, but it’s undeniable that people interacting with it got far more results than previously released chatbots.
Guy Parsons shares how it gave him some ambitious home decor ideas:
Amjad Masad was amazed by its ability to identify, explain and fix coding errors:
Many people think that ChatGPT has potential as a search engine replacement, or even a replacement, because it provides detailed answers to many questions:
Sky’s own Ed Conway commissioned it to write a column on QE:
As Ed rightly points out, the results are impressive but dull – dubious and sterile imitations of real newspaper columns rather than convincing alternatives.
Ask about the top line of stories Harry and Meghan’s Netflix series Considering that ChatGPT’s training data only lasts until 2021, there is no mention of the current context.
Prince Harry and Meghan Markle have signed a multi-year deal with Netflix to produce a variety of content, including documentaries, series, features and children’s shows.
But for some background contexts it does a good job.
ChatGPT was blunt when asked why Harry and Meghan quit the royal family.
Prince Harry and Meghan Markle announced their decision to step down from royal duties in January 2020.
In a statement, the couple cited their desire to achieve financial independence and focus on philanthropy as the main reasons for their decision.
and ask to define Streptococcus AIt provides a crisp response.
If you suspect you have a group A strep infection, it is important to see your doctor so that appropriate treatment can be given.
But it’s easy to see how such AI could be misused, whether to indulge laziness or something more sinister.
like deepfakes did to videoThe potential for artificial intelligence to generate text that is barely discernible to humans will ring alarm bells that it can be exploited maliciously.
As with any technology, AI has the potential to be used maliciously by individuals or organizations with malicious intent.
For its part, OpenAI says ChatGPT still has a lot of room for improvement: Answers can be “incorrect or nonsensical” — although they sound legitimate in most cases — it can also be “too verbose” and “Overuse of certain phrases”.
While the tech company “works hard to have the model reject inappropriate requests, it sometimes responds to harmful instructions or exhibits biased behavior”.
read more:
“Don’t be afraid of artificial intelligence”
“I’m in love with my AI girlfriend”
AI ‘could help UK fight disinformation’
Can machines have feelings?
I ended our own conversation by asking him if he thought I needed to adapt to AI as a journalist.
It is important for journalists to understand advances in artificial intelligence and how they could potentially impact journalism. However, rather than adapting to AI, it is more important for journalists to focus on honing their craft and keeping abreast of the latest developments in their field.
Well, that’s what I was told.