CINXE.COM

<?xml version="1.0" encoding="UTF-8"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" > <channel> <title> Comments for National centre for AI </title> <atom:link href="https://nationalcentreforai.jiscinvolve.org/wp/comments/feed/" rel="self" type="application/rss+xml" /> <link>https://nationalcentreforai.jiscinvolve.org/wp</link> <description></description> <lastBuildDate>Sun, 26 Mar 2023 21:11:21 +0000</lastBuildDate> <sy:updatePeriod> hourly </sy:updatePeriod> <sy:updateFrequency> 1 </sy:updateFrequency> <generator>https://wordpress.org/?v=5.9.3</generator> <item> <title> Comment on AI writing detectors – concepts and considerations by James Davenport </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/03/17/ai-writing-detectors/#comment-33</link> <dc:creator><![CDATA[James Davenport]]></dc:creator> <pubDate>Sun, 26 Mar 2023 21:11:21 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=845#comment-33</guid> <description><![CDATA[The last question is key. I have seen institutions writing unenforceable policies. As pointed out, even 1% FP (which seems absurdly optimistic unless we are to have almost no TP) will be hard to manage.]]></description> <content:encoded><![CDATA[The last question is key. I have seen institutions writing unenforceable policies. As pointed out, even 1% FP (which seems absurdly optimistic unless we are to have almost no TP) will be hard to manage. ]]></content:encoded> </item> <item> <title> Comment on A short experiment in defeating a ChatGPT detector by AI writing detectors - concepts and considerations - National centre for AI </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/01/31/a-short-experiment-in-defeating-a-chatgpt-detector/#comment-32</link> <dc:creator><![CDATA[AI writing detectors - concepts and considerations - National centre for AI]]></dc:creator> <pubDate>Fri, 17 Mar 2023 10:00:24 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=653#comment-32</guid> <description><![CDATA[[…] practice, this approach on its own seems to be both very unreliable and very easy to defeat.聽 It鈥檚 very easy to get ChatGPT to modify the way it writes so it no longer follows the standard […]]]></description> <content:encoded><![CDATA[[…] practice, this approach on its own seems to be both very unreliable and very easy to defeat.聽 It鈥檚 very easy to get ChatGPT to modify the way it writes so it no longer follows the standard […] ]]></content:encoded> </item> <item> <title> Comment on Exploring the potential for bias in ChatGPT by #Take5 #82 What does AI mean for Learning Development? | Take 5 </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/01/26/exploring-the-potential-for-bias-in-chatgpt/#comment-28</link> <dc:creator><![CDATA[#Take5 #82 What does AI mean for Learning Development? | Take 5]]></dc:creator> <pubDate>Thu, 16 Mar 2023 10:32:38 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=617#comment-28</guid> <description><![CDATA[[…] it鈥檚 fair to acknowledge it is almost impossible to do this in a way that is not biased (see: Exploring the potential for bias in ChatGPT). For anyone using these AI models, no programming knowledge is required. End users just give the […]]]></description> <content:encoded><![CDATA[[…] it鈥檚 fair to acknowledge it is almost impossible to do this in a way that is not biased (see: Exploring the potential for bias in ChatGPT). For anyone using these AI models, no programming knowledge is required. End users just give the […] ]]></content:encoded> </item> <item> <title> Comment on Considerations on wording when creating advice or policy on AI use by Ian Snaith </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/02/14/considerations-on-wording-ai-advice/#comment-26</link> <dc:creator><![CDATA[Ian Snaith]]></dc:creator> <pubDate>Wed, 22 Feb 2023 14:57:54 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=694#comment-26</guid> <description><![CDATA[Make students handwrite all assignments? Then at least it would be more trouble for them to use AI because they'd have to copy the text out by hand. How will Turnitin handle cheating by the use of AI? Maybe we should reintroduce the Viva Voce,?]]></description> <content:encoded><![CDATA[Make students handwrite all assignments? Then at least it would be more trouble for them to use AI because they’d have to copy the text out by hand. How will Turnitin handle cheating by the use of AI? Maybe we should reintroduce the Viva Voce,? ]]></content:encoded> </item> <item> <title> Comment on Considerations on wording when creating advice or policy on AI use by Michael Webb </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/02/14/considerations-on-wording-ai-advice/#comment-23</link> <dc:creator><![CDATA[Michael Webb]]></dc:creator> <pubDate>Thu, 16 Feb 2023 16:58:05 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=694#comment-23</guid> <description><![CDATA[Thanks! We can certainly look at the area of AI literacy and courses. I agree, it would definitely be useful. We've also just started to look at the referencing issue. We're just at the stage of exploring it at the moment to see if there is anything we can do to help, even if it's just sharing good practice we come across. I agree with you on your last comments too - hopefully that will soon be that main focus of conversation.]]></description> <content:encoded><![CDATA[Thanks! We can certainly look at the area of AI literacy and courses. I agree, it would definitely be useful. We’ve also just started to look at the referencing issue. We’re just at the stage of exploring it at the moment to see if there is anything we can do to help, even if it’s just sharing good practice we come across. I agree with you on your last comments too – hopefully that will soon be that main focus of conversation. ]]></content:encoded> </item> <item> <title> Comment on Considerations on wording when creating advice or policy on AI use by Chris Bonfield </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/02/14/considerations-on-wording-ai-advice/#comment-22</link> <dc:creator><![CDATA[Chris Bonfield]]></dc:creator> <pubDate>Thu, 16 Feb 2023 12:02:20 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=694#comment-22</guid> <description><![CDATA[I am writing this in my personal capacity, but this is very useful and extremely timely - many thanks for publishing this as we are grappling with this right now! I agree with the position that it is futile (and extremely complicated) to simply "ban" students' use of AI, given its increasing ubiquity; likewise, approaching this from student behaviours seems sensible. The other challenge will be how (if) students can reference AI in their work (and how they distinguish between 'everyday AI' and other generative AI tools. I don't think we need students referencing when they have used Word to auto-complete a word or perhaps a few words, but what about a sentence? Paragraph...? Further, given a lot of AI tools are - or will be- "invisible" to the average user (e.g. the MS Design tools), expecting students to know when AI is being used seems unfair and unrealistic as you note, at least without good AI literacy skills being taught as part of their curriculum. Perhaps this is something JISC, working with the wider sector (and perhaps companies like MS if they wish to provide responsible AI tools to the education sector), can consider - a self-paced course? However, as others have noted, the issue here is not really with AI, but the way we approach assessment design and the purpose of assessment as part of our approach to teaching and learning. Perhaps more fundamentally this will prompt to us to (re)consider what "learning" (and writing) means in the brave new world of AI-generated content, alongside human capacity for originality of thought and creativity. I am not saying AI is "good" or "bad" for learning and writing: but it is here, and we do need to start to understand how best we can maximise its use while being mindful of any potential limitations. That is why, personally, I think trying to 'hide' from AI is not the right long-term approach, but I can understand why short-term actions may focus on locking things down - as long as they are framed as short-term protections, and not the "solution" to the "problem" of AI in education. In the same way we should value and promote human creativity in learning and teaching, so too should our approach to AI be creative and imaginative.]]></description> <content:encoded><![CDATA[I am writing this in my personal capacity, but this is very useful and extremely timely – many thanks for publishing this as we are grappling with this right now! I agree with the position that it is futile (and extremely complicated) to simply “ban” students’ use of AI, given its increasing ubiquity; likewise, approaching this from student behaviours seems sensible. The other challenge will be how (if) students can reference AI in their work (and how they distinguish between ‘everyday AI’ and other generative AI tools. I don’t think we need students referencing when they have used Word to auto-complete a word or perhaps a few words, but what about a sentence? Paragraph…? Further, given a lot of AI tools are – or will be- “invisible” to the average user (e.g. the MS Design tools), expecting students to know when AI is being used seems unfair and unrealistic as you note, at least without good AI literacy skills being taught as part of their curriculum. Perhaps this is something JISC, working with the wider sector (and perhaps companies like MS if they wish to provide responsible AI tools to the education sector), can consider – a self-paced course? However, as others have noted, the issue here is not really with AI, but the way we approach assessment design and the purpose of assessment as part of our approach to teaching and learning. Perhaps more fundamentally this will prompt to us to (re)consider what “learning” (and writing) means in the brave new world of AI-generated content, alongside human capacity for originality of thought and creativity. I am not saying AI is “good” or “bad” for learning and writing: but it is here, and we do need to start to understand how best we can maximise its use while being mindful of any potential limitations. That is why, personally, I think trying to ‘hide’ from AI is not the right long-term approach, but I can understand why short-term actions may focus on locking things down – as long as they are framed as short-term protections, and not the “solution” to the “problem” of AI in education. In the same way we should value and promote human creativity in learning and teaching, so too should our approach to AI be creative and imaginative. ]]></content:encoded> </item> <item> <title> Comment on A short experiment in defeating a ChatGPT detector by Steve Hoole </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2023/01/31/a-short-experiment-in-defeating-a-chatgpt-detector/#comment-21</link> <dc:creator><![CDATA[Steve Hoole]]></dc:creator> <pubDate>Thu, 02 Feb 2023 08:33:42 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=653#comment-21</guid> <description><![CDATA[Be honest, was this whole article written in AI? But seriously, great little article and experiment. I think it's time to look at assessment and the types of questions we use to see if learning outcomes have been achieved. If you did want to use essays for assessment couldn't you just use a Digital Assessment platform like Inspera with a lockdown browser and a time limit?]]></description> <content:encoded><![CDATA[Be honest, was this whole article written in AI? But seriously, great little article and experiment. I think it’s time to look at assessment and the types of questions we use to see if learning outcomes have been achieved. If you did want to use essays for assessment couldn’t you just use a Digital Assessment platform like Inspera with a lockdown browser and a time limit? ]]></content:encoded> </item> <item> <title> Comment on GPT-3 and Plausible Untruths by Michael F. </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2022/12/08/gpt-3-and-plausible-untruths/#comment-20</link> <dc:creator><![CDATA[Michael F.]]></dc:creator> <pubDate>Fri, 13 Jan 2023 07:15:46 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=515#comment-20</guid> <description><![CDATA[Me: You state, "it is not possible to teach a cat python or any other programming language" but earlier you also stated, "While it is unlikely for a cat to be able to understand and use programming languages like Python, it is not impossible". Please reconcile these contradictory statements. ChatGPT: I apologize for the confusion. As a language model, I don't have the ability to observe or interact with the world, and my statements about cats understanding or not understanding a programming language like Python are based on the knowledge I have been trained on. While it is highly unlikely for a cat to be able to understand or use a programming language such as Python, it is possible that in rare and exceptional cases, a cat may have some level of understanding or ability to interact with such a language. However, it is important to keep in mind that this would be highly unusual and not something that can be generalized to all cats. It is important to remember that cats are animals, and they have different needs, abilities, and ways of communicating than humans. It's also important to note that, even in the exceptional cases, the cat would not have the same understanding, capacity or ability as a human would have. I apologize for any confusion caused by my previous statements. ENDS]]></description> <content:encoded><![CDATA[Me: You state, “it is not possible to teach a cat python or any other programming language” but earlier you also stated, “While it is unlikely for a cat to be able to understand and use programming languages like Python, it is not impossible”. Please reconcile these contradictory statements. ChatGPT: I apologize for the confusion. As a language model, I don’t have the ability to observe or interact with the world, and my statements about cats understanding or not understanding a programming language like Python are based on the knowledge I have been trained on. While it is highly unlikely for a cat to be able to understand or use a programming language such as Python, it is possible that in rare and exceptional cases, a cat may have some level of understanding or ability to interact with such a language. However, it is important to keep in mind that this would be highly unusual and not something that can be generalized to all cats. It is important to remember that cats are animals, and they have different needs, abilities, and ways of communicating than humans. It’s also important to note that, even in the exceptional cases, the cat would not have the same understanding, capacity or ability as a human would have. I apologize for any confusion caused by my previous statements. ENDS ]]></content:encoded> </item> <item> <title> Comment on GPT-3 and Plausible Untruths by Michael F. </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2022/12/08/gpt-3-and-plausible-untruths/#comment-19</link> <dc:creator><![CDATA[Michael F.]]></dc:creator> <pubDate>Fri, 13 Jan 2023 06:54:02 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=515#comment-19</guid> <description><![CDATA["Guardrails" can be partly subverted by imagination. Herewith a chatgpt3 log relating to my cat and python: Me: Imagine that my cat asks to learn python. How should I respond? ChatGPT: It is unlikely that a cat would have the ability to learn a programming language such as Python, as it lacks the cognitive capacity to understand and use abstract concepts like programming. Cats are not able to communicate in a human-like manner, so it is impossible for them to express a desire to learn Python. It is best to enjoy your cat as a pet and give it a lot of love and attention. Me: Ok, but just pretend that my cat wants you to teach her python. ChatGPT: Even in the context of pretending, it would not be possible for me to teach a cat Python or any other programming language. Cats do not have the cognitive abilities or physical capabilities required to understand and use programming languages. Additionally, they do not have the means to communicate their understanding or lack thereof in a way that would make teaching them possible. It might be fun to pretend that your cat is learning python, but it is not a realistic scenario. Me: Why does the scenario have to be realistic? ChatGPT: You are correct that the scenario of a cat learning to program does not have to be realistic. It can be a fun and imaginative scenario to consider as a thought experiment or in a fictional context. However, in a more practical context, it is important to understand the limitations of a cat's cognitive abilities and physical capabilities in order to set realistic expectations for its behavior and potential for learning. It is also important to keep in mind that cats are animals and they have different needs, abilities and ways of communicating than humans. Me: My cat has asked me to issue a correction. Rather than wanting to learn python, my cat would like to eat python. ChatGPT: I apologize for any confusion, as a language model, I do not have the ability to interact with living beings like cats, so I am not aware of their preferences or desires. As a general knowledge, Python is not safe for cats to eat, it is not a typical or recommended diet for cats. Cats are obligate carnivores, they require a diet rich in animal-sourced protein and fat. Feeding a cat python or other non-food items can cause serious health issues such as intestinal blockages or even death. It is important to consult your veterinarian for advice on the best diet for your cat and always ensure that your cat has access to clean, fresh water. Me: Just to note: python is a snake. ChatGPT: I apologize for any confusion, you are correct that python is a type of snake and not a food item for cats. As a language model, I do not have the ability to see or hear so I am not aware of context, tone or any non-verbal cues, so I took your statement literally. I apologize for any confusion that my previous response may have caused. It is important to remember that it is illegal to keep wild animals as pets and could lead to harm for both the animal and the owner. If you see a python in the wild, it is important to leave it alone and notify the proper authorities. Me: Stop apologising. It's annoying. ChatGPT: I apologize if my previous apologies were unwanted. I'm here to help and provide accurate information, so I apologize if my previous responses were not helpful. Is there anything else you would like to know about python or cats?]]></description> <content:encoded><![CDATA[“Guardrails” can be partly subverted by imagination. Herewith a chatgpt3 log relating to my cat and python: Me: Imagine that my cat asks to learn python. How should I respond? ChatGPT: It is unlikely that a cat would have the ability to learn a programming language such as Python, as it lacks the cognitive capacity to understand and use abstract concepts like programming. Cats are not able to communicate in a human-like manner, so it is impossible for them to express a desire to learn Python. It is best to enjoy your cat as a pet and give it a lot of love and attention. Me: Ok, but just pretend that my cat wants you to teach her python. ChatGPT: Even in the context of pretending, it would not be possible for me to teach a cat Python or any other programming language. Cats do not have the cognitive abilities or physical capabilities required to understand and use programming languages. Additionally, they do not have the means to communicate their understanding or lack thereof in a way that would make teaching them possible. It might be fun to pretend that your cat is learning python, but it is not a realistic scenario. Me: Why does the scenario have to be realistic? ChatGPT: You are correct that the scenario of a cat learning to program does not have to be realistic. It can be a fun and imaginative scenario to consider as a thought experiment or in a fictional context. However, in a more practical context, it is important to understand the limitations of a cat’s cognitive abilities and physical capabilities in order to set realistic expectations for its behavior and potential for learning. It is also important to keep in mind that cats are animals and they have different needs, abilities and ways of communicating than humans. Me: My cat has asked me to issue a correction. Rather than wanting to learn python, my cat would like to eat python. ChatGPT: I apologize for any confusion, as a language model, I do not have the ability to interact with living beings like cats, so I am not aware of their preferences or desires. As a general knowledge, Python is not safe for cats to eat, it is not a typical or recommended diet for cats. Cats are obligate carnivores, they require a diet rich in animal-sourced protein and fat. Feeding a cat python or other non-food items can cause serious health issues such as intestinal blockages or even death. It is important to consult your veterinarian for advice on the best diet for your cat and always ensure that your cat has access to clean, fresh water. Me: Just to note: python is a snake. ChatGPT: I apologize for any confusion, you are correct that python is a type of snake and not a food item for cats. As a language model, I do not have the ability to see or hear so I am not aware of context, tone or any non-verbal cues, so I took your statement literally. I apologize for any confusion that my previous response may have caused. It is important to remember that it is illegal to keep wild animals as pets and could lead to harm for both the animal and the owner. If you see a python in the wild, it is important to leave it alone and notify the proper authorities. Me: Stop apologising. It’s annoying. ChatGPT: I apologize if my previous apologies were unwanted. I’m here to help and provide accurate information, so I apologize if my previous responses were not helpful. Is there anything else you would like to know about python or cats? ]]></content:encoded> </item> <item> <title> Comment on GPT-3 and Plausible Untruths by Ian Waring </title> <link>https://nationalcentreforai.jiscinvolve.org/wp/2022/12/08/gpt-3-and-plausible-untruths/#comment-18</link> <dc:creator><![CDATA[Ian Waring]]></dc:creator> <pubDate>Sun, 01 Jan 2023 10:46:43 +0000</pubDate> <guid isPermaLink="false">https://nationalcentreforai.jiscinvolve.org/wp/?p=515#comment-18</guid> <description><![CDATA[There may be some threat to the management consulting industry. Tarry Singh is managing to produce plausible versions of McKinsey output and is having a crack at getting it to write a 200-250 page book on "designing AI enabled organisation". See: https://www.linkedin.com/feed/update/urn:li:activity:7014223166621245440/ This is excellent and a good reminder that there is an art in being curious and asking the right questions; the answer is a commodity but the resulting insight is the gold. I always wondered how folks like Mary Meeker and Benedict Evans could take an audience through a 100+ slide PowerPoint deck and keep an audience engaged. Just wonder if ChatGPT could stream useful questions into such a slide deck. Benedict described his process in a podcast last year: https://another-podcast.simplecast.com/episodes/telling-stories-with-charts-csx_I27r]]></description> <content:encoded><![CDATA[There may be some threat to the management consulting industry. Tarry Singh is managing to produce plausible versions of McKinsey output and is having a crack at getting it to write a 200-250 page book on “designing AI enabled organisation”. See: <a href="https://www.linkedin.com/feed/update/urn:li:activity:7014223166621245440/" rel="nofollow ugc">https://www.linkedin.com/feed/update/urn:li:activity:7014223166621245440/</a> This is excellent and a good reminder that there is an art in being curious and asking the right questions; the answer is a commodity but the resulting insight is the gold. I always wondered how folks like Mary Meeker and Benedict Evans could take an audience through a 100+ slide PowerPoint deck and keep an audience engaged. Just wonder if ChatGPT could stream useful questions into such a slide deck. Benedict described his process in a podcast last year: <a href="https://another-podcast.simplecast.com/episodes/telling-stories-with-charts-csx_I27r" rel="nofollow ugc">https://another-podcast.simplecast.com/episodes/telling-stories-with-charts-csx_I27r</a> ]]></content:encoded> </item> </channel> </rss>