But is that not exactly how ChatGPT works? It does not "understand" what it is saying; rather, it is an incredibly powerful engine that reads and analyses collections of words that it has found on the internet and repeats them. The way in which it does this is only a little short of miraculous in that it can extract some kind of query from what the user types in and can then find a form of words that is often very close to answering it. But at the end of the day it is an example of the old IT principle of "garbage in, garbage out" and if it "learns" from browsing the internet, it is always llikely to pick up a bit of dross from time to time. If it finds 100 entries saying that the earth is flat and only 1 saying that is it spherical, it is going to repeat accepted wisdom and gossip. After all, it must be true if you read it on Facebook…

Artificial Intelligence might well catch that disease. It's pandemic because most humans prefer opinion and hearsay to fact. Not only is collecting and understanding evidence hard work, but people reject difficult truths that upset them. Be interesting to see if AI becomes as dishonest as humans!

I'm surprised ChatGPT didn't suggest EDEN as the answer to Amundsen's forwarding address. Amundsen disappeared in 1928 on a rescue mission, suggesting God called Amundsen home because He loved him too much. In comparison to a clear case of divine intervention is it likely a Norwegian knew 'mush' was the 'go forward' command given in Canada to Huskies? I don't believe Amundsen ever said 'mush', or that his hounds knew what it meant…

Dave

There are many situations in which a scream is all that is needed to confer meaning. You could call that a proto-word. And of course external context (drowning or fire) is always helpful in refining meaning ("help" or "danger!" ). But in many if not most cases of written matter, the context is provided primarily by other words. And that context isn't just the words that are immediately being used, the point is that it includes the whole corpus of language.

The crazy thing that ChatGPT is proving is just how much actual information and knowledge is embedded in the connections between words. This isn't the old-school "if then else" kind of hand-wired knowledge, nor is it brute-force computation as in Deep Blue. With only weights (strengths of connections) between basically every word and every other word, it can do things like solve the above crossword puzzle. That is an amazing revelation!

Edited By S K on 23/09/2023 18:04:32

Well, the computer can't see contexts such as an actual fire or bullying or other non-verbal context, it just works on what it's given, and hence it has certain limitations. But if you added verbal context such as saying "there's a fire!", "there's a bully kicking someone," etc., it would likely do reasonably well.

Researchers are also tying various AI systems together, such as connecting text generation with picture generation and math facilities. Research in vision is a pretty tough problem, as Tesla is finding, but that's getting there too.

As amazing as they can be already (and also still lame at times), these new generative systems are still in their infancy. Companies, Universities and sovereign states are racing to build ever larger models, and because their "intelligence" scales with the size of the models, they will continue to improve.

It's both hopeful and scary.

The Fry example shows how some, a very small sample of the population, will be affected by AI just as say thatchers were put out of work by the availability of clay tiles. But after a period even they have had a resurgence of employment as aspects of their work were found desirable.
Very little of what I have done this week would be done by a machine or benefit from AI. Pity none of it is a paying job either.

The combination of Michael's comments about Stephen Fry, and this little video I came across the other day are potentially quite frightening.
On the fly language translation, where you are shown speaking a different language, complete with lip sync on a manipulated video output.

Edited By peak4 on 24/09/2023 01:28:01

Take a look at THIS thread to see how reliable AI can be.

Did I miss the question?

… it is now ‘later’

.

09/08/2023 08:47:11

9/08/2023 08:57:08

09/08/2023 11:36:33

09/08/2023 15:33:09

.

It is perfectly reasonable that Rob might confuse AI with AI

but I was trying to understand how [any version of ] AI prompted thoughts of Aluminium

.. I offered my hypothesis

MichaelG.

.

Now wish I had never mentioned it.

Well that's indeed creepy! It's also vastly more 'intelligent' than the nonsense I have got, repeatedly, from the (assumed) 'phone help (misnomer) line at a major UK high-street bank. Those jokers' jobs are surely under threat…

It's scary because, like politicians, the answers are glib and plausible, but almost impossible to check for correctness – unless you already know the answer. If you don't trust politicians, you shouldn't trust this sort of software! It will flood the internet with AI-generated content, but what will it do for the signal-to-noise ratio?

Although it's said to be based on the probability of words following other words, it must have been elaborated to extend the analysis of the text beyond single words, to phrases and beyond, if only to 'understand' the context. It is doubtless be a small computational step to parse text to extract ever more complex concepts, and then link them together (probabilistically?). The example given suggests it's well on the way to that. And that's worrying.

Philosophical question: if something works indistinguishably as if it's conscious, intelligent, whatever, isn't that effectively the same? How do you know I'm not an unconscious zombie, just acting my simulation of conscious thought pretty effectively?

.

Clearly you are more than a match for it, Robin … but my ‘take-away’ from this is that the thing is already capable of teaching someone how to think !

MichaelG.

I thought I'd ask ChatGPT for advice (it didn't mention the big clue which is AI loves to make numbered or bulleted lists in response to a question!):

1. Lack of Personalization: AI-generated content often lacks a personal touch and may not contain specific, individualized details or information.

2. Unusual Language or Style: AI-generated content might exhibit a strange or inconsistent writing style, grammar errors, or awkward phrasing that a human writer would likely avoid.

3. Repetitive Patterns: AI may generate content with repetitive patterns or phrases. Look for redundancy in the text.

4. Rapid Production: AI can produce content at an incredibly fast rate. If you notice an account or source consistently publishing an unusually high volume of content, it could be a sign of automation.

5. Inhuman Speed: Check the response time for chatbots or automated social media accounts. They often respond almost instantly, regardless of the time of day.

6. Lack of In-Depth Knowledge: AI may provide information on a wide range of topics but might lack depth and context in its responses.

7. Incoherent or Nonsensical Content: AI-generated content can sometimes produce sentences or paragraphs that do not make sense or are disjointed.

8. Examine User Accounts: Check the profiles of users or accounts posting content. If a profile seems suspicious, with limited information, stock images, or a lack of personal interactions, it might be automated.

9. Reverse Image Search: If you suspect an image is AI-generated, you can perform a reverse image search to see if it appears on multiple websites or is associated with AI-generated content.

10. Be Cautious of Automation Tools: Tools that automate content generation, such as chatbots and content generators, can be a source of AI-generated content. Look for disclaimers or indications of automation.

11. Monitor for Trends: Keep an eye on emerging AI-generated content trends and technologies, as AI capabilities are continually evolving.

12. Trust Reliable Sources: Rely on reputable and well-established sources for information, especially when verifying facts or news.

It's important to note that AI-generated content is not inherently deceptive or harmful. In many cases, it serves legitimate purposes, such as chatbots providing customer support or AI-generated summaries of news articles. However, it's essential to remain aware of the potential presence of AI-generated content and use critical thinking when evaluating information online.