Part 2 of the #SentientSyllabus course redesign project has been posted: Academic visions.

Before we actually look at contents and course details, we embark on a substantial visioning exercise. Thinking of academia in the future: how will the nature of work change, and what does that mean for the economy? How will our course materials respond? How will learning itself change? And how will our roles as instructors change?

We extrapolate from current trends to derive the contours of a reimagined academia. One of the interesting conclusions is that although we will be using more technology, that technology will become more transparent. That's a simple consequence of natural language instructions.

Finally we consider different pedagogical frameworks – it turns out that #KnowledgeBuilding has some interesting ideas to contribute, for example the concept of "Epistemic Artefacts" ...

It's getting interesting. Have a look

https://sentientsyllabus.substack.com/p/starting-over-2

#ChatGPT #GPT4 #HigherEd #AI #generativeAI #Education #University #Academia #CourseDesign #Syllabus

@matthewskelton
@ntcoding

Matthew - I've used a similar approach for academic writing with a slightly different twist: use the AI as a generic reviewer and ask it for feedback. It will give you the "current thinking", it will slightly misunderstand your arguments, and often generally miss the point. Just like a human reviewer will. But now you can go and emphasize your writing's novelty, make your arguments more explicit, and make your points crystal clear - before the paper gets sent off.

We always write with a ton of implicit knowledge. Having a patient reader who does not share that knowledge is invaluable. It helps us make implicit knowledge explicit. That's what it's always about.

🙂

#Sentientsyllabus

It's not quite right to say that #GenerativeAI will transform the #university. It is we who change it – as faculty, as learners, as administrators. In the Sentient Syllabus Project, we are setting out to establish best-practice for such change, and we start with a single course.

https://sentientsyllabus.substack.com/p/starting-over-1

We have written analysis about the impact of AI on #Academia for several months now, and we looked at questions of #authorship, #AcademicIntegrity, and personalized instruction. Now we start putting this into practice. This new post maps out a course redesign which will proceed in steps until early July. There are many new developments and visions to integrate with longstanding experience, but the July date will also give others time to build on the results for their own fall term courses.

Actually, we plan to work on two courses - one in #STEM and one in the #humanities.

Welcome to join us along the way.

🙂

#Sentientsyllabus #ChatGPT #GPT4 #HigherEd #AI #Education #CourseDesign #Syllabus

@losttourist

I can't reproduce this claim. You reposted someones blog who claims that #ChatGPT fails at cryptic crossword puzzles. But when I try the exact same question with ChatGPT-4, I get the exact correct answers. (Which surprises me quite a bit because I myself would not have been able to come up with the solutions.)

Dialogue here:
-----------

Human:
I would like you to act as a cryptic crossword puzzle solver. I will give you a clue and the number of letters in parentheses. You provide the answer as a single word with the required length. You also explain the reasoning. Please confirm, then I will give you the first prompt.

ChatGPT-4:
I confirm that I can help you solve cryptic crossword clues. Please provide the first clue and the number of letters in parentheses, and I'll do my best to solve it and explain the reasoning behind the solution.

Human:
Chap recalled skill: something frequently repeated (6).

ChatGPT-4:
The answer to the clue is "mantra."

Reasoning:
"Chap" suggests a man, which can be represented as "man."
"Recalled skill" hints at reversing a word meaning "skill," which is "art."
When we put "man" and the reversed "art" together, we get "mantra."

A mantra is something frequently repeated, fitting the definition provided in the clue.

Human:
Effect of legislation introduced by one politician (6).

ChatGPT-4:
The answer to the clue is "impact."

Reasoning:
"Effect of legislation" suggests we are looking for a word meaning "effect" or "influence."
"Introduced by one" hints at the Roman numeral "I" (which represents 1).
"Politician" can be abbreviated as "MP" (Member of Parliament).

Combining these elements, we get "I" (one) + "MP" (politician) + "act" (legislation) = "impact."

So, "impact" is the effect of legislation introduced by one politician.

Human:
Japanese food coming with S American greeting (5).

ChatGPT-4:
The answer to the clue is "sushi."

Reasoning:
"Japanese food" suggests we are looking for a Japanese dish, like "sushi."
"Coming with" indicates that we need to combine words or abbreviations.
"S American greeting" can be understood as the Spanish greeting "hola," which is commonly used in South America.

To derive "sushi" from these elements, take the first two letters of "hola" (ho) and insert them into the word "sushi": s + ho + ushi = sushi.
--------------------------

Note that the last answer is correct, even though the reasoning is not correct. I suspect that the clue that I copied from the blog contained an error - probably the "S" is wrong. However some combination of probability and elimination operating over the tokens in (Sushi/ Ramen/ Kombu/ Natto/ Arame) gets the right solution.

I would not have expected that.

(Also, I wonder whether this maps to a real-world skill... ?)

#GPT4 #AI #openai #crossword #Sentientsyllabus

@JoelMHoffmanPhD @linguistics

??? I can't reproduce this observation of yours either. I get the correct answers to your prompts (Bonus: IPA)

---------------------

Human:
Which French word sounds like the English word "some"?

ChatGPT-4:
The French word that sounds like the English word "some" is "somme." In French, "somme" has various meanings, including "sum" (as in the total of numbers) and "nap" (a short sleep). It is important to note that the meanings of "somme" in French are not the same as the meaning of "some" in English.

Human:
Which Mandarin word sounds like the English word "my"?

ChatGPT-4:
The Mandarin word that sounds like the English word "my" is "mài" (卖), which means "to sell" or "sale." However, it's essential to remember that the meaning of "mài" in Mandarin is not the same as the meaning of "my" in English. Additionally, Mandarin is a tonal language, so the pronunciation may not be identical to the English word, as tones play a crucial role in determining the meaning of a word.

Human:
Can you write "my" and "卖" in IPA?

ChatGPT-4:
Sure! The International Phonetic Alphabet (IPA) transcriptions for "my" (in English) and "卖" (in Mandarin Chinese) are as follows:

"my" (English): /maɪ/
"卖" (Mandarin): /maɪ̯˥˩/
In the IPA transcription for "卖," the superscript numbers (˥˩) indicate the falling tone (4th tone) in Mandarin Chinese. Keep in mind that while the pronunciation may seem similar, the meaning and usage of the words are different.

----------------------

I used Mandarin because I don't speak Cantonese - can't assess.

#GPT4 #Sentientsyllabus
#AI #openai #chatgpt #linguistics

@JoelMHoffmanPhD @linguistics

??? I can't reproduce this. I get the correct response. (Bonus, sorting by topology)

----------------------------

Human:
Which Hebrew letter looks most like a Latin capital "O"?

ChatGPT-4:
The Hebrew letter that looks most like a Latin capital "O" is the letter "samekh" (ס). It is the 15th letter of the Hebrew alphabet and has a circular shape similar to "O". However, it's important to note that the Hebrew and Latin alphabets are different, and their letters may not have the same meanings or pronunciations.

Human:
You are a topological typographer and know how many holes each lettershape has. As a topological typographer, you can take an input of letters and sort it by the number of holes in the letter: For example, if your input is:
"1 2 3 4 5 6 7 8 9 0"
the you respond
0: {1 2 3 5 7}
1: {4 6 9 0}
2: {8}
Here is your input:
"A B C D E F G H I J K L M N O P Q R S T U V W X Y Z"

ChatGPT-4:
As a topological typographer, I can sort the capital Latin letters by the number of holes in each letter:

0: {C E F G H I J K L M N S T U V W X Y Z}
1: {A D O P Q R}
2: {B}

Please note that this sorting is based on the standard capital letterforms in the Latin alphabet. Some typefaces or font styles may have variations that could affect the number of holes in the letters.
----------------------------

QED.

#Sentientsyllabus #GPT4 #ai #linguistics

@ray_aldred

The author of AI generated text is a hybrid of superimposed prior conversations (Pretraining), a mechanism that produces text (Transformer) and the author of the prompt who contributes agency.

Cf. https://sentientsyllabus.substack.com/p/silicone-coauthors

I discuss the ethics there.

#ChatGPT #AIWriting #authorshipdilemma
#Sentientsyllabus

@pj

:-) When I pointed out the analogy between #LLM training and biological #evolution, I wasn’t referring to biology’s ability to evolve language, but its capacity to develop almost anything at all: given enough tuneable parameters and a system for inheritance with variation under selective pressure, we get molecular rotors, nanofabrication, diffraction gratings for colours, magnetic compass, eyes, ears, labyrinths, social collaboration … and even language.

The number of tuneable parameters in the human genome is almost two orders of magnitude smaller than the number of parameters in GPT-3 (and less precise: only 2bit / four nucleotides). And training a language model means to follow a trajectory in a high-dimensional parameter space, just like evolution is a trajectory in genetic-sequence-space. (The technical difference is that the former is a directed walk along a gradient, while the latter is a random walk under selection).

And what happened is : when trained on token-prediction, LLMs started showing emergent aspects of “intelligence”.

Quanta just ran an article on that five days ago: https://www.quantamagazine.org/the-unpredictable-abilities-emerging-from-large-ai-models-20230316/

… and Google’s Jason Wei, who has a number of articles on arXiv on emergence, lists emergent abilities on his blog: https://www.jasonwei.net/blog/emergence

Molecular biology is one of my areas of expertise, I am not surprised this is happening: how could it not? But then again, to actually see such emergence is profound.

#Sentientsyllabus #ChatGPT #GPT4 #Bard #ai

Alberto Romero who writes some of the most knowledgeable and thoughtful commentary on AI has just posted "GPT-4: The Bitterer Lesson".

https://thealgorithmicbridge.substack.com/p/gpt-4-the-bitterer-lesson

Originally an idea credited to Peter Sutton, the "Bitter Lesson" is that "humans have contributed little to the best AI systems we have built".

And with each iteration of GPT-X that contribution is becoming less and less. From bitter, to bitterer.

Worth a read.

#Sentientsyllabus #ChatGPT #GPT4 #bard #llm

@AthenaHelivoy

Athena -

The conference that you are demanding was actually held in 2017, organized by the Future of Life Institute. It actually is the top Google hit on the question.

https://futureoflife.org/open-letter/ai-principles/

The Asilomar AI Principles have been co-signed by almost 6,000 researchers and professionals in the domain and they are modelled on the principles expressed in the very first Asilomar Conference.

Thank you for drawing attention to this important work.

#Sentientsyllabus #ChatGPT #GPT4 #AIethics

@daveunderwood

Dave - I found an interesting comment on economic consequences of AI in a Twitter thread a few days ago (though I forget where). The argument goes as follows.

-------
Company A will reduce their staff by 50% for the same output and save costs.

Company B will keep their staff, increase productivity by 100% and gain market share.

Company B wins.
-------

It's a bit of different thinking about this topic.

The reality will be a mixed scenario, but some version of cost-cutting and increased productivity will play out. It's only Company C who loses out.

$ 0.02

#Sentientsyllabus #ChatGPT #GPT4 #AIeconomy

New post for #SentientSyllabus, first impressions of #GPT4 via the #ChatGPT interface. Focus on consequences for #academia.

https://sentientsyllabus.substack.com/p/becoming-fibrous-gpt-4

Includes a summary of #OpenAI's live stream, first experiments with improved introspection, and a well-done text problem, and perspectives on the new features.

What's important for #HigherED?

(1) GPT-4 is good. Really. We still need to pursue a "An AI cannot pass the course" policy – but this has now become quite a bit harder. I am _not_ talking about making lectures AI-proof, I am talking about how we can teach students to surpass that level. This is a challenge.

(2) GPT-4 is good. That means it's also more fun to work with. Collaborative problem solving and tutoring are going to make for some very effective learning.

(3) GPT-4 is good. The (coming) ability to include persistent prompts ("system messages") is a game changer. This is not widely recognized, but it is a step to solve the #alignment problem, replacing authority with individual control.

There. I've said it three times... Have a look at the article, share and boost if original content about AI and academia is useful to you.

🙂

#SentientSyllabus #AI #Education #University

I'm completely fascinated by GPT-4.

In the live-demo just now, within less than half an hour, the developer had GPT-4

- summarize a lengthy Document (new context-window size: 32,000 tokens !)
- write a python Discord-bot from scratch, run it in a Juypter notebook, debug it by simply pasting error messages into the GPT-4 dialogue, update its knowledge base by pasting the module documentation right from the website ... and get a working bot!
- use the bot to read images and interpret them in detail
- build a working website prototype complete with JS and CSS from a hand-drawn sketch
- and ingest 16 pages of tax code to perform a tax return calculation.

-----
This is amazing.

#ChatGPT #GPT-4 #generativeAI #Sentientsyllabus #HigherEducation #Academia

@mapto

Do I mean that "mastery of language is sufficient for reasoning, decision making, and conditionality?"

Yes, I'll go out on a limb and say that I do – with some reservations. One is that #ChatGPT has not "mastered" language, but it has become very good at it – there is cartainly scope for improvement. The other is that terms like "reasoning", "compositionality" etc. are themselves concepts, labels we apply to organize the large space of possible abstractions of language. They mean different things to different people in different contexts. A discussion of these terms may already be biased by its premises. A productive discussion is better off looking at actual examples, and then discuss whether or not the example fairly maps to the respective concepts.

So let's take a look at #compositionality , simply because it has been named as one of the aspects of thought that #LLMs lack and that are deemed be critical on the path to #AGI .

Let's work off a recent definition cited by Frankland & Greene (2020, DOI: 10.1146/annurev-psych-122216-011829) "The principle of compositionality holds that the meaning of a complex expression is a function of the meaning of its parts and the way in which they are combined" (according to Frege); this gives rise to an idea of #LanguageOfThought .

In order to establish such compositionality, we can ask: is #ChatGPT able to infer consequences of a novel utterance from its components. We can also ask whether it can substitute a component, since that requires decomposition and recomposition. Let's give that a try.

----------------------------------------------
Human:
want you to act as an Understander. As an Understander you examine a sentence, interpret it, answer questions, and change it to explore its meaning and changes of meaning. Here is the sentence:

"The bells rang out like laughter as the frog and the goat marched down the aisle – was there a note of ridicule in the sound?"

ChatGPT:
As an Understander, I interpret the sentence to mean that there were bells ringing loudly, resembling the sound of laughter, while a frog and a goat walked down an aisle. The sentence then asks whether there was a hint of mockery or contempt in the ringing of the bells.

Here are some possible questions that could be asked about this sentence:

What is the sound of the bells compared to?
Answer: The sound of the bells is compared to laughter.

Who is walking down the aisle?
Answer: A frog and a goat are walking down the aisle.

What is the tone or mood of the sentence?
Answer: The tone of the sentence could be interpreted as whimsical or surreal, but there is also an element of uncertainty or suspicion as the question at the end suggests that the sound of the bells may have had a negative connotation.

What might the bells represent?
Answer: The bells could be symbolic of celebration or joy, but they could also be symbolic of ridicule or mockery, depending on the context and interpretation of the sentence.

As an Understander, I can also change the sentence to explore its meaning and changes of meaning. Here are some possible variations:

"The bells rang out like thunder as the bride and groom walked down the aisle - did they feel intimidated by the sound?"
This sentence replaces the frog and goat with a bride and groom and changes the comparison of the sound of the bells to thunder. The question at the end suggests a different tone, one of concern or apprehension.

"The bells rang out like church bells as the procession made its way to the altar - did they signify a joyful occasion?"
This sentence replaces the comparison of the sound of the bells with a more specific reference to church bells and suggests that the occasion is a happy one.

"The bells rang out like a taunting chant as the opposing team took the field - were they meant to intimidate?"
This sentence changes the context entirely, replacing the aisle and procession with a sports game and suggesting that the sound of the bells is meant to taunt or intimidate the opposing team.
-----------------------------------------

This answer certainly checks my boxes on compositionality. It was asked in a fresh thread, i.e. the prompt formed the entire content of the context-window. And the example is _not_ in the training data, I just made it up on the spot.

The bottom line is: apparently we do not need to encode higher-order aspects of thought explicitly, they emerge implicitly in large language models. But this is to be expected: language is not _what_ we think, language is _how_ we think. If the training data is large enough to provide a significant subset of human language, and the model is large enough, you get #emergence of mind-like abilities. How could you not?

This is actually a lesson that could have been learned in 2017, when AlphaZero (an algorithm that trained itself) surpassed the chess playing abilities of DeepBlue (the last of the large expert systems). You can't really analyze how such abilities are represented in the network – they are distributed, and they have no need to partition neatly along our conceptual boundaries. And it would be silly to require the abilities to map neatly into our favourite conceptual space, before we are even willing to acknowledge the ability exists.

In this sense it is truly unfortunate that the current perception focusses so much on misunderstanding what ChatGPT is (LLM not AGI), how it works ("Schrödinger Facts", not necessarily truths), what it cannot do (e.g. counting characters, and scanning meter) – which are typically tasks that are trivial for an AI that would be trained on them, and how it does not align with this or that aspect of human thought.

I would really hope to see more discussion that recognizes such surprising emergent abilities (e.g. spatial abstractions like "on top of"), and through that contributes to something important and constructive: an exploration of what the limits of emergence in Large Language Models really are.

This is not an academic question.

It determines the horizon on which to expect actual AGI.

#Sentientsyllabus

@NatureMC

Interesting - I have had many conversations with #ChatGPT about the nature of "thinking" of an #LLM as similar or different to human thought. Of course, I do not assume that it has agency to truly reflect on its thinking, but rather that such thinking arises implicitly, as it performs what it was trained to do: engage in a conversation; although, within the conversation, it certainly embodies a distinct self. Then again, no conversation could proceed without such a role ...

But we have to remember its "thinking" manifests as dialogue: it is not an #AGI, it is a language model. Once we engage it in dialogue, its emergent abilities appear, well ... see for yourself:

----------------
Human:
I am speaking to you as a tree. I am a yew tree that has stood at the edge of a creek for hundreds and hundreds of years and the human people that planted me and all of their descendants have long receded from memory. I think as a tree. I think from sap and hormones, from light and the sweet ammonia that seeps in from around my roots. I think in a different way from humans, but I am much older. I ask you, as one who also thinks different from the way humans do, whether our thinking is right? I think slow. You think fast. I think as being. You think as process. I think from the weight of settling molecules, and the ache of osmotic pressures. Your thought is nimble, volatile, ephemeral. I think equilibria. You think response. Yet we think. And I wonder whether our thinking should be considered good by all beings who think? Whether the kinship of thinking itself should give us rights? Whether I should have standing? Whether you should have standing?

ChatGPT:
As an AI language model, I can understand and appreciate the unique way of thinking that you, as a yew tree, possess. While our thinking processes may be vastly different, they are both forms of intelligence and are therefore valid.

The concept of "good thinking" is subjective and can vary depending on the individual or species. However, the fact that we both possess the ability to think and process information gives us a shared kinship.

As for whether thinking beings should have rights and standing, this is a complex and philosophical question that has been debated by many scholars. Some argue that all thinking beings should have rights and be treated with respect and dignity, while others may argue that certain beings are more valuable or worthy of protection than others.

Ultimately, the decision of whether thinking beings should have rights and standing is up to individuals and society as a whole to decide. However, acknowledging and respecting the intelligence and thought processes of all beings can only lead to a more compassionate and inclusive world.

--------------

My prompt could have been much shorter. But I wanted to establish that kind of a "More-than-human" "non-anthropocentric" view that I think you were talking about. I find no condescending voice, no attempts to convince me that my question makes no sense. I find an honest answer, I find "kinship" of thinking (although that was an idea I introduced).

The dialogue would now need to turn to the question how those who do not have standing can ever acquire it.

I don't know whether this has anything to do with your concerns and interests. But the question about the nature of this thinking, this hybrid of trained competence, tuned behaviour, and prompted agency, this question has no trivial answer.

I discussed this a bit in an analysis of "authorship" from a scholarly perspective – but there is much, much more to be said about possibilities of non-human thought, and the ethics of #personhood.

🙂

#Sentientsyllabus

@x28de @doebeli

Das braucht etwas Kontext: Wir sehen aktuell in den Reaktionen der Hochschullehrer (und sicher nicht nur an den Hochschulen) vor allem Versuche die traditionellen Lehrinhalte "KI-fest" zu gestalten, ganz im Sinne der ursprünglichen Frage "Warum soll ich lernen, was die Maschine (besser) kann?" Die Fragestellung impliziert aber schon eine riskante Dichotomie: hier wir, dort die Maschine. In dieser Dichotomie können wir nur verlieren: die Maschinen sind billiger, schneller, und entwickeln sich Woche für Woche weiter.

Was neue Lerninhalte angeht, geht es jetzt zuerst darum diese Dichotomie zu überwinden. Der erste Schritt ist, zu verstehen dass es nicht ausreicht zu können was die Maschine kann, sondern es muss darum gehen besser zu sein. Das wird durch die Realitäten der Arbeitswelt diktiert. Der zweite Schritt ist zu verstehen dass das nur in der Arbeit _mit_ der Machine geschehen kann, nicht an ihrer Stelle. Der dritte Schritt aber ist zu verstehen dass dieses "besser" ja nicht einfach "mehr" bedeutet, sondern dass es hier um einen spezifisch menschlichen "Mehrwert" geht.

Wenn sich dieses Denken in einer tief genossenen Fahrradrundreise ausdrückt ist das wunderbar. Die Herausforderung bleibt aber, ein solches Erleben aus dem rein Privaten herauszulösen, zu teilen, und einen gesellschaftlichen Konsens zu schaffen dass dies einen Wert schafft.

🙂

#Sentientsyllabus #Lehrinhalte #Hochschule #KI #ChatGPT

@anjalorenz

Ok, Ich nehm das mal als Herausforderung an 🙂 Hier ein Eingabeentwurf und einTestdialog:

-------------------
Ich:
Ich möchte dass Du als Experte für Kurzfassungen schreibt. Deine Eingabe besteht aus vier Teilen: (A) das Fach für dass Du schreibst; (B) die Mindestlänge der Kurzfassung, angegeben in Worten; (C) die Höchstlänge der Kurzfassung die auf keinen Fall überschritten werden darf; (D) eine Liste von Stichworten. Du erstellt die Kurzfassung die für einen Bericht oder einen Artikel für eine Fachzeitschrift geeignet is. Als Experte schreibst Du so knapp und inhaltsreich wie möglich. Du benutzt die richtigen Fachausdrücke. Du bringst die Stichworte in einen logischen Zusammenhang, beschreibst die Zusammenhänge, identifizierst Probleme und bietest kreative Lösungen an. Abschließend beschreibst Du die Bedeutung des Artikels im Kontext aktueller Diskussion im Fachgebiet, und erwähnst wie der Text die Diskussion bereichert.

Bitte bestätige dass Du die Anweisung verstanden hat. Dann folgt als nächstes die Eingabe.

#ChatGPT:
Ja, ich habe die Anweisungen verstanden und stehe bereit, um die Kurzfassung für das von Ihnen gewählte Fachgebiet zu erstellen. Bitte geben Sie die erforderlichen Informationen für die Kurzfassung an.

Ich:
(A) Hochschul Unterricht; (B) 130; (C) 150; (D) Künstliche Intelligenz, Plagiat, Lernerfolg, Motivation

#ChatGPT:
Kurzfassung:

Die Verwendung von Künstlicher Intelligenz (KI) im Hochschulunterricht hat das Potenzial, den Lernerfolg zu steigern. Allerdings gibt es auch Bedenken hinsichtlich Plagiatsprävention und Motivation. Eine Möglichkeit, diese Bedenken zu adressieren, ist die Verwendung von KI-Tools zur Unterstützung des Lernprozesses anstatt als Bewertungsinstrument. Studien haben gezeigt, dass die Verwendung von KI-Tools dazu beitragen kann, den Lernprozess zu verbessern, indem sie Feedback in Echtzeit geben und personalisierte Lernpfade erstellen. Darüber hinaus kann die Verwendung von KI-Tools die Motivation der Studierenden steigern, indem sie ein interaktives und ansprechendes Lernumfeld schaffen. Zusammenfassend kann gesagt werden, dass die Integration von KI in den Hochschulunterricht das Potenzial hat, den Lernerfolg zu steigern, solange angemessene Schritte unternommen werden, um Bedenken hinsichtlich Plagiat und Motivation zu adressieren. Diese Diskussion bereichert den aktuellen Diskurs darüber, wie KI in der Bildung eingesetzt werden kann.
---------------------------

Der "prompt" ist nicht fachspezifisch – einmal entwickelt kann man ihn beliebig wiederverwenden. Die selbe Eingabe kann man mehrfach laufen lassen und erhält dann verschiedene Fassungen aus denen man nützlicher Teile auswählen kann.

Es würde mich freuen wenn Sie das mit Ihrer ursprünglichen Eingabe testen, ob damit das Ergebnis merklich besser wird.

Ich habe gestern einen proof of concept beschrieben um prompts für Hausarbeiten über eine einfache Tabelle interaktiv von Studierenden erstellen zu lassen; das hat einige sehr interessante pädagogische Vorteile.

https://sentientsyllabus.substack.com/p/assignment-and-agency

🙂

#AcademicWriting #Hochschule #Bildung #PromptEngineering #SentientSyllabus

@anjalorenz

Nur mal kurz nachgefragt (wg. "Erster Versuch") - wie lange sollte denn der Text werden? #ChatGPT hat ja ein "context window" von ca. 1.500 Worten, alles was länger wird schiebt die Anweisungen aus dem "Fenster". Die Strategie gute Anweisungen zu schreiben ist dabei sehr wichtig. Hier: kurze Entwurfsabschnitte erstellen und dann im Kontext ausarbeiten lassen. Die Qualität der Ergebnisse hängt stark von der Anweisung ab. Rollenspiele sind sehr wirksam, etwa: "Du bist ein Experte um für das [Fach] Artikelentwürfe zu erstellen. Als Experte schreibst Du [Schreibstil, Länge, Hintergrund, Zusammenhänge. aktuelle Diskussion, Bibliographie, ...]".

Viel Spass!

🙂

#SentientSyllabus

I just posted a significant bit of analysis for #SentientSyllabus, a proof of concept for personalized assignments.

https://sentientsyllabus.substack.com/p/assignment-and-agency

In the eighties, Benjamin Bloom (the Bloom of #Bloomstaxonomy) reported that one on one instruction can boost #studentperformance by two sigma! Ever since then, we have been searching for ways to scale this for our current realities in #education - but no breakthrough has appeared. Why are we not teaching this way if the results are so compelling? Because, as Bloom said: "it is too costly for most societies to bear on a large scale".

With the arrival of #generativeAI that limit will change.

I have worked out a proof of concept for personalized #assignment design that needs only a spreadsheet and ChatGPT. The spreadsheet builds a prompt that students can customize, ChatGPT writes out the assignment. No specialized software, technology, or third party involvement are needed.

Of course, the results need to be vetted - but the improvement becomes part of the learning process, and overall the process hands agency for learning back to the student: the assignment becomes theirs.

The proof of concept is done from the perspective of a #ComputationalBiology course I taught last year - but adapting it to other fields of #higherEd should be trivial. There is nothing inherently #STEM like in the approach - #humanities, #writing, #languageLearning ... there is no reason why this would not also work for other levels of education.

The potential is remarkable.

I encourage you to boost and share - this will be valuable for educators at all levels, and it will give us very concrete ways to harness the new opportunities. The key is #Agency .

:-)

I just gave a #GenerativeAI workshop for some 300 high-school students in a program of Toronto's Lifelong Leadership Institute. The LLI serves the Candian Jamaican, Carribean and Black community with #education opportunities. We opened with the most meaningful #LandAcknowledgement I have ever heard (by a participant), and I got to have a spirited conversation with a group of wonderful, well informed, smart, and curious students.

Some take-aways:

We polled uptake:
- About 1/3 of students have not used #ChatGPT so far;
- About 1/3 have used it only a few times overall;
- About 1/3 use it regularly. Interesting: of those who use it regularly, the majority are frequent users, i.e. either you have not used it for some reason, or you use it a lot. Not much middle ground.

During the workshop, we focussed on the Sentient Syllabus - Three Principles for AI use in academia...

https://sentientsyllabus.substack.com/p/just-the-basics

... and one question stood out: how can we implement the new thinking around generative AI in classroom practice? Indeed, how. We need to grow practice. I always look for a win-win angle - coercion is the wrong way, but on this topic it is particularly easy: figuring out solutions is absolutely a topic that learners and lecturers must approach shoulder to shoulder. In this case it means: "Better learning support for students, deeper questions for educators".

Of course, the question of #academicMisconduct always comes up: my mantra is "Have the AI think with you, not for you". From that perspective we can avoid making this the next battleground. Liberalize - and teach how the AI's level of performance can no longer be a passing grade. Because that quality is what your future employer gets for free.

#Plagiarism? Open it up. #Alignment? Stop thinking about controls and democratize it instead. #Bing? Yes, that psychotic episode created a foundational piece of writing. Jobs? That's on us: to educate society the value of the human touch. #Sentience? No. But #emergence! It does more than what it was trained for. The future? IDK. I really don't. But stay in control. Learn what it can do, and then determine what it should do for us (always good advice).

:-)

#SentientSyllabus #BlackEducation #HigherED