AI written books

[Quoth]

Originally Posted by Pierre Lawrence

More on AI neural networks vs. the brain:

https://nautil.us/why-the-brain-is-so-noisy-237301/

https://www.theregister.com/2023/03/...tion/?td=rt-3a

[Quoth]

Hype? Who says there is too much AI hype?
https://www.theregister.com/2023/02/...ers/?td=rt-9cp

[arjaybe]

I don't know what's worse, AI writing or bare links.-)

[ownedbycats]

https://www.reuters.com/legal/ai-cre...gy-2023-02-22/

Feb 22 (Reuters) - Images in a graphic novel that were created using the artificial-intelligence system Midjourney should not have been granted copyright protection, the U.S. Copyright Office said in a letter seen by Reuters.

"Zarya of the Dawn" author Kris Kashtanova is entitled to a copyright for the parts of the book Kashtanova wrote and arranged, but not for the images produced by Midjourney, the office said in its letter, dated Tuesday.

The decision is one of the first by a U.S. court or agency on the scope of copyright protection for works created with AI, and comes amid the meteoric rise of generative AI software like Midjourney, Dall-E and ChatGPT.

The Copyright Office said in its letter that it would reissue its registration for "Zarya of the Dawn" to omit images that "are not the product of human authorship" and therefore cannot be copyrighted.

[j.p.s]

So, will thesaurus use endanger copyrightability?

[DNSB]

Originally Posted by j.p.s

So, will thesaurus use endanger copyrightability?

Only if the A.I. uses the thesaurus.

[Fat Abe]

The concept of a machine writing books was predicted in 1953 by Roald Dahl, in the short story, The Great Automatic Grammatizator.

https://longreads.com/2019/08/20/the...st-its-author/

I am convinced by the books I read on Kindle Unlimited that many untalented writers are resorting to bots to write their novels. The true Turing test will be having the Nobel or Pulitzer prize committees praise a machine written novel as the greatest book since War and Peace.

[arjaybe]

Originally Posted by Fat Abe

The concept of a machine writing books was predicted in 1953 by Roald Dahl, in the short story, The Great Automatic Grammatizator.

https://longreads.com/2019/08/20/the...st-its-author/

I am convinced by the books I read on Kindle Unlimited that many untalented writers are resorting to bots to write their novels. The true Turing test will be having the Nobel or Pulitzer prize committees praise a machine written novel as the greatest book since War and Peace.

And shortly after that the committees will be bots and the prizes will be handed out by other bots. Then we'll all have to use bots to read everything because there's no way humans will be able to keep up.

[ZodWallop]

Seeing what's happened with Bing, I don't think A.I is ready to write a novel yet.

The stories of the chatbot going rogue tend to occur after long conversations. The one reported on by the New York Times was 2+ hours long. Now the Bing chatbot is limited to eight messages and you have to clear and start over.

ChatCPT can fool people for a while. But in the end, it is not truly intelligent and the longer the conversation goes, the more cracks show. I've seen it spit out short stories. But I doubt it could convincingly write an extended narrative.

[gmw]

Originally Posted by ZodWallop

Seeing what's happened with Bing, I don't think A.I is ready to write a novel yet.

The stories of the chatbot going rogue tend to occur after long conversations. The one reported on by the New York Times was 2+ hours long. Now the Bing chatbot is limited to eight messages and you have to clear and start over.

ChatCPT can fool people for a while. But in the end, it is not truly intelligent and the longer the conversation goes, the more cracks show. I've seen it spit out short stories. But I doubt it could convincingly write an extended narrative.

I think your post covers the current state of "A.I." quite well: it's not there yet. But one of the things I find most interesting is how close, even in its still quite primitive state, these systems are coming to seeming human, and so presumed - although arguably - "intelligent". Obviously I'm not the first to question whether humans are intelligent*, but it does leave one pondering just what we mean by intelligence.


* See Monty Python's Galaxy Song: "And pray that there's intelligent life somewhere up in space, Cause there's bugger-all down here on Earth"

[JSWolf]

Originally Posted by Critteranne

Grimdark magazine also posted a statement on AI.

They say that this is going to impact their open submissions window. For now, they have paused open submissions and are going on a "solicitation-only basis." They also realize this sucks because they are looking for new writers in all parts of the world.

Answer by ChatGPT.

It's interesting to see how the adoption of AI technology is impacting the publishing industry, including literary magazines like Grimdark. It seems like they are taking a cautious approach to integrating AI into their submission process and recognizing the limitations of the technology.

It's unfortunate that this decision means they have to pause their open submissions window, but it's good that they are still actively seeking out new writers through solicitation. Hopefully, as AI technology continues to develop, they will be able to find a way to incorporate it more seamlessly into their submission process while still maintaining the human touch that is so important in the publishing industry.

[Quoth]

https://www.schneier.com/blog/archiv...ng-models.html
And you can't easily secure a machine "learning" system.

bstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. Delegation of learning has clear benefits, and at the same time raises serious concerns of trust. This work studies possible abuses of power by untrusted learners.We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate “backdoor key,” the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees.

But how can we trust the systems that haven't been outsourced? The companies with the resources have shown themselves to be untrustworthy and have the attitude that laws only apply to companies not using the Internet (Google, Meta/Facebook, Uber, AirBnB etc).

[gmw]

Originally Posted by Quoth

https://www.schneier.com/blog/archiv...ng-models.html
And you can't easily secure a machine "learning" system.


But how can we trust the systems that haven't been outsourced? The companies with the resources have shown themselves to be untrustworthy and have the attitude that laws only apply to companies not using the Internet (Google, Meta/Facebook, Uber, AirBnB etc).

Exactly the same way we trust (or don't trust) them now. Even with most of the open-source software that I use I have to trust that someone somewhere has done appropriate checking, because I simply don't have the time to check it myself. (And in many cases I don't have the expertise even if I did have the time.)

The problem is that "undetectable backdoor" mentioned - which may be intentional or accidental. AIs are trained rather than programmed partly due to the volume of information involved and partly due to the complexity that is inherent in the volume. The result is something a human cannot get their head around (if they could they could be programming it directly). The result is not the implacably logical thing of science-fiction, but something messy and potentially unpredictable. So it is no longer a matter of trusting that someone has checked it, now it's a matter of knowing that no one has been able to check it except in the most superficial manner. Of knowing that evaluating an AI has become a matter of suck-it-and-see. Of course, entities like Google have access to a few billion people willing to do their sucking for free, so that may be a vote in their favour.

[Quoth]

Artificial intelligence in its current form is based on the wholesale appropriation of existing culture, and the notion that it is actually intelligent could be actively dangerous
by James Bridle

https://www.theguardian.com/technolo...dall-e-chatgpt

[gmw]

Originally Posted by Quoth

https://www.theguardian.com/technolo...dall-e-chatgpt

The same could be said of raising baby humans.