drjohsmith
- Joined Dec 13, 2021
- 1,601
If thats what you want, Im certain @joeyd999 that if you dont want to participate, rather than be terminated, you could just stop posting,
Of course, that’s not how you would use ChatGPT for that sort of thing. You’d say “generate a Black Mirror episode with plot elements X, Y, and Z. ChatGPT will respond with something novel if that’s specified. But, I have to say, it is REALLY bad at writing jokes, so the episode might still be bad because of it simply being bad writing. Still, if you want to get novelty you have to seed it, to provide a framework.https://www.empireonline.com/tv/news/charlie-brooker-chatgpt-black-mirror-episode-exclusive-image/
Artificial intelligence is actually really stupid. ChatGPT will never be creative.
This was unexpected, perhaps it though I meant to write a novel…I asked it for the answer to a riddle. It answered as if it were a perfectly logical statement. I told ChatGPT it was a riddle and it claimed not to understand riddles or jokes.
OK but that's its function, to be a language droid.This was unexpected, perhaps it though I meant to write a novel…
Me: Give me a novel response to the classic joke question, “why did the chicken cross the road?”
ChatGPT: As the sun began its descent, casting a warm golden glow upon the world, the chicken stood at the precipice of its existence, peering beyond the asphalt expanse that lay before it. A soft breeze whispered secrets through the trees, as if urging the chicken to embark on a profound journey of self-discovery. With a heart filled with courage, the chicken took its first steps onto the sacred path.
For centuries, the chicken had been confined to the monotonous routine of the barnyard, longing for adventure and purpose beyond its feathered existence. It yearned to transcend the mundane and seek enlightenment in the great unknown. The road, that symbolic divider between the known and the mysterious, beckoned the chicken like a siren's call.
The chicken's quest was not simply to cross to the other side, but to unravel the enigma of its own being, to discover the essence of its existence. It knew that within the vastness of the world lay wisdom, experiences, and connections waiting to be explored.
As it traversed the treacherous asphalt, dodging the rumbling carriages that rushed by, the chicken pondered the question that had haunted its kind for generations. Why did it cross the road? The answer was both simple and profound: to embrace the symphony of life, to dance to the rhythm of the universe, and to embrace the limitless possibilities that awaited on the other side.
In that daring act of defiance, the chicken broke free from the chains of convention, becoming an icon of courage, inspiring others to question their own boundaries. Its journey reminded us that sometimes, the most profound answers lie beyond the mundane questions we ask. And as the chicken disappeared into the horizon, it left behind a legacy that would forever echo in the hearts of those who dared to dream.
ChatGPT likely 'wrote' that too.There was a man who lived and breathed for the thrill of adventure. He was a force of nature, a gladiator of the mountains, and a true embodiment of the human spirit's unbreakable will. With his eyes set on the highest peak on earth, Marco pushed his limits to the brink of sanity, defying death with every breath and leaving behind a legacy that would forever echo in the hearts of those who dared to dream.
Must be ChatGPT or it would have to be plagiarism.... and leaving behind a legacy that would forever echo in the hearts of those who dared to dream.
As a result, all artists, filmmakers, illustrators, and photographers commissioned by Nature "will be asked to confirm that none of the work they submit has been generated or augmented using generative AI.""Why are we disallowing the use of generative AI in visual content? Ultimately, it is a question of integrity. The process of publishing — as far as both science and art are concerned — is underpinned by a shared commitment to integrity. That includes transparency. As researchers, editors and publishers, we all need to know the sources of data and images, so that these can be verified as accurate and true. Existing generative AI tools do not provide access to their sources so that such verification can happen."
I once read an article about a tv producer/director saying that film making is a lot like cooking. It all boils down to taste ... I wonder about the kind of recipes that ChatGPT could come up with ...https://inews.co.uk/culture/televis...e-black-mirror-human-emotion-not-tech-2396597
Of course ChatGPT couldn’t write Black Mirror – it’s about humans, not tech
Writer Charlie Brooker tried and failed to get AI to write a Black Mirror episode, proving television is more than a good idea and a script playing that idea out
Give it a list of ingredients and ask it. Whether or not the results would be palatable is debatable.I wonder about the kind of recipes that ChatGPT could come up with ...
Using AI-generated data to train AI could introduce further errors into already error-prone models. Large language models regularly present false information as fact. If they generate incorrect output that is itself used to train other AI models, the errors can be absorbed by those models and amplified over time, making it more and more difficult to work out their origins, says Ilia Shumailov, a junior research fellow in computer science at Oxford University, who was not involved in the project.
Even worse, there’s no simple fix. “The problem is, when you’re using artificial data, you acquire the errors from the misunderstandings of the models and statistical errors,” he says. “You need to make sure that your errors are not biasing the output of other models, and there’s no simple way to do that.”

This is nothing more than a reflection of human nature that is seen -- and overlooked -- again and again throughout history.https://www.technologyreview.com/20...to-train-ai-are-outsourcing-their-work-to-ai/
The people paid to train AI are outsourcing their work… to AI
It’s a practice that could introduce further errors into already error-prone models.
View attachment 296921
A related case I heard if involved a new prison that had been built, using every anti-vandalism measure they could buy or devise. Vandalism was, it seems, a very costly problem.This is nothing more than a reflection of human nature that is seen -- and overlooked -- again and again throughout history.
People develop a technology and, through sheer wishful thinking, assume that it is going to work the way they would like it to work, even if that means assuming that everyone that uses it is going to behave as if they were experts in every field under the sun and are going to follow all of the ideal-case guidelines. But then the actual users of the technology assume that the technology is so perfect and anyone can use it and that it can be used for anything, regardless of whether it is actually suitable for that use. History is replete with examples.
The old Chinese-whispers effect. A classic example (probably fictional) being the war-time message sent as "The enemy's advancing on the left flank. Send reinforcements" but received as "The elephants are dancing on a wet plank. Send three and fourpence"Clones of clone of clones gets you exponentially decreasing levels of intelligence and increasing stupidity.
That's why we have “repeat-back” orders chains in the Navy.The old Chinese-whispers effect. A classic example (probably fictional) being the war-time message sent as "The enemy's advancing on the left flank. Send reinforcements" but received as "The elephants are dancing on a wet plank. Send three and fourpence"
[For the benefit of those not familiar with UK pre-decimal currency, that amount is 3 shillings and four pence]

This is something I've seen over and over and catalogue it as being victims of our own technological success. People in fields across the board rely, from day one, on the tools to do their thinking for them. The result is that you get degreed electrical engineers that can only use an oscilloscope with an auto-set button and blindly assume that whatever pressing it results in is correct. We are seeing the same thing with ChatGPT -- people are just blindly using it, assuming that whatever it spews forth must be good. I just got an e-mail from the university where I work talking about how we need to integrate ChatGPT into courses so that students can learn to utilize this productivity-enhancing tool.But they never looked, never knew to look, and had no idea it would be useful. For me, this, is the lesson here. The entire loop of trying to create something physical never involved actually looking at the result at the level they were creating it. They just used an instrument whose readings they didn't understand and parameters in a UI that were not doing what they claimed because the ink wasn't laid down as they'd just assumed it was.
| Thread starter | Similar threads | Forum | Replies | Date |
|---|---|---|---|---|
|
|
asked Chatgpt to recommend some upgrades/modifications for my Akai MPC3000 | General Electronics Chat | 1 |