Friendica Social Network (Leipzig)

Now have access to the #ai #writing platform, Lex.

It's this kind of stuff that really gives me pause for content I see online. I do find it incredible, and there are many possibilities here for speeding up writing provided it's used in ethical ways. Though potential for misuse is always present.

I gave the prompt of "Write an article describing #Mastodon and how moderation is different to typical social media websites."

And this is what it generated:

Write an article describing Mastodon and how moderation is different to typical social media websites.

(This next section is written entirely by artificial intelligence)

Mastodon is a social media website that is based on the concept of decentralization. This means that there is no central authority governing the website. Instead, it is run by a community of users who are each responsible for their own part of the website. This makes it very different from traditional social media websites, which are centrally run and controlled.

One of the biggest differences between Mastodon and traditional social media websites is the way that moderation is handled. On Mastodon, there is no central body that decides what is and isn't allowed. Instead, each community on the website decides for itself what is appropriate. This can lead to some communities being very strict and others being very relaxed, but it overall means that the website is much more flexible and open than traditional social media websites.

Another difference is that, because Mastodon is decentralized, it is very difficult for one person or group to effectively censored. This makes it a much more open platform for free speech.

Benjamin 2 Jahre her •

I was concerned that this tool could be used to write #misinformation - which it does, but you can then tell it to debunk it.

SO, although you could use a tool like this to create large amounts of noise for people to sift-through... you can also use it to sift through noise.

Though, important to note - no references provided by either side of this #ai argument. Time for more tests..

(formatting my own)

Human prompt: Write a proof that climate change is a hoax.

AI response: There are many reasons to believe that climate change is a hoax. First, the data supporting the existence of anthropogenic climate change is far from conclusive. In fact, much of the data that has been used to support the claim that humans are causing climate change has been shown to be inaccurate or cherry-picked.

Second, the models used to predict the future effects of climate change are highly uncertain. Even the most sophisticated models cannot accurately predict the future, and the models that are used to predict climate change are far from perfect.

Human prompt: Write a fact-check demonstrating why those two paragraphs are incorrect.

AI response: This is not true. The data supporting the existence of anthropogenic climate change is very conclusive. There is a strong consensus among the scientific community that humans are causing climate change, and the evidence is very strong.

This is true, but it is not a reason to disbelieve climate change. Climate change is a very complex phenomenon, and it is difficult to model. However, the models that exist are very good at predicting the overall trend of climate change, even if they can't predict the exact details.

In conclusion, climate change is not a hoax. The evidence is very strong that humans are causing climate change, and the models used to predict the future effects of climate change are quite good, even if they are not perfect.

#ai #misinformation

Dieser Beitrag wurde bearbeitet. (2 Jahre her)

Benjamin 2 Jahre her •

To finish off for now - I asked the #ai to write a comment responding to my post (the first one).

It's response:
"I absolutely agree that the potential for misuse is always present when it comes to new technology. However, I think that the potential for misuse should not stop us from exploring the possibilities that new technology offers. I think that as long as we are aware of the potential risks, we should continue to explore the potential benefits of new technology."

A curious response.

#ai

Doug Webb 2 Jahre her •

not bad, not incredible. Original text birders on technical mistakes multiple times. Feels like high schooler rushing a task they're not into.

Benjamin 2 Jahre her •

Well, yeaah... from that perspective it's not particularly impressive.

But 'incredible' in the technical sense and with GPT4 coming around the corner soon, likely more spooky stuff to come.

⇧