Boris Steipe @boris_steipe@qoto.org

#ChatGPT - How much is too much?

As far as #HigerEd is concerned, the answer is simple: "Assistance from an #AI system is too much when it interferes with the educational objectives, or the assessment of a submitted work."

But really, there is nothing simple here: this question goes to the core of what we mean by "educational objectives", what is the "work" that we are assessing, and how we are assessing in the first place.

I unravel this in the latest post at the #SentientSyllabus Project" - it's a bit of a deep dive, before we come up for air again. In the end, it's all about #joy .

https://sentientsyllabus.substack.com/p/how-much-is-too-much

#Education #University #Academia #syllabus

I just came up with a use of #ChatGPT that promises to be a huge time-saver: reformatting of bibliographies. For reasons, I never follow the standard styles when I write. Of course editors usually insist on whatever. So here's ChatGPT:

Human: Please reformat the following reference in MLA style:

Alster, Bendt (1973). “An Aspect of ‘Enmerkar and the Lord of Aratta’”. Revue d'Assyriologie et d'archéologie orientale 67(2): 101–110.

ChatGPT:
Alster, Bendt. "An Aspect of 'Enmerkar and the Lord of Aratta'." Revue d'Assyriologie et d'archéologie orientale 67, no. 2 (1973): 101-110.

Human:
Now give me a bibtex for that.

ChatGPT:
Here is a BibTeX entry for the reference you provided:

@article{alster1973aspect,
title={An Aspect of 'Enmerkar and the Lord of Aratta'},
author={Alster, Bendt},
journal={Revue d'Assyriologie et d'archéologie orientale},
volume={67},
number={2},
pages={101--110},
year={1973}
}

... that looks correct to me – of course it will need proofreading, but it looks like it will save a lot of pain.

🙂

#SentientSyllabus #ChatGPT

Reacting to news posted today by @abcxyz @donwatkins @techhelpkb @johnew

---
While we were busy thinking things – it appears that the NYC Department of Education is embarking on a fascinating experiment with its staff and students https://www.zdnet.com/article/chatgpt-was-just-blocked-by-the-biggest-us-school-district-heres-why/

We will learn a lot from this.

For educators who are more convinced by the alternative, we have resources at the Sentient Syllabus Project http://sentientsyllabus.org

#SentientSyllabus #ChatGPT #AI #Education #HigherEd #University #Academia #syllabus

Just finished a number of updates of our resource files at the Sentient Syllabus Project – summaries posted at https://sentientsyllabus.substack.com/p/resource-updates-2023-01-05. In brief: New sections on "Critique and Improvement" and "Personalized Tutoring" in the Course Activities file; most writing went into "Understanding AI Issues": training data and process, the Sysiphus work of plagiarism detection (hint: the tools are unlikely to work); first perspectives on energy use, machine use for better training - and the resulting "Kurzweilian" acceleration.

#SentientSyllabus #ChatGPT #AI #Education #HigherEd #University #Academia #syllabus

ChatGPT's Achilles Heel

I just posted a discussion of ChatGPT's major weakness for the Sentient Syllabus Project: https://sentientsyllabus.substack.com/p/chatgpts-achilles-heel

It falls prey to its "Schrödinger Facts".

In a nutshell: ask the AI for sources - and then check whether they actually exist. They usually don't. Requests for specific, provable sources turn out to be ChatGPT’s achilles heel.

That's a big deal: (a) we can (and should) always require students to attribute ideas anyway, and chasing down the source of a ChatGPT claim may be more work than working from an actual source; (b) ChatGPTs information is not useless though - and can be very valuable to point to the right direction; (c) while we become masters in attribution, the collaboration benefits in other ways, and the end result is improved.

Find our resources on academia and the new AI at https://sentientsyllabus.substack.com and on http://sentientsyllabus.org

... and share this information to whoever might find it useful.

#SentientSyllabus #ChatGPT #AI #Education #HigherEd #University #Academia #syllabus

Three principles for the academy in the era of digital thought:

1: An AI cannot pass a course.

2: AI contributions must be attributed and true.

3: AI use should be open and documented.

I explain why in our latest post for the Sentient Syllabus Project. Have a look at https://sentientsyllabus.substack.com

#SentientSyllabus #ChatGPT #AI #Education #HigherEd #University #Academia #syllabus

The Sentient Syllabus Project
Charting a course for academia in the era of digital thought.
--

I've been really busy over the last days rolling this out: the large-scale availability of literate AI has imploded the academy as we know it. We need to re-orient. How? I founded The Sentient Syllabus Project to share concrete, practicable advice. Check it out at http://sentientsyllabus.org and at https://sentientsyllabus.substack.com/p/the-sentient-syllabus-project

Most importantly: this includes text samples how to start re-thinking and adapting our winter-term syllabi by next week. This is needed _now_. Drop in, have a look, and if you know someone who might benefit please share.

#SentientSyllabus #ChatGPT #AI #Education #HigherEd #University #Academia #syllabus

"A beginning is the time for taking the most delicate care that the balances are correct."

(Frank Herbert, Dune - 1965)
--

I was a teenager when I first read Dune, waiting in the queues of the Stubai glacier ski-lifts, in Austria. At the top of the glacier, a short hike would bring you to the saddle and the view from there soars over an untouched snowy plain, beckoning, sparkling, dipping into the Windach Valley high above Sölden, and the view leaps across the slope and continues all the way to the blue peaks of Italy's Dolomites that make the horizon. I stuck my skis in a drift, sat on a heap of scree, chewed on an apple and read.

--

So this is a beginning. Hello, Mastodon. Are the balances correct? The thing is, one cannot know that, at the beginning. Such knowing is for the end. Until then, there is a path. Let's see where it leads to.

In lieu of an #introduction just tags: #Bioinformatics and #ComputationalBiology, programming and teaching #R, #DataScience, #Complexity and #SelfOrganization and #UofT ... but also #MolecularLinguistics and more recent published work in #PhilosophyOfArt, #ConfucianEthics and #JapaneseAesthetics - jointly with @yi_chen .