Attention: Please take a moment to consider our terms and conditions before posting.
ChatGPT
Comments
-
By making a stand and not using it won’t really help though will it, it’s happening either way, so might as well take advantage.Dazzler21 said:Adapting here seems to be replacing yourselves?!
I just don't think for what I do that ChatGPT etc is there yet.
Its not ‘there’ for my job either (it definitely can’t write a half decent lesson plan) but it’s a brilliant tool to help get a lot of projects started.1 -
Yes, hallucinations exist. Part of the art of what I teach others is how to construct prompts to maximise correct outcomes but also to question itself ( as you did).PragueAddick said:
ChatGPT literally makes shit up. For professional purposes I asked it for a list of TV competition shows highlighting excellence in retail. Some of the answers looked suspicious. i challenged it one by one, and in each case it backed down and apologised for a “mistake”. I have the transcript, it’s hilarious but too long for a post here.Covered End said:
Well yes, but how do you know encyclopedias, google or anything you read is correct?MrOneLung said:
how do you know the answer was correct ?Covered End said:
Anything you want an answer to.Dazzler21 said:For what?
I asked for the full explanation to the Israel/Arab conflict for example.Have you not noticed the caveat (warning) it now posts tot he effect that it may make mistakes (or make shit up) ?As per my examples I posted earlier, none of the best use cases relate to something that can be googled and solved in 30 seconds, especially recent content. I personally don’t think this is what the tool is for. It is for complex tasks for which you have an idea, but not the skill, to execute.2 -
You see it as a shortcut, I see it as a facilitator.Dazzler21 said:What could take many hours of research can now be done in a fraction of the time, giving me the freedom to spend more time on the real work.It only gives outputs to my input … if I didn’t provide the parameters, it would not be of value.To an extent, it does feel like ‘cheating’ but it is only producing data in response to my detailed input. There can be issues with the output but that just requires care and attention.I am now able to do my work way quicker than I could before giving me more time to develop and implement the results.1 -
Fair point, but humans that make too much stuff up or contradict themselves would hopefully get banned from updating Wikipedia.Covered End said:
Well yes, but how do you know encyclopedias, google or anything you read is correct?MrOneLung said:
how do you know the answer was correct ?Covered End said:
Anything you want an answer to.Dazzler21 said:For what?
I asked for the full explanation to the Israel/Arab conflict for example.
ChatGPT's answer above to my Ronaldo/Rooney question has Ronaldo being sent off AND scoring in the penalty shootout.
I can see uses for ChatGPT in summarizing, drafting and brainstorming.
What irks me is calling it Generative Artificial Intelligence. I think this is partly marketing, since the more specific (and accurate in my opinion) 'Generative Language Model' has nowhere near the mistery.1 -
Is it just me that suspects all of the posts on this thread have been written by ChatGPT? Even this one?3
-
7 -
It would say that though wouldn’t it…?8
-
1
-
InterestingCallumcafc said:0 -
1
- Sponsored links:
-
Brilliant0
-
This is going to revolutionise the filmography, cinema and 🦐hub0
-
Video games learning to code their own graphics too is an insane thought.0
-
I'm in the amazing camp on this one: really like it. Would love to have a go.
But yes, I can see the potential for misuse.0 -
PWR but I suspect the Air Canada AI Chatbot issue where it basically made up its own more generous policy than the one AC had and the carrier has to honour it will put a brake on adoption of those systems for business purposes.2
-
Much like Dalle-3, this may be useful in some circumstances, but there will be limitations. You won’t be able to edit or fix specific elements you don’t like (even re promoting won’t give you exactly what you want), you won’t be able to alter angles or colours. Anything that has words on it will be a mess.The promo video looks good and could be useful for small clips or corporate videos for websites but SORA is not going to replace human creativity and even short films (much like Dalle-3 has not replace creative depts).The tech will get better so who knows what will happen in 5-10 years.One point of note on potential fake news generation (which this could be used for). OpenAI have committed to adding a watermark (C2PA) to content generated via SORA. This has already been applied to DALLE-3 images since feb. It should make it easier to identify ‘real’ images for both new outlets and individuals alike. A standard such as this needs to be adopted across the whole AI industry to be effective.3
-
Have I just been Lol’d by an AI chatbot that’s realised the games up ?letthegoodtimesroll said:PWR but I suspect the Air Canada AI Chatbot issue where it basically made up its own more generous policy than the one AC had and the carrier has to honour it will put a brake on adoption of those systems for business purposes.2 -
Very interesting podcast by the Guardian called Blackbox - it has nothing to do with the Charlton recruitment process, but is about the development of AI.
Episode 1 Looks at the initial development.
Episode 2 looks at how deep fake is adversely affecting people already.
https://www.theguardian.com/technology/series/blackbox0 - Sponsored links:
-
Interesting first episode on the history of neural networks.Raith_C_Chattonell said:Very interesting podcast by the Guardian called Blackbox - it has nothing to do with the Charlton recruitment process, but is about the development of AI.
Episode 1 Looks at the initial development.
Episode 2 looks at how deep fake is adversely affecting people already.
https://www.theguardian.com/technology/series/blackbox
Second episode describes great detective work to track the creators of ClothOff.
But I do wish podcast transcripts were made available as a matter of course for people that haven't got time to listen to them.
I still think there's a lot of marketing in the term Artificial Intelligence. Not long ago it was all about algorithms, and just before that 'big data'.
There's so much non-intelligent technology called AI that they've had to come up with another term, Artificial General Intelligence, to excuse mistakes in regular AI.
1 -
Robotic Table Tennis
https://x.com/googledeepmind/status/1821562365931855970?s=46&t=ynww82GMl7VKBjthBflU0g
0 -
I Google searched the question below and Google gave their AI overview (as stated) reply. How many billions has it cost to come up with this?
1 -
Weird. I'm watching the cycling in the velodrome and they're playing Chelsea Dagger.Raith_C_Chattonell said:I Google searched the question below and Google gave their AI overview (as stated) reply. How many billions has it cost to come up with this?0 -
Anyone know the name of the A.I song generator that was on the A.I thread?0
-
And a year later I came round to understanding that you are basically right; although I find it is great for accelerating a task for which you may have the skills but not the time, concentration level or focus to execute efficiently on your own. (I use Claude rather than ChatGPT, but I guess they are similar. I use Perplexity for search)BalladMan said:
Yes, hallucinations exist. Part of the art of what I teach others is how to construct prompts to maximise correct outcomes but also to question itself ( as you did).PragueAddick said:
ChatGPT literally makes shit up. For professional purposes I asked it for a list of TV competition shows highlighting excellence in retail. Some of the answers looked suspicious. i challenged it one by one, and in each case it backed down and apologised for a “mistake”. I have the transcript, it’s hilarious but too long for a post here.Covered End said:
Well yes, but how do you know encyclopedias, google or anything you read is correct?MrOneLung said:
how do you know the answer was correct ?Covered End said:
Anything you want an answer to.Dazzler21 said:For what?
I asked for the full explanation to the Israel/Arab conflict for example.Have you not noticed the caveat (warning) it now posts tot he effect that it may make mistakes (or make shit up) ?As per my examples I posted earlier, none of the best use cases relate to something that can be googled and solved in 30 seconds, especially recent content. I personally don’t think this is what the tool is for. It is for complex tasks for which you have an idea, but not the skill, to execute.
Last week, a fellow local activist citizen received a reply to his FOi request, refusing his request. The authority in question, Prague Airport, sent him 16 pages of dense legalese as their reasoning, a deliberate tactic, not least because Czech legalese confounds even the most intelligent Czech native speaker. First I got Claude to translate it into English. A matter of seconds. I skimmed through enough to see that it was bollocks, then asked Claude to prepare text for an appeal. 30 seconds later, there it was. Very solid, very concise (I know a bit about FOI). I sat there dumbfounded for a few moments, then sent it on to my colleague. I could hear his jaw crashing to the ground as he opened it up. The entire tactic of getting lawyers to tie ordinary citizens in knots with dense legalese lies in tatters, and I'm celebrating that.2 -
“Who will win this season’s League One playoffs?”
“Charlton Athletic are strong contenders to win the League One playoffs this season largely because of their impressive form under manager Nathan Jones. Under his leadership, Charlton have won 10 of their last 14 matches, demonstrating excellent momentum at the right time. Their defensive solidity, shown by 20 clean sheets across the season, and a balanced attack led by Matt Godden, make them well-equipped for high-pressure playoff matches. Additionally, Charlton’s prior playoff experience and their organizational stability give them an advantage over less battle-tested sides.In contrast, Stockport County and Wycombe Wanderers each face notable challenges heading into the playoffs. Stockport, while impressive in their first season back in League One after 15 years, have shown signs of vulnerability recently and lack experience at this level. Wycombe started the season strong but have been inconsistent following a mid-season managerial change, and their heavy reliance on top scorer Richard Kone could be problematic. These factors suggest that although both teams are dangerous, Charlton may be better positioned to navigate the playoffs successfully.”
0 -
Perfect example of using AI to level up by thinking creatively.PragueAddick said:
And a year later I came round to understanding that you are basically right; although I find it is great for accelerating a task for which you may have the skills but not the time, concentration level or focus to execute efficiently on your own. (I use Claude rather than ChatGPT, but I guess they are similar. I use Perplexity for search)BalladMan said:
Yes, hallucinations exist. Part of the art of what I teach others is how to construct prompts to maximise correct outcomes but also to question itself ( as you did).PragueAddick said:
ChatGPT literally makes shit up. For professional purposes I asked it for a list of TV competition shows highlighting excellence in retail. Some of the answers looked suspicious. i challenged it one by one, and in each case it backed down and apologised for a “mistake”. I have the transcript, it’s hilarious but too long for a post here.Covered End said:
Well yes, but how do you know encyclopedias, google or anything you read is correct?MrOneLung said:
how do you know the answer was correct ?Covered End said:
Anything you want an answer to.Dazzler21 said:For what?
I asked for the full explanation to the Israel/Arab conflict for example.Have you not noticed the caveat (warning) it now posts tot he effect that it may make mistakes (or make shit up) ?As per my examples I posted earlier, none of the best use cases relate to something that can be googled and solved in 30 seconds, especially recent content. I personally don’t think this is what the tool is for. It is for complex tasks for which you have an idea, but not the skill, to execute.
Last week, a fellow local activist citizen received a reply to his FOi request, refusing his request. The authority in question, Prague Airport, sent him 16 pages of dense legalese as their reasoning, a deliberate tactic, not least because Czech legalese confounds even the most intelligent Czech native speaker. First I got Claude to translate it into English. A matter of seconds. I skimmed through enough to see that it was bollocks, then asked Claude to prepare text for an appeal. 30 seconds later, there it was. Very solid, very concise (I know a bit about FOI). I sat there dumbfounded for a few moments, then sent it on to my colleague. I could hear his jaw crashing to the ground as he opened it up. The entire tactic of getting lawyers to tie ordinary citizens in knots with dense legalese lies in tatters, and I'm celebrating that.0
https://www.youtube.com/watch?v=HK6y8DAPN_0
