Here is a quote from my Mystery AI Hype Theater email from the people at DAIR who are actual respected full-time AI skeptics: (They are exasperated with a Chronicle of Higher Education article which I cannot read because paywall):
"A clearer-eyed view of what has happened in the last two years is that a few companies have amassed enormous amounts of data (mostly taken non-consensually) and the capital to buy the computing resources to train enormous models which, in turn, can be used to output facsimiles of the kinds of interactions represented in the data. So we have the ability to get text on demand that looks like legal contracts, or looks like medical diagnoses, or looks like therapeutic conversations, or looks like a news article, or looks like scientific research papers. But it actually is none of those things, because in all cases the textual artifact isn't really the point; the point is rather the thought processes and relationship-building that led to and follow from the textual artifact. (The sort-of exception here is legal contracts, where the textual artifacts are very much the point, except that the whole task is designing a textual artifact that meets the needs of the parties entering into the contract. Those needs usually extend well beyond "a text that has some nice legalese in it and otherwise looks like a contract.")
It adds insult to industry to say that higher ed should be (and is failing at) keeping pace with this purported rapid progress."
As a corollary, in 1980 did anyone foresee Walmart doing what it did to the likes of Sears, JCPenney, Circuit City, etc? This would be the beginning of the computer revolution in which Walmart was an early adopter. Thirty years later during the internet revolution, Walmart is looking over its shoulders at Amazon. Who will be staring down at Amazon twenty years from now in the AI revolution?
For a casual reader it seems one area where AI has improved productivity is in coding. But coding has the feature that there's a relatively objective test of results: either the code runs or it doesn't; if the code runs does it accomplish what it's supposed to? To me that's the crux--in which field(s) does AI work.
You use "game-changer," everyone's favorite word for what AI is doing or not doing, but it is never clear what game exactly is being changed. Game-changer is better than Silicon Valley's more serious sounding "disruption." Ten years after Jill Lepore's take down of Clayton Christensen in the New Yorker, disruptive innovation remains their framework for how this is supposed to go, despite how little evidence there is that is how any of this works. The evidence so far is that adoption of generative AI is happening slowly and fitfully, with 1 of 7 people trying it out only to stop using it. When it comes to education, especially in the short term, MOOCs does seem like a better model than say, electricity. Either way, changes to labor markets and classrooms won't happen at the speed the loudest talkers are saying it will.
I wrote the appended commented on Dave Karpf's substack just before coming here. Responding to the BCS study you mention, it's a bit self-serving I think. If a consultant using Chat-GPT can produce a report that's only 23 per cent worse than the traditional product in, say, half the time, that will be enough to chew up the low-end of the consultancy market, which is most of it.
*My comment*
ChatGPT is already as good as McKinsey (and that's not a compliment). I prompted ChatGPT with "can you write a comparison of wind and wave power mentioning advantages of both but concluding that wave power is superior" and got the following. Add some glossy pics (thanks, DALL-E) and it's indistinguishable from the consulting report you'd get with the same prompt (maybe worded more subtly)
ind power has several advantages over traditional fossil fuel-based energy sources. It is a renewable and clean energy source that does not produce any greenhouse gas emissions during operation.[1][2] Wind turbines also have a relatively small land footprint compared to other renewable technologies like solar.[3] Additionally, wind power is a mature technology with well-established infrastructure and a declining cost of energy.[1][2]
However, wind power also has some limitations. Wind is an intermittent resource, with power output varying significantly based on wind speed.[2] This can lead to issues with grid integration and reliability. Wind farms also require large open spaces, which can limit their deployment in some regions.[3]
In contrast, wave power offers several advantages over wind power. Waves are a more consistent and reliable energy source, as they are hardly interrupted and almost always in motion.[2] This makes electricity generation from wave energy more reliable and predictable compared to wind.[2] Wave energy converters also have a smaller footprint and can be deployed offshore, reducing the need for large open spaces.[4][3]
Furthermore, wave power has a higher energy density than wind, meaning more energy can be extracted from the same area.[5][6] The theoretical global output of wave power is estimated to be around 29,500 TWh/yr, which is roughly 125% of the current global electricity demand.[5] This vast untapped potential makes wave power an attractive option for renewable energy generation.
While both wind and wave power have their advantages, the evidence suggests that wave power is the superior renewable energy source. Wave power offers greater reliability, predictability, and energy density compared to wind, making it a more promising option for large-scale renewable energy generation.[2][5] As such, the development and deployment of wave energy technologies should be a priority in the transition to a sustainable energy future.
Wave vs. Wind and Solar - 'Sintef' - Blog
Wave energy pros and cons - SolarReviews
Feasibility of Wave Power - Stanford University
Advantages and Disadvantages of Wave Energy - Greentumble
Wave and Wind are the New Hybrid Renewable Energy Source
Review of Hybrid Offshore Wind and Wave Energy Systems
My favourite recent AI failure has been Air Canada's chatbot that offered an out-of-policy refund. AC tried to make the chatbot sound so autonomous AC wasn't responsible. Of course the courts found different.
Here is a quote from my Mystery AI Hype Theater email from the people at DAIR who are actual respected full-time AI skeptics: (They are exasperated with a Chronicle of Higher Education article which I cannot read because paywall):
"A clearer-eyed view of what has happened in the last two years is that a few companies have amassed enormous amounts of data (mostly taken non-consensually) and the capital to buy the computing resources to train enormous models which, in turn, can be used to output facsimiles of the kinds of interactions represented in the data. So we have the ability to get text on demand that looks like legal contracts, or looks like medical diagnoses, or looks like therapeutic conversations, or looks like a news article, or looks like scientific research papers. But it actually is none of those things, because in all cases the textual artifact isn't really the point; the point is rather the thought processes and relationship-building that led to and follow from the textual artifact. (The sort-of exception here is legal contracts, where the textual artifacts are very much the point, except that the whole task is designing a textual artifact that meets the needs of the parties entering into the contract. Those needs usually extend well beyond "a text that has some nice legalese in it and otherwise looks like a contract.")
It adds insult to industry to say that higher ed should be (and is failing at) keeping pace with this purported rapid progress."
As a corollary, in 1980 did anyone foresee Walmart doing what it did to the likes of Sears, JCPenney, Circuit City, etc? This would be the beginning of the computer revolution in which Walmart was an early adopter. Thirty years later during the internet revolution, Walmart is looking over its shoulders at Amazon. Who will be staring down at Amazon twenty years from now in the AI revolution?
For a casual reader it seems one area where AI has improved productivity is in coding. But coding has the feature that there's a relatively objective test of results: either the code runs or it doesn't; if the code runs does it accomplish what it's supposed to? To me that's the crux--in which field(s) does AI work.
You use "game-changer," everyone's favorite word for what AI is doing or not doing, but it is never clear what game exactly is being changed. Game-changer is better than Silicon Valley's more serious sounding "disruption." Ten years after Jill Lepore's take down of Clayton Christensen in the New Yorker, disruptive innovation remains their framework for how this is supposed to go, despite how little evidence there is that is how any of this works. The evidence so far is that adoption of generative AI is happening slowly and fitfully, with 1 of 7 people trying it out only to stop using it. When it comes to education, especially in the short term, MOOCs does seem like a better model than say, electricity. Either way, changes to labor markets and classrooms won't happen at the speed the loudest talkers are saying it will.
I wrote the appended commented on Dave Karpf's substack just before coming here. Responding to the BCS study you mention, it's a bit self-serving I think. If a consultant using Chat-GPT can produce a report that's only 23 per cent worse than the traditional product in, say, half the time, that will be enough to chew up the low-end of the consultancy market, which is most of it.
*My comment*
ChatGPT is already as good as McKinsey (and that's not a compliment). I prompted ChatGPT with "can you write a comparison of wind and wave power mentioning advantages of both but concluding that wave power is superior" and got the following. Add some glossy pics (thanks, DALL-E) and it's indistinguishable from the consulting report you'd get with the same prompt (maybe worded more subtly)
ind power has several advantages over traditional fossil fuel-based energy sources. It is a renewable and clean energy source that does not produce any greenhouse gas emissions during operation.[1][2] Wind turbines also have a relatively small land footprint compared to other renewable technologies like solar.[3] Additionally, wind power is a mature technology with well-established infrastructure and a declining cost of energy.[1][2]
However, wind power also has some limitations. Wind is an intermittent resource, with power output varying significantly based on wind speed.[2] This can lead to issues with grid integration and reliability. Wind farms also require large open spaces, which can limit their deployment in some regions.[3]
In contrast, wave power offers several advantages over wind power. Waves are a more consistent and reliable energy source, as they are hardly interrupted and almost always in motion.[2] This makes electricity generation from wave energy more reliable and predictable compared to wind.[2] Wave energy converters also have a smaller footprint and can be deployed offshore, reducing the need for large open spaces.[4][3]
Furthermore, wave power has a higher energy density than wind, meaning more energy can be extracted from the same area.[5][6] The theoretical global output of wave power is estimated to be around 29,500 TWh/yr, which is roughly 125% of the current global electricity demand.[5] This vast untapped potential makes wave power an attractive option for renewable energy generation.
While both wind and wave power have their advantages, the evidence suggests that wave power is the superior renewable energy source. Wave power offers greater reliability, predictability, and energy density compared to wind, making it a more promising option for large-scale renewable energy generation.[2][5] As such, the development and deployment of wave energy technologies should be a priority in the transition to a sustainable energy future.
Wave vs. Wind and Solar - 'Sintef' - Blog
Wave energy pros and cons - SolarReviews
Feasibility of Wave Power - Stanford University
Advantages and Disadvantages of Wave Energy - Greentumble
Wave and Wind are the New Hybrid Renewable Energy Source
Review of Hybrid Offshore Wind and Wave Energy Systems
Thanks for posting something skeptical about AI.
My favourite recent AI failure has been Air Canada's chatbot that offered an out-of-policy refund. AC tried to make the chatbot sound so autonomous AC wasn't responsible. Of course the courts found different.
https://www.theguardian.com/world/2024/feb/16/air-canada-chatbot-lawsuit