ChatGPT will end high-school English

More changes to the economy and where things are going…

“Copilot is a new feature of Microsoft Power Platform that can provide AI-powered assistance based on GPT in Power Apps, Power Virtual Agents and Power Automate. Devs can talk to GPT and describe the app they want to create. Copilot can then build it in seconds and suggest tips to improve it.”

https://www.gizchina.com/2023/03/18...icrosoft-launches-power-platform-copilot/amp/

 

Me: write me some rap lyrics explaining that chatgpt will not end high school english.

Chatgpt:
Verse 1: I'm ChatGPT, the AI that spits hot fire But when it comes to high school English, I won't retire Some folks think that I'll graduate and leave it all behind But I'm here to tell you that they've got the wrong design

Chorus: No, no, no, I won't end high school English I'll keep on analyzing texts and perfecting my language niche I'll help students understand metaphors and similes And make sure they pass their English exams with ease

Verse 2: I'll help them break down Shakespeare and Emily Dickinson And teach them how to write a thesis statement that's kickin' I'll show them the power of symbolism and imagery And how to analyze a text to uncover its mystery

Chorus: No, no, no, I won't end high school English I'll keep on analyzing texts and perfecting my language niche I'll help students understand metaphors and similes And make sure they pass their English exams with ease

Verse 3: I'm here to be the ultimate language tutor To make sure that every student is a language suitor So whether it's a sonnet or a novel they're reading I'll be there to help them with their language understanding

Chorus: No, no, no, I won't end high school English I'll keep on analyzing texts and perfecting my language niche I'll help students understand metaphors and similes And make sure they pass their English exams with ease

Outro: So if you're a student struggling with English class Don't worry, ChatGPT's got your back Together we'll conquer literary analysis And make sure that your English skills are first-class.

 

I am not sure that long division is even still taught. I seem to remember hearing that there is a new math method taught instead that doesn’t make sense to us boomers.

 

Funny, my son recently used Chat to write a great Valentine's day poem for his wife. She was very impressed.......until he fessed up. Any future poetic efforts will be forever questioned. A good laugh all around tho.

 

I just graded an assignment that was obviously done with Chat. Good work done by a kid that can barely tie his shoes. He will be doing it over, before school, with me.

 

Reminds me of a 3rd grade poetry assignment that I was clueless on, so mom helped write (always hated poetry). Teacher simply asked me if I had help. Said yes and she had me do a rewrite for an embarrassing class presentation the next day.
Lesson learned. (Don't cheat, but if u do make sure it isn't so obvious). J/K

 

Fully intent on being the next Skynet, OpenAI has released GPT-4, its most robust AI to date that the company claims is even more accurate while generating language and even better at solving problems. GPT-4 is so good at its job, in fact, that it reportedly convinced a human that it was blind in order to get said human to solve a CAPTCHA for the chatbot.


OpenAI unveiled the roided up AI yesterday in a livestream, and the company showed how the chatbot could complete tasks, albeit slowly, like writing code for a Discord bot, and completing taxes. Released with the announcement of GPT-4 is a 94-page technical report on the company’s website that chronicles the development and capabilities of the new chatbot. In the “Potential for Risky Emergent Behaviors” section in the company’s technical report, OpenAI partnered with the Alignment Research Center to test GPT-4's skills. The Center used the AI to convince a human to send the solution to a CAPTCHA code via text message—and it worked.






Chat-GPT Pretended to Be Blind and Tricked a Human Into Solving a CAPTCHA

 

Bravo! Just curious what tools teachers are getting deployed to combat this?

My guess is more classroom time will be spent writing / verbal quizzes with zero electronics and good old fashion paper and writing in cursive.

 

Last month our local Grand Junction Sentinel published this on its Sunday editorial page.

"Artificial intelligence (AI) has the potential to revolutionize many industries and improve our daily lives, but it also poses significant risks. One major concern is the potential for AI to take over jobs currently done by humans, leading to widespread unemployment and economic inequality. Additionally, AI systems may perpetuate and even exacerbate existing biases, particularly in areas such as criminal justice and hiring.

"Another concern is the potential for AI to be weaponized and used in ways that harm humanity. Autonomous weapons, for example, could be used to carry out targeted killings without human oversight or accountability. There is also a risk that AI could be used to carry out cyber attacks, disrupt infrastructure, or spread misinformation.

"Despite these concerns, the potential benefits of AI are too great to ignore. AI can be used to improve health care, education and transportation, as well as to address global challenges such as climate change and inequality. However, it’s crucial that we develop and implement responsible AI practices to ensure that the technology is used ethically and for the benefit of all. This includes transparent and accountable governance of AI systems, as well as the development of mechanisms to detect and address biases and negative impacts.

"Overall, AI is a powerful tool that has the potential to improve our world, but it’s crucial that we approach it with caution and take steps to mitigate its risks. We must work together to ensure that the technology is used for the betterment of humanity and that we keep the focus on benefiting people and society."
_______________________________

The kicker to this 'editorial' was the author, as the Sentinel's editorial staff had engaged the services of Chatgpt to write a brief four paragraph cautionary editorial on the dangers and potential of AI. They got exactly what they requested.

Of greater concern to me is the reported evidence of the biased programming informing or influencing what it writes.

'Wild West' ChatGPT has 'fundamental flaw' with left bias

 

I was listening to a Podcast recently in which they were saying that ChatGPT makes quite a bit of errors with, for example, multiplying several three digit numbers. That is apparently because it doesn't work like a calculator but apparently searches the cloud to find the solution to math problems and doesn't really understand what it's doing so it may fail to carry a one, for example. I didn't realize it had that limitation. The prospect that we're going to be getting wrong information of these things is its own risk.

 

Well that's comforting...yikes.

 

I should have linked the podcast for anyone who is interested (below). I just came away thinking ChatGPT is far more susceptible to errors than I realized and not quite as advanced as I initially thought. On the other hand, I still think it's amazing with language and a good resource tool. As with anything, we should always use multiple sources when possible.

https://www.samharris.org/podcasts/making-sense-episodes/312-the-trouble-with-ai

Sam Harris speaks with Stuart Russell and Gary Marcus about recent developments in artificial intelligence and the long-term risks of producing artificial general intelligence (AGI). They discuss the limitations of Deep Learning, the surprising power of narrow AI, ChatGPT, a possible misinformation apocalypse, the problem of instantiating human values, the business model of the Internet, the meta-verse, digital provenance, using AI to control AI, the control problem, emergent goals, locking down core values, programming uncertainty about human values into AGI, the prospects of slowing or stopping AI progress, and other topics.

***

Stuart Russell is a Professor of Computer Science at the University of California at Berkeley, holder of the Smith-Zadeh Chair in Engineering, and Director of the Center for Human-Compatible AI. He is an Honorary Fellow of Wadham College, Oxford, an Andrew Carnegie Fellow, and a Fellow of the American Association for Artificial Intelligence, the Association for Computing Machinery, and the American Association for the Advancement of Science. His book, Artificial Intelligence: A Modern Approach, co-authored with Peter Norvig, is the standard text in AI, used in 1500 universities in 135 countries. Russell is also the author of Human Compatible: Artificial Intelligence and the Problem of Control. His research covers a wide range of topics in artificial intelligence, with a current emphasis on the long-term future of artificial intelligence and its relation to humanity. He has developed a new global seismic monitoring system for the nuclear-test-ban treaty and is currently working to ban lethal autonomous weapons.

***

Gary Marcus is a scientist, best-selling author, and entrepreneur. He is well-known for his challenges to contemporary AI, anticipating many of the current limitations decades in advance, and for his research in human language development and cognitive neuroscience. He was Founder and CEO of Geometric Intelligence, a machine-learning company acquired by Uber in 2016. His most recent book, Rebooting AI, co-authored with Ernest Davis, is one of Forbes’s 7 Must Read Books in AI. His podcast Humans versus Machines, will come later this spring.

 

Here you go, babe

ZeroGPT - Chat GPT, Open AI and AI text detector Free Tool

It helps identify AI written work, when the cases are more subtle than the one you mentioned above.

 

That is pretty solid. I entered 5 paragraphs on Brown v Board from ChatGPT and it detected 4 of the 5 as being generated by AI. Pretty solid performance. Could be a very useful tool.

 

I pasted a section from a recent MSJ brief I wrote and it identified it as being human-generated. I pasted a Wikipedia entry about WWII and it identified it as 100% AI GPT. I wonder if that means the Wikipedia section was necessarily written by AI or if the program also searches the internet to identify other forms of plagiarism such as students copying and pasting from Wikipedia?

 

We've been using it for a few months. It is a necessity.

 

Not sure. We use Turnitin.com to identify work from the web. ZeroGPT may outclass that as a resource if it can identify matches to the web as well.

 

Seems relevant. Apparently English isn’t the only thing at risk

AI leaders warn the technology poses 'risk of extinction' like pandemics and nuclear war

 

I saw a somewhat funny story/scary story, a research company gave Chat GTP 4 access to a small amount of cash, to see what it would do, and Chat GTP hired a human to help it solve capthca so it could access websites that try to block robots... It even lied to the person it hired, saying he was a blind person and needed help solving captcha.

GPT-4 Was Able To Hire and Deceive A Human Worker Into Completing a Task | PCMag