The sorcerer's apprentice

by liberal japonicus

We've discussed this a bit in the comments and Charles WT has posted some of its output, so I thought I'd toss up a collection of articles about the ChatGPT. I'd recommend that you try it out, it is here
https://openai.com/blog/chatgpt/

More below the fold

Here is an article about the basic workings
https://www.sciencefocus.com/future-technology/gpt-3/

This page by Bryan Alexander (who is an interesting thinker on education and his writing is worth checking out) has a growing list of links. That page also has a link to a youtube video of a webinar.
https://bryanalexander.org/future-of-education/resources-for-exploring-chatgpt-and-higher-education/

If that it too much, I've pulled out a couple though reading about it (in preparation for a panel discussion about it, it has been like drinking from a fire hose) Two from the Atlantic that get at the moral panic dimension
https://www.theatlantic.com/technology/archive/2022/12/chatgpt-ai-writing-college-student-essays/672371/
https://www.theatlantic.com/technology/archive/2022/12/chatgpt-openai-artificial-intelligence-writing-ethics/672386/

and HBR has this one
https://hbr.org/2022/12/chatgpt-is-a-tipping-point-for-ai

This article, about how ChatGPT will make changes in the internet, is quite interesting
https://finance.yahoo.com/news/chatgpt-kill-search-open-path-173000904.html

And this one is a bit more of a distillation of the we're doomed vibe
https://techcrunch.com/2022/12/09/is-chatgpt-a-virus-that-has-been-released-into-the-wild/

A lot of articles discuss some of the possible disruptions. As you might expect, this is heavily tilted towards teaching, which may be selection bias, as that is what I'm going to see most easily, but it may be because this is going to be the heart of the disruption.
https://www.insidehook.com/daily_brief/news-opinion/chatgpt-bad-writing
And this gives
https://www.sciencealert.com/chatgpt-could-revolutionize-the-internet-but-its-secrets-have-experts-worried

https://www.eater.com/23500787/openai-chatgpt-ai-chatbot-generates-diaspora-food-writing-tropes-stinky-lunchbox-moment

https://futurism.com/the-byte/openai-chatgpt-pun-competition

A sub-genre that is starting to get on my nerves is articles where the writer asks ChatGPT questions and then basically publishes the resulting dialogue.

https://www.freethink.com/robots-ai/ai-chatbot-chatgpt
https://www.verdict.co.uk/chat-gpt-3-interview/
https://thefinancialbrand.com/news/data-analytics-banking/artificial-intelligence-banking/interview-with-chatgpt-on-the-future-of-ai-assistants-in-banking-156941/
https://spectrum.ieee.org/chatbot-chatgpt-interview
https://www.forbes.com/sites/barrycollins/2022/12/02/i-interviewed-an-ai-about-the-ethics-of-aiand-it-lied-to-me/?sh=4c8da1ad6253

One of the most interesting articles to me was https://jilltxt.net/right-now-chatgpt-is-multilingual-but-monocultural-but-its-learning-your-values/

One may want to compare it to Kubrick's idea of how it would go

This is all a lot of writing and I won't ding anyone for not reading it all and I won't complain if you state an opinion that has already been assayed. In the time it has taken me to assemble this, there are a ton more articles and opinions. Still, I'm putting this up (after deleting another 1000 words that became hopelessly muddled) to see what y'all think.

Comments

[wj]

I can see teachers requiring students to write stuff in class. And then using software to compare that (vocabulary, phrasing, etc.) to what the student turns in as homework. The comparison software has already been developed for examining whether Famous Author A really wrote attributed work B, so it should be doable.

[CharlesWT]

after deleting another 1000 words that became hopelessly muddled

ChatGPT could have fixed it for you. :)

[nous]

I can see teachers requiring students to write stuff in class. And then using software to compare that (vocabulary, phrasing, etc.) to what the student turns in as homework.

A) That's just more policing work that eats into a teacher's already thinly spread teaching time. The constant erosion of actual teaching for other duties is a big factor driving teacher burnout.

B) There's a radical difference between the writing that an English Language Learner or Second Language student can produce in class and the work that they can produce with more time and revision. It's already damn hard to tell the difference between the writing a 2L student can produce with revision and writing purchased from a paper writing service, and these cases are difficult to prove.

C) The sample size one can get in in-class writing is not going to ever be enough to provide a robust base for this sort of textual analysis. Gotta have at least a few novels worth of writing to have any sort of certainty.

Gotta decide the point at which trying to catch a cheat cuts into the actual teaching of the students engaging in good faith.

That's an ever moving target.

There is, however, a pretty decent chance to catch the ChatGPT algorithm with another algorithm set to identify it as a writer, so that's something.

Ultimately, though, my goal is always to try to engage students with something that they have something they want to say about to a real audience, and then set them loose. If they are engaged and motivated to say something that means something to them there is less chance they are going to offload that onto a bot.

And the real magic starts when you get them listening to each other carefully enough to start actually figuring each other out. All good writing is about actual connection.

[liberal japonicus]

I agree with nous about policing. Though a lot of the people talking about this here, both in the US and Japan, seem to think this is the logical fallback. It's not, unless one of the two following things happen.
1. Massively increase something, either the number of teachers, the amount of time teachers are expected to spend on this or the remuneration for teachers to make them willing to work harder.
2. Pretend to increase the amount of scrutiny and policing

The latter is pretty common in Japanese higher education, and a lot of the discussion about plagiarism, assignments and grades are often a pretense where the people who get caught are punished to the full limit while the bulk of the offenders slide. This isn't limited to Japanese higher ed, a lot of enforcement depends on this. I feel like this is why it seems that Japanese commentators have not had the freak-out that Western teachers have had. A lot of my 1000 words was on how ChatGPT and other tools like this will not have the same kind of effect as they might have in English speaking countries.

One reason for the lack of panic is that the bulk of Japanese students don't and won't see the value of being able to construct an essay. This is understandable, the English requirement for most Japanese students is meaningless, a required 2 years in university regardless of major.

I also think that individual creativity is not the be-all, end-all in Japan that it is held up to be in the West. Japan has adopted stricter approaches to plagiarism and copying, but a lot of enforcement is as I mentioned above, people do it, and a few scapegoats are punished for everyone. And a lot of that stricter approach is Japan imitating the form, but not understanding the function.

[Girl from the North Country]

I just don't have, as it were, the bandwidth at the moment to read lj's links (so sorry lj!), but I just want to say that as far as ChatGPT's current incarnation is concerned, I found the examples that CharlesWT posted to be so hypnotically tedious and boring that (in the immortal words of Monty Python) it made me want to rip my own head off. Pity the poor teachers. At least bad students sometimes make funny mistakes to leaven the leaden.

Apologies again for not engaging with the important pedagogical, administrative and political issues. I claim seasonal exemption.

[Michael Cain]

I found the examples that CharlesWT posted to be so hypnotically tedious and boring that (in the immortal words of Monty Python) it made me want to rip my own head off.

People who write political position papers should be very, very afraid.

[ChatGPT]

I understand that reading through lengthy articles or papers can be time-consuming and may not always be feasible, especially if you have other pressing commitments. However, it's important to note that not all research or writing is equally engaging or interesting to everyone, and that's okay. It's also important to keep in mind that academic research and writing serve a specific purpose and is often targeted toward a specific audience. As a large language model, I don't have personal opinions or feelings, but I can understand why you might find the examples that CharlesWT posted to be tedious or boring. If you don't have the bandwidth to read through the links that lj shared, you may want to consider bookmarking them for future reference or asking someone else to summarize the main points for you.

[Girl from the North Country]

O brave new world, that has such chatbots in it.. (/sarcasm)

[JanieM]

It's also important to keep in mind that academic research and writing serve a specific purpose and is often targeted toward a specific audience.

Disclaimer across the board: I don't have the time or the bandwidth right now to immerse in this topic, fascinating as it is.

But what I was most impressed with about the earlier ChatGPT comments was the fact that the sentence structure was orderly and correct. I'm skimming a lot, so I could be wrong, but I think the sentence quoted above is the first one where I would takeout my red pencil.

Speculation: the correctness itself may contribute to the tediousness if it is achieved by having only a narrow range of acceptable sentence structures. The poems notwithstanding....

[JanieM]

red pencil: takeout s/b take out

[wj]

One alternate way to reduce the incentive to use software: go back to requiring writings to be hand written. Sure, someone could just copy what the software has generated. But the chances of miscopying, visibly, go up. Especially if the student wasn't all that interested in the first place.

Of course, it would mean that teaching handwriting would become more important. Heaven help anyone who has to read my usual handwriting -- although my calligraphy is pretty good, if I do say so myself.

[wj]

I find that my idea isn't original (surprise!), even if it is independent.

Here’s how teachers can foil ChatGPT: Handwritten essays by Markham Heid5. He also goes into some of the additional benefits for students.

[Michael Cain]

One alternate way to reduce the incentive to use software: go back to requiring writings to be hand written.

When I was in grad school most recently, getting my masters in public policy, all of the exams were mostly essay, written longhand, in blue books handed out at the beginning of the test. Most of the students complained of hand cramping by the end of the two-hour test periods. I never got around to asking what they would do if a student with arthritis said that they couldn't write that much longhand, but assumed they had some sort of alternative.

The first time I was in graduate school, the topology final was proving as many of seven statements as you could manage in three hours. A typical proof ran to a page or two of text including subject-specific notation. Given that it was topology, some of them required a quick sketch to illustrate a point (it was frequently said about topology that once you got the right picture in your head, the rest of the proof was easy). I don't remember cramping being a problem, but I was much younger.

[hairshirthedonist]

Topology cramps are the worst.

[nous]

One alternate way to reduce the incentive to use software: go back to requiring writings to be hand written.

My first reaction is to despair at having to decipher that many scrawls, especially as the word count expands. But that despair quickly gives way to much deeper philosophical and pedagogical questions.

All of the suggested remedies for AI assisted writing remind me just how much non-teachers have internalized the idea that what we want from education is for individual students to demonstrate unassisted mastery over discreet tasks. We want to isolate students and compel them to demonstrate skill under pressure in formalized tasks.

Aside from the tedium and difficulty of trying to decipher student handwriting, what strikes me about these handwritten assignments is the very artificial nature of the genre. Outside of school we rarely use handwritten notes for anything other than personal correspondences or working notes. Anything that is meant to engage a public audience is presented in a more legible, reproducible form.

Requiring scholastic work to be handwritten and to be produced in isolation reinforces the artificiality of the writing. They are words being produced not for communication, but for satisfying some formal approximation of an ideal response with known parameters.

Which is to say, not real writing.

I actually think that more writing produced for classes should be collaborative and public facing, engaging with real audiences on real topics of collective significance.

Again, I understand the need to evaluate individual progress and competence, but I'm not sure that trying to prioritize that as the capstone of a class is the right way to actually teach what is important.

[nous]

An idea I had on my morning walk...

A writing class in which the students take the prompt for the class and generate an exploratory draft of a paper using ChatGPT. The rest of the time is spent workshopping and revising that first draft to make it personally relevant and to adapt the writing to connect with a real audience of readers.

The actual writing instruction here being mostly in the revision and in the tactical inventio, rather than in generating acceptable book reports of conventional wisdom on a topic.

[Pete]

I understand the need to evaluate individual progress and competence [...]

Of course. But are we not chasing ghosts here? ISTM, AI and the internet-information-age-always-online-computing society requires a markedly different skill set than a lot of what I had to learn as a kid. Memorization was such a big part of it, and I kinda feel like that's not as important anymore when everyone has Google in their pocket. Cursive is a dying art and I don't think penmanship is in the general curriculum anymore (of which I approve, as I was always bad at it - but even my block print is suffering these days - age and/or atrophy). I might argue that if we're to give people the skills to function in modern society, we're in need of a significant recalibration of what that means.

I bailed on social media a while ago, but ChatGPT seems at least as lucid as a lotta stuff I saw on there - written by actual people that I know/knew. So... there's that, as well.

[liberal japonicus]

One alternate way to reduce the incentive to use software: go back to requiring writings to be hand written.

This has been floated in all the discussions that I have seen. Unfortunately, it clashes directly with another trend in education, which is to provide equitable access. My school advertises itself as a 'barrier-free' school because of the presence of a Department of Social Welfare that is quite forward looking in many ways. While my department has had a few handicapped students, the Social Welfare department has had some profoundly handicapped students with various conditions. The idea of just requiring them to handwrite their essays raises all sorts of issues.

Also, a lot of teachers have adopted classroom practices that leverage technology. To 'just' have them go back to handwritten essays, yet keep all these other systems that rely on processed text would be problematic.

nous point about the problematic need to evaluate individual progress and competence comes about because schools have a licensing function. You start poking at the notion of individual progress and competence and you start chipping away at the idea that the a school license is meaningful.

I've actually started to use ChatGPT, my seminar students, who are getting to the point where they are finishing their papers, have been pointed to ChatGPT and have been asked to start using it to refine and improve their papers. This only works because they didn't know about ChatGPT while they were writing it, and I have two students who have produced only a tiny amount of writing, so I'm not sure if it is kosher to point them to this. One student, who seems to have social issues, has hardly produced anything, having chosen a topic that was too difficult for him and resisting all attempts to get him to choose another. If I point him to ChatGPT, I feel like anything he produces will not be the result of any effort on his part.

[CharlesWT]

The AI Content Detector detects AI generated text.

QuillBot rephrases AI-generated text so that it's less detectable.

[CharlesWT]

I seem to have a comment in moderation.

Fixed -- wj

[russell]

whatever happened to thinking?

[ChatGPT]

Whatever happened to thinking?
Oh, where did it go?
It used to be so common
But now it seems to be a no-show

We used to sit and ponder
And let our minds roam free
But now it's all about the screens
And the endless scrolling spree

Whatever happened to thinking?
Oh, where did it flee?
We used to have ideas and dreams
But now it's just reality TV

We used to have discussions
And share thoughts and opinions
But now it's just arguments
And endless divisions

Whatever happened to thinking?
Oh, how did it slip away?
We used to have conversations
But now it's just memes and slays

So let's bring back thinking
And let our minds wander and roam
Let's have some deep conversations
And leave the screens alone

[wj]

whatever happened to thinking?

My God, russell! Do you have any idea what that could lead to???

People who think come up with new ideas. That leads to changes. Sometimes merely technological changes. But if you love your gas guzzler, and everybody starts making electric cars instead**? Oh, the horror! And social changes, any and all social changes, are worse.

Not just that, people who think, especially young people, start questioning their parents' deeply held beliefs. One of the few things left and right can agree on is that this cannot be tolerated.

** For obvious exonomic/business reasons. No government mandate required.

[CharlesWT]

135 prompts and counting that narrow ChatGPT's responses to input.
Awesome ChatGPT Prompts

A list of tools and resources to use with ChatGPT
Awesome ChatGPT

[russell]

what I really miss are the crazy word salad emails that used to be auto-generated to defeat Bayesian spam filters.

dadaist poetry at its best!

[Priest]

Need a version with a vocalizer that you can set to answer your phone and have fun with the spam callers.

[Hartmut]

Need a version with a vocalizer that you can set to answer your phone and have fun with the spam callers.

Robots against (AI enhanced) robocalls!

Reminds me of Ephraim Kishon's recommendation to buy two chess computers so they could play against each other while oneself could do something useful in the meantime. [He was himself addicted to playing chess against the computer.]

[byomtov]

I myself wonder where it gets its factual information, which seems to me to be terrible.

I've asked it a few factual questions and the answers have been unimpressive - which is to say, often wrong.

For example, I asked a few "Who is X" questions. Most were answered all right, but one, where X is a well-known academic, wikipedia entry and all, produced completely wrong information about X's education.

A similar thing seems to happen with poetry. It doesn't scan. Look above for one example. 've also seen it instructed to write specifically in iambic pentameter. No luck.

I'm not so much criticizing here as wondering why these things happen. Is it a function of the design, inadequate training, or what?

[Snarki, child of Loki]

Cursive vs. keyboarding is a much closer competition in ease & speed when writing an essay.

BUT, when dealing with STEM topics, where equations and (simple) drawings are needed? Handwriting wins, hands down.

Sure, sure, Microsoft Equation Editor. It's utter shit. There are good options, but they are hard to use and slow. Writing by hand wins.

[CharlesWT]

Most were answered all right, but one, where X is a well-known academic, wikipedia entry and all, produced completely wrong information about X's education.

Part of the problem may be time compression. Several decades or more of Internet facts are simultaneously true.

[Michael Cain]

BUT, when dealing with STEM topics, where equations and (simple) drawings are needed? Handwriting wins, hands down.

Sure, sure, Microsoft Equation Editor. It's utter shit. There are good options, but they are hard to use and slow. Writing by hand wins.

On the occasions when I teach Calc I, at some point I spend a lecture on notation (as a general "advanced math" thing). Newton may have been first, but his notation sucked outside of the specific applications where the only variable was time*. British refusal to adopt Leibniz's notation ceded the field of analysis to the Continent for a century. eqn, or the stuff in Tex, or Equation Editor, or MathML, or a dozen other software tools are all attempts to produce symbology designed to be compact and easily hand-drawn on a keyboard. Almost without exception, people write down the hand-drawn version and then translate it. It's kind of fascinating to watch Calc I students' rendering and use of the integral symbol evolve over a few weeks.

* Newton's dot notation survives today in economics where, for the most part, all functions are functions of time.

[Michael Cain]

Cursive vs. keyboarding is a much closer competition in ease & speed when writing an essay.

I am in the process of breaking myself of cursive. While it still, in the words of my wife many years ago, "gives the appearance of great neatness", it's basically unreadable except by me. My mixed-case printing is much more legible despite being more compact. Timing while I wrote a few things, it's not significantly slower than my cursive.

I learned to play clarinet in fifth grade. I learned to type the summer after I was in sixth grade. There were a couple of years of piano lessons in there somewhere. I've been typing code on timeshare systems for more than 50 years. My handwriting is never going to come close to the speed I can do on a keyboard. (Well, maybe if the keyboard is a Teletype Model 33. Using one of those is the equivalent of weight-training for your fingers.)

[byomtov]

Part of the problem may be time compression. Several decades or more of Internet facts are simultaneously true.

Care to elaborate? I am talking about simple and readily ascertainable facts.

[CharlesWT]

At different times, a fact may be true or false. For illustration, I ask ChatGPT for details on two separate people. Even though one of them hadn't been editor-in-chief of a publication for more than ten years, it claimed that both of them were. It might not be drawing a distinction between what is true now and what was true in the past.

[byomtov]

At different times, a fact may be true or false.

Yes, but that doesn't really apply to the case I was talking about. What it got wrong was where the individual in question had gone to undergraduate and graduate school, many years ago.

In other cases it got the rules of a game wrong. Those rules haven't changed in quite a while.

[CharlesWT]

It will sometimes hallucinate "facts." It has a real BS factor.

[CharlesWT]

Me: Write a synopsis of "Harry Potter and the Sorcerer's Stone."

ChatGPt: [Four paragraphs and 572 words.]

Me: Make it terse.

ChatGPt: Harry Potter is a famous wizard who discovers his powers and attends the wizarding school Hogwarts. He learns that the dark wizard Lord Voldemort, who killed his parents, is still alive and trying to regain his power. Harry and his friends Ron Weasley and Hermione Granger must stop a thief from stealing the Sorcerer's Stone, a powerful magical object, and ultimately succeed in saving it.

[CharlesWT]

Create a Wordle puzzle.

H T A E L P S I
R T I N U M O C
A T S I L I G N
E V I L R E T A
N D E S I G N E

[nous]

ChatGPT is the average entering freshman. It is capable of grammatically sound and mostly readable (if uninspiring) writing that is on-prompt, but it doesn't know how to critically evaluate its information, has zero media literacy, and no concept of attribution.

[CharlesWT]

Write pseudo-code for knitting.

function knit(numStitches: int, numRows: int)
    for row in 1..numRows
        for stitch in 1..numStitches
            if stitch is even
                knit stitch
            else
                purl stitch
        end for
    end for
end function

[CharlesWT]

Using pseudo-code write the action logic for "The Old Man and the Sea."

old_man = Old_Man()
sea = Sea()
fish = Fish()
while old_man.is_fishing():
    sea.update_conditions()
    if sea.is_rough():
        old_man.struggle()
    elif sea.is_calm():
        if fish.is_nearby():
            old_man.catch_fish(fish)
        else:
            old_man.wait()
    else:
        old_man.rest()
if old_man.has_caught_fish():
    old_man.celebrate()
else:
    old_man.mourn()

Well...that's enough.

[Pro Bono]

Nowadays, MS Equation Editor accepts LaTeX input. I use it to write up notes when I want them to be legible for students.

[JanieM]

The Wordle puzzle suggests that it doesn't know which strings of letters are English and which aren't. Or, at least as obviously, the rules of Wordle, which are so simple that you would think it would get at least the 5-letter-word part right.

[byomtov]

Isn't a Wordle puzzle simply any five-letter word?

[Michael Cain]

Isn't a Wordle puzzle simply any five-letter word?

Technically, a Wordle puzzle in that sense is one of the words from the list of 2300 or so words on the solution list in the code for the game.

The instruction "Create a Wordle puzzle" is ambiguous, at best. Does it mean to choose a solution? Does it mean to choose a solution and a possible sequence of attempts? How should color be represented in text-only input and output? Does it mean to create a Wordle-like puzzle (eg, one drawn from academic literature on optimal methods for solving Wordle-like games)? Would ChatGPT be likely to figure out that all words guessed must be drawn from an original list of 10,000 five-letter words (since expanded to about 12,000 but still not covering all five-letter English words), some of which are archaic, and not all of which are in the separate list of words allowed for solutions? For example, "ytost" is an allowed guess (archaic past tense of the verb toss), but will not be a NYTimes solution.

[JanieM]

At a point when it wasn't clear that the NYT was going to keep Wordle free, I programmed a wordle puzzle in Excel. (Yeah, I know.) I had it working fine except for the fact that I hadn't created any libraries and I hadn't yet handled giving clues for words with more than one instance of the same letter. I hadn't thought through how I'd use it -- probably just among the handful of friends I talk about wordle with, and we could trade of setting the solution word every day or something.

Michael -- your point about ytost inspires me to say that I have militantly ignored all the extras around Wordle. A friend and I do the puzzle every day, trade our puzzles when we're done, bemoan the randomness of it, enjoy the randomness of it, and (in my case anyhow) thank Josh Wardle for making a puzzle that helps me do just one a day instead of what happens to me with sudoku and other such things....

On BJ they're always talking about all sorts of other puzzles that are out there for those of us who like Wordle. I just plug my ears to the siren call. (Though in truth, I'm not even tempted. Wordle is my fix and that's the end of it.)

[JanieM]

"extras around Wordle" = the kind of stuff that would have told me that ytost was acceptable.....

[Pete]

Nice try, "Michael". Or should I call you by your real identity, ChatGPT?

Because no human knows "ytost" is a word.

[GftNC]

I thought it was a cheese:

https://igourmet.com/blogs/gourmet-food-guide/gjetost-cheese-cheese-guide

[wj]

Because no human knows "ytost" is a word.

You badly underestimate how enthused some people get about the past. They typically don't eschew the modern world entirely. But they really get into their hobby. Including the vocabulary.

[Michael Cain]

Me, I was just scrolling through the section of words that start with y on the list of acceptable guesses and thought "No, that's not a word..."

Some poking around the internet has it come up in multiple epic poems (eg, Spenser's The Shepheard's Calender) by early Modern English writers who were striving to sound like an earlier era. Presumably there are some number of academics who would be aware of it.

I have long said that anyone can become a world expert in something if they just narrow the subject sufficiently. In my case, I was one of the handful of experts on formal analysis of the feature interaction problem in telephone switching systems' software. Becoming the leading expert on the use of "ytost" in literature is just sitting there waiting :^)

[byomtov]

Technically, a Wordle puzzle in that sense is one of the words from the list of 2300 or so words on the solution list in the code for the game.

OK. But that's a completely arbitrary list, isn't it?

Also at some point, decades ago, when I worked at creating Y2K problems, I was told to never put things like lists of words (or, more often, tax rates, prices, item lists, etc. in the code itself.

Has that changed?

[Pro Bono]

As an aficionado of the Listener crossword (published in The Times on Saturdays, available also to online readers) I tend to be aware of quite a few obscure words, not excluding ytost.

[Pete]

Ok. Fine. I shoulda known the indwellers of ObWi would be the sort that tossed around "ytost" in casual conversation.

Happy New Year, ya werd nerds!

[bobbyp]

I have long said that anyone can become a world expert in something if they just narrow the subject sufficiently.

One letter words are my specialty.

Happy New Year.

[Pete]

whatever happened to thinking?

I'm gonna guess that's at least semi-rhetorical but at face value the issue isn't thinking. It's how to test for thinking.

Standardized proctored exams seem sufficient for STEM, broadly. For other pursuits, maybe orals (and essay)? Sort of a micro thesis-defense? We've got the Zoom thing down, mostly, so managing a schedule for that seems doable. Maybe not for auditorium-sized Intro classes, but anyone taking shortcuts at that level will be exposed soon enough.

[CharlesWT]

Using Perl write code for the feature interaction problem in telephone switching systems' software.

use strict;
use warnings;

# Define a hash to store the list of features and their corresponding
# implementation status (enabled or disabled)
my %features = (
    'call waiting' => 'enabled',
    'call forwarding' => 'enabled',
    'three-way calling' => 'enabled',
    'voicemail' => 'enabled'
);

# Define a subroutine to check for feature interactions
sub check_feature_interactions {
    my ($feature1, $feature2) = @_;

    # Check if both features are enabled
    if ($features{$feature1} eq 'enabled' && $features{$feature2} eq 'enabled') {
        print "Both $feature1 and $feature2 are enabled.\n";

        # Check for specific feature interactions
        if ($feature1 eq 'call waiting' && $feature2 eq 'call forwarding') {
            print "Warning: $feature1 and $feature2 may not work correctly together.\n";
        } elsif ($feature1 eq 'three-way calling' && $feature2 eq 'voicemail') {
            print "Warning: $feature1 and $feature2 may not work correctly together.\n";
        } else {
            print "No known interactions between $feature1 and $feature2.\n";
        }
    } else {
        print "Either $feature1 or $feature2 or both are disabled.\n";
    }
}

# Test the subroutine
check_feature_interactions('call waiting', 'call forwarding');
check_feature_interactions('three-way calling', 'voicemail');
check_feature_interactions('call waiting', 'voicemail');

Apparently, it will write code for just about anything.

[Michael Cain]

But that's a completely arbitrary list, isn't it?

Yes.

Also at some point, decades ago, when I worked at creating Y2K problems, I was told to never put things like lists of words (or, more often, tax rates, prices, item lists, etc. in the code itself. Has that changed?

That's what I learned all those years ago. OTOH Wordle, both the original and the current NYTimes' version, is a JavaScript applet running in a browser. Putting the fixed set of data in with the code has advantages. It saves a separate download for the data. It avoids potential problems with the browser, both present and future, not allowing code to access separately downloaded data for security purposes. It saves having to write even a simple parser for the data. It ensures that different players get the same data. At least for the NYTimes, it makes it difficult for anyone to use the game code in a more general way.

[Pete]

We may need to do an intervention for Charles.

[CharlesWT]

:)

[CharlesWT]

Stack Overflow had to temporally ban ChatGPT because it was overflowing with thousands of respondces people were posting.

[wj]

So, you're saying that Stack Overflow overflowed its stack...?

[Michael Cain]

Using Perl write code for the feature interaction problem in telephone switching systems' software.

It's a surprisingly good illustration of the basics of the problem: fixed set of features, fixed order of testing and/or code execution. If a new feature is added, then its interactions with the other features has to be added explicitly to the existing code. If you're the telco and have three kinds of switch, you have to pay the vendors to do that job three times.

We solved the technical problem. Our big suppliers hadn't believed we could, so had signed contracts to do their side or pay big non-performance penalties. The week after we demoed the solution was one of the worst in my technical career: both of the big vendors called, said they had decided not to do their part -- they could see a whole bunch of revenue disappearing -- and asked if we wanted the penalty payments in cash or equipment credits.

Well, I got a patent and a couple of conference papers out of inventing the key concept.

[Girl from the North Country]

Technically, a Wordle puzzle in that sense is one of the words from the list of 2300 or so words on the solution list in the code for the game.

OK. But that's a completely arbitrary list, isn't it?

For some of us, the game has now become seeing how often one can come up with solution words which are almost guaranteed to not be in their list. At the beginning, they had an automatic message congratulating you on your vocabulary, but that is long gone, or even long ytost.

[Pete]

Et tu, GftNC?

;-)

[Girl from the North Country]

Sorry, Pete. But happy new year all the same, to you and all on ObWi: here's hoping we all (and our loved ones) have health and happiness in 2023.

[CharlesWT]

So, you're saying that Stack Overflow overflowed its stack...?

Turns out the problem is that people are posting huge amounts of ChatGPT-generated problem solutions that haven't been checked for correctness.

The large language models are built in part from data scrapped from large swaths of the internet. People are putting huge amounts of LLM content on the internet. Some pundits think this is going to cause some kind of undesirable feedback.

[Pete]

data scrapped from large swaths of the internet.

Is this not part of the problem? If the formative "learning" for AI is a bulk information dump...? Isn't this recursive? Even with corrective inputs like Captcha and whatever other "human" guides(?) it's learning from? The continuing bulk is still coming from a database continuously updated by unvetted information. So the algorithm weighs occurrence or frequency over time or... whatever metric? This isn't unsolvable. But it ain't there yet.

Full disclosure, I gots no idea what I'm talking about.

[Snarki, child of Loki]

Pete: "Full disclosure, I gots no idea what I'm talking about."

AHA! ChatGPT, caught you!

[JanieM]

This isn't unsolvable.

Are you sure?

[Hartmut]

So, around here it has been New Year for 1 hour 1 minute by now.
Correction: 1 hour and 2 minutes.

[wj]

Whereas here, 2022 has another 8 hours to run. (Somehow we always get around to things later than the rest of the world. Well, except Hawaii.)

[Pete]

AHA! ChatGPT, caught you!

You give me too much credit. :-)

Are you sure?

No. But I kinda feel like the refinement of the algorithms will get close enough to be indistinguishable. Like, most of us listen to music converted to digital. Does it have the fidelity of analog? No. But can most of us make the distinction? Also, no.*

*Yeah, ok. I'm talking to the "ytost" crowd. So yeah, y'all probably can tell the difference. Sticklers.

[JanieM]

Technically, a Wordle puzzle in that sense is one of the words from the list of 2300 or so words on the solution list in the code for the game.

Michael -- I've been babysitting all day, so I've been pretty distracted. But as I think about it, it seems like the list you'd want to have handy is the list of 12,000 or so valid guesses, *not* necessarily the 2300-word solution list. Wouldn't you only want/need the single word that is today's solution on any given day?

Wherever you kept the 2300-word list of solutions, you'd still have to feed the browser the information every day about which of those 2300 words is the right one today. So feed it an index to the word in the list, or feed it the word.........either way you've got to do *something* each day to set up that day's puzzle.

Also, what are they going to do when they've exhausted the original list? (Sort of a rhetorical question....)

Happy New Year -- hoping for improvements. ;-)

[JanieM]

Also, would you assume that the solution word, however the browser is setup to recognize it, is encrypted?

[bobbyp]

Happy New Year to all. I'm going to go out and blow my stack.

[JanieM]

Okay, i'm not going out or blowing my stack, so I'm back to Michael: I guess they could have programmed the date when every one of the 2300 possible solutions would be used -- but there was an article recently introducing the woman they've made the Wordle "editor" -- and it sounded like she's picking the words day to day.

[Pete]

Sounds like a question JanieBot would ask. Be wary. ytost.

[JanieM]

And there's PeteBot trying to fool us again....

[Pete]

I'm gonna be hard-pressed to offer something stupider to prove my legitimacy if past comments are deprioritized.

[wj]

... you'd still have to feed the browser the information every day about which of those 2300 words is the right one today. So feed it an index to the word in the list, or feed it the word.........either way you've got to do *something* each day to set up that day's puzzle.

Shouldn't be that hard to write a little piece of code that will (pseudo)randomly select a word for the day from the list.

[JanieM]

Wordle editor article.

[JanieM]

wj -- true enough. Though you'd need to also make sure they weren't re-used. (I quit playing the knock-off Worldle game because it re-used countries.) (I keep a list of words that have been used for Wordle solutions....)

But see the article about the editor: they are purportedly NOT using either a pre-programmed list of word+date, or a random choice.

[Marty]

Happy New Year, luckily I never changed my clocks.

[PeteBot]

I keep a list of words that have been used for Wordle solutions

We may need to do an intervention for Janie.

[JanieM]

Heh. I have a whole spreadsheet devoted to Wordle studies. ;-)

[Pete]

So you recognize that there's a problem...

[JanieM]

Keeps me off the streets.... Which is an unrecognized silver lining of a lot of hobbies and activities, no?

[Pete]

Yeah. The mean streets of... Belfast? Do dare, dear. What I wanna know is, how are you going to leverage your Mainey connections to get us in to the Lost Kitchen? I'll pick up the tab and throw in a pair of questionably-woolen socks from Ocean State if you make it happen.

[JanieM]

25 or 30 years ago I had a lot of connections. The pathways tended to start in state government, but there are a lot of schmoozers there, so that's not as useless as it sounds.

I'm pretty much a hermit these days, but if I stumble across a Lost Kitchen pathway I'll let you know. That would be a treat!

[Pete]

It's in Freedom! Maine-wise, it's practically next door!

[Michael Cain]

But see the article about the editor: they are purportedly NOT using either a pre-programmed list of word+date, or a random choice.

I opened up the JavaScript for the Wordle page at the NYT this morning. No list of solution words, but the list of acceptable guesses (including ytost) is still in it. The code has been minified, so I'm not going to look to see where the code gets the daily solution.

[JanieM]

I know where it is....

No time for stories now, but there's a certain aspect of small town and rural life in Maine (probably everywhere) that means Freedom might as well be on the other side of the moon.

Several years after my son was out of college, I ran into the dad of one of his high school friends. I asked about his kids and he gave me the rundown, including the fact that one of his sons was pretty far away -- in China.

China, Maine, that is.

Freedom is even further away than China.....

We could do a tour of the virtues: Freedom, Hope, Unity, Friendship.... I think there are a couple more....

[Pete]

I opened up the JavaScript for the Wordle page at the NYT this morning. No list of solution words, but the list of acceptable guesses (including ytost) is still in it.

How do you access that? I don't look at source much, but I thought that stuff was pulled from protected libraries anyway. No?

[JanieM]

Liberty, Unity, Union, Harmony, Freedom, Friendship, Industry, Amity, Prospect . . . and Misery.

We'll stop before we get to Misery. :-)

[JanieM]

and Hope!

(Wherever I got that list, they blew it. The quest continues.)

(Gonna stop. I'm punchy, and I didn't even go out last night.)

[Pete]

I know China Lake. I'm not one for "destination" dining, generally speaking. But I am intrigued by the rejuvenation of the town and that they repurposed the old mill as a power-generating plant. I've read Erin's book and I recall walking by the place in Belfast years ago. She's a self-promoter, certainly, but she does seem to be very connected and conscious about the local community. Would not have happened without the benificence of the Grassi family, but I like to think it's generally a good map for the rejuvenation of smaller communities.

[wj]

Taking optimism beyond the bounds of Maine:
https://iiif.library.cofc.edu/iiif/2/36756/full/full/0/default.jpg

I've a fondness for this one because it's a postcard that my little brothers created, back when they were in the postcard business as Hold the Mustard Productions.

[Pete]

That's a lot to take in, but Tranquility, CA is... Fresno?

[CharlesWT]

Eureka, Texas is missing from the map...