News   Dec 05, 2025
 675     2 
News   Dec 05, 2025
 2.2K     4 
News   Dec 05, 2025
 466     0 

Generative AI (ChatGPT, DeepSeek, Google AI, etc.)

Admiral Beez

Superstar
Member Bio
Joined
Apr 28, 2007
Messages
14,227
Reaction score
8,634
I tried to break ChatGPT below. My last question below was autocorrected by traditional google.

IMG_3279.png
 
Last edited:
People will laugh at the foibles of current AI techniques until it surpasses human capability.

This is example is a test that is being widely used to break/evaluate large language models on numeracy. There are many previous tests that we used to laugh at how badly these models performed that they now ace.
 
We laugh now, but...
True. Interestingly, China's DeepSeek just kicked the US off the AI podium for a tenth of the spend.


Just for fun I just asked ChatGPT the following:

How is DeepSeek better than chatgpt?
ChatGPT said:
DeepSeek has introduced several advancements that distinguish it from ChatGPT:
1. Human-Like Reasoning Process
Unlike ChatGPT, which provides final answers directly, DeepSeek showcases its internal reasoning by presenting a step-by-step thought process. This approach offers users insight into how conclusions are reached, enhancing transparency and understanding. Android Authority
2. Cost-Effective Development
DeepSeek's development emphasizes efficiency. The DeepSeek-V3 model was trained in approximately 55 days at a cost of around $5.58 million, utilizing fewer resources compared to its peers. This efficient approach challenges the traditional high-cost models in the AI industry. Wikipedia
3. Open-Source Accessibility
DeepSeek offers its models as open-source, allowing developers worldwide to access, modify, and implement the technology. This openness fosters innovation and collaboration within the AI community. Wikipedia
4. Performance in Reasoning Tasks
DeepSeek's R1 model has demonstrated superior performance in tasks requiring logical inference and mathematical reasoning, often surpassing ChatGPT in benchmarks like the American Invitational Mathematics Examination (AIME). Wikipedia
5. Rapid User Adoption
Following its release, DeepSeek's AI Assistant quickly became the top-rated free application on the U.S. Apple App Store, indicating significant user interest and adoption. Reuters

In summary, DeepSeek distinguishes itself through its transparent reasoning process, cost-effective development, open-source model, strong performance in reasoning tasks, and rapid user adoption, setting it apart from ChatGPT.
 
Last edited:
Does anyone else feel as though A.I. is ruining the internet?

A lot of content on YouTube is increasingly just videos using random stock footage with an A.I. generated voice overs reading off a script. A lot of the commenters for these videos are probably A.I. as well.

I find myself more often wondering if I'm interacting with an actual human or just a bot.

Is this giving rise to the "Dead internet theory"?

 
I had read how sometimes, AI can surpass human judgement in medical diagnostics, and I thought about the medical issue I started experiencing about 12 years ago and that led to several ambulance rides, a lot of discomfort, countless tests and scans and the stereotypical attitude that it was "in my head". It was only through trial and error and doing "my own research" :rolleyes: that I was able to find a possible cause that fit my symptoms, and act accordingly to prevent them.

So last week I input those symptoms into ChatGPT and it took 2 seconds for it to find the cause that it had taken several years for me to discover without any help from the medical profession.

On a less serious note, ChatGPT also provides pretty good wine recommendations, and uses excellent French (but it stinks at translation - I might actually reach retirement before being put to pasture prematurely).
 
A lot of content on YouTube is increasingly just videos using random stock footage with an A.I. generated voice overs reading off a script.
I’ve said it before, but I wish YouTube would include a filter to give the option to block text to voice and AI-voice videos.
 
Last edited:
Does anyone else feel as though A.I. is ruining the internet?

A lot of content on YouTube is increasingly just videos using random stock footage with an A.I. generated voice overs reading off a script. A lot of the commenters for these videos are probably A.I. as well.

I find myself more often wondering if I'm interacting with an actual human or just a bot.

Is this giving rise to the "Dead internet theory"?


I also sometimes go through the comments just to understand if others have noticed something strange and if there are even real people there. But not everything in AI is bad because there are tools that really save time and make life easier. For example, when you need to quickly prepare a short resume or some description, I can easily generate resume summary because it does not replace real experience but only helps to structure thoughts. I think the main thing is to learn to distinguish real content from completely generated and use AI as a tool and not as a replacement for everything. And how often do you yourself encounter the fact that you cannot determine whether it is a bot or a person?
I already hate AI because now I don't understand where the real video is and where the AI is. Every time I go to the comments to find out what people think. In the future, they won't make real videos at all (it's scary). It's terrible.
 
Last edited:
I already hate AI because now I don't understand where the real video is and where the AI is. Every time I go to the comments to find out what people think. In the future, they won't make real videos at all (it's scary). It's terrible.
I'm starting to feel the same. Strangely, the rapid appearance of AI is making me miss the pre-internet era...
 
I already hate AI because now I don't understand where the real video is and where the AI is.
In your search entries in Chrome before you finish include before:2024 at the end of your query. This will show results from 2023 or earlier, before Ai turned everything to garbage. Click Videos in the results to see YouTube pre-Ai.
Or the early-Internet era, before the rise of social media conglomerates.
I feel somehow fortunate to have been born in the early 1970s. I got to experience IMO the best of personnel computing, gaming and networking. I remember my first computer, a Timex Sinclair, followed by a Commodore 128 and a clone 386 pc. You'd open those things with such excitement. Gaming was amazing, and you owned the game which came in a box, with a printed manual, where there were no micro purchases, online overseers or paywalls for added features. I remember playing Civilizations for hours. As for the internet, the early days BBS chats, followed by Freenet, Netscape, etc. were great fun. But it was not addictive or attention span destroying, in the sense that you would play on your pc, but then I'd still sit for a couple hours to read a book, participate in organized sports and go out and actually see my friends. I would never have guessed that in two decades or so that big corporate would destroy it all, turning us into anxiety-ridden, attention-deficit, semi-illiterate zombies who can't turn off their screens for more than a hour.
 
Last edited:
For those seeking high-quality AI-free educational documentaries made by many of the most popular educational YouTubers, there's Nebula:


However, it requires a paid subscription as it is 100% ad-free.

It's like Discovery, TLC, or History Network before they decayed in the 2000s.

I'm strongly considering a Nebula subscription.
 
  • Like
Reactions: PL1
For those seeking high-quality AI-free educational documentaries made by many of the most popular educational YouTubers, there's Nebula:


However, it requires a paid subscription as it is 100% ad-free.

It's like Discovery, TLC, or History Network before they decayed in the 2000s.

I'm strongly considering a Nebula subscription.
I've had Nebula for a few years. I appreciate the lack of ads
 
It freaks me out when I see the comments of what seems like obviously AI generated video full of people commenting suggesting it is real. It scares me that we are entering a post-truth world and it scared me that I will get that undiscerning in time.
 

Back
Top