Re: ChatGPT for py teaching

Wes Turner <[email protected]> Fri, 24 Mar 2023 16:12:31 -0400
Newsgroups gmane.comp.python.education
Message-ID <CACfEFw87OFQBbYJn+-DzWG1BSRkmUHNRShEroOoLJMZfvDKakw@mail.gmail.com>
--===============7107119619413045032==
Content-Type: multipart/alternative; boundary="0000000000000d87f405f7ab04e9"

--0000000000000d87f405f7ab04e9
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Khanmigo is a new (2023-03-14) Khan Academy tutoring AI:
https://blog.khanacademy.org/harnessing-ai-so-that-all-students-benefit-a-n=
onprofit-approach-for-equal-access/
:

"""
Participants in our limited pilot can use Khanmigo to:

- Get help with math
- Write a story together through back-and-forth idea generation (but
Khanmigo won=E2=80=99t write the story for them!)
- Prep for AP exams
- Practice new vocabulary words
- Learn computer programming
Interview a historical figure like Cleopatra or Jane Austen
- Debate a topic like =E2=80=9CShould schools ban AI?=E2=80=9D

Khanmigo does not, however, give students answers. Nobody learns anything
by being given the answer. Instead, Khanmigo asks questions. Questions are
thought-provoking. Questions are open-ended. And most importantly,
questions lead to learning
"""

What is the Socratic method?
https://en.wikipedia.org/wiki/Socratic_method

Why are LLMs picking random positive integers 42 and 7 most frequently?

On Fri, Mar 24, 2023, 12:20 AM Jurgis Pralgauskis <
[email protected]> wrote:

> I suspect some nice things are comming - see examples of "Socratic tutor"
> :)
>
> https://openai.com/research/gpt-4
>
> 2023-01-06, pn 19:03, Wes Turner <[email protected]> ra=C5=A1=C4=97:
>
>>
>>
>> On Wed, Jan 4, 2023 at 4:34 PM Wes Turner <[email protected]> wrote:
>>
>>> What are the expected limitations of [ChatGPT]?
>>>
>>> What is "Prompt Engineering"?
>>> [Prompt engineering - Wikipedia](
>>> https://en.wikipedia.org/wiki/Prompt_engineering )
>>>
>>> What lessons about technology reliance could you teach, in regards to
>>> Clippy?
>>>
>>> - "What is ChatGPT? Wrong answers only"
>>>   - Human_n: EDGES WITH REASONING
>>>
>>> - "Tell me IDK ("I don't know") when you don't know"
>>>
>>
>> - What are "Truthiness", Confidence Intervals and Error Propagation?
>> - What is Convergence?
>> - What does it mean for algorithmic outputs to converge given additional
>> parametric noise?
>>
>>
>>>
>>> - "How certain are you that that is the correct answer?"
>>>
>>
>> - How does [ChatGPT] handle known-to-be or presumed-to-be unsolved math
>> and physics problems?
>>
>> - "How do we create room-temperature superconductivity?"
>>
>> - "How will planetary orbital trajectories change in the n-body gravity
>> problem if another dense probably interstellar mass passes through our
>> local system?"
>>
>>
>>>
>>> - "Are static analysis code metrics sufficient for Safety Critical code=
?"
>>>
>>
>> - Where in the DevOpSec software development lifecycle should human code
>> review for security best practices and common vulnerabilities and
>> weaknesses?
>>   - Is the [ChatGPT] model trained from *only* Formally Verified code
>> with associated tests?
>>     - Branch and line coverage metrics indicate which tests run which
>> lines of which functions. Code coverage typically implies dynamic analys=
is?
>>
>>
>>>
>>> - "Whose code is this based on?"
>>>
>>> - "Where and when did you learn this?"
>>>
>>
>> - Explainability (XAI)
>> - How can models "Unlearn" or "Learn over" given a sufficient
>> meta-analytic procedure given the information available at that point in
>> spacetime?
>>
>>
>>
>>> - "Why would a US President abstain from using ChatGPT or similar to
>>> fill speeches 'just like what I said before'?"
>>>
>>> #Burgundy
>>>
>>
>> - How can we use [ChatGPT] and other Prompt Engineering approaches to
>> perform Evidence-Based Policy with supporting computational analyses
>> prepared in form for meta-analysis given verification of data quality an=
d
>> experimental controls?
>>
>>
>>>
>>> GPT or similar trained on only Formally-Verified code with associated
>>> tests
>>> and/or e.g. Lean Mathlib, or e.g. the Principia in SymPy & Cirq; that
>>> could probably eliminate my job, but maybe still not teaching
>>>
>>
>> - "Q: ChatGPT etc. trained on mathlib and tests"
>>   https://github.com/leanprover-community/mathlib/issues/17919
>>
>> - "Port the QuantumQ game to Cirq (SymPy (Python))?"
>>   - https://quantumai.google/cirq/start/start
>>     -
>> https://colab.research.google.com/drive/11WGNX8TKOmjpmvJWO7v19gXKoEwIwxy=
w?usp=3Dsharing
>>
>> - "How does [ChatGPT] compare to Critical Thinking, Reasoning, Logic, an=
d
>> Rationality?
>>   https://en.wikipedia.org/wiki/Critical_thinking#Logic_and_rationality
>>
>>
>>
>>> On Wed, Jan 4, 2023, 6:28 AM Christian Mascher <[email protected]=
e>
>>> wrote:
>>>
>>>> Hi,
>>>>
>>>> a student of mine was aware of this chatbot and asked it about a
>>>> class-assignment of his own accord. We program in Java with some extra
>>>> homemade library class used by some schools in our region.
>>>>
>>>> The bot came up with a "solution" which was flawed in several respects=
:
>>>> 1. It used some other (unimported) classes - solution doesn't work and
>>>> doesn't fit the assignment.
>>>> 2. It put all the code into the constructor, a typical (design and
>>>> style) error for students beginning with Java.
>>>>
>>>> When confronted with the problem number one above, it acknowledged the
>>>> fault and produced a different unrelated solution.
>>>>
>>>> Sooo....
>>>>
>>>> I was impressed how well the chatbot simulated a typical clueless huma=
n
>>>> who even thinks he is smart, while his code is basically bullshit.
>>>> (Probably a result of googling forums, where other learners posted the=
ir
>>>> solutions to assignments with the given school library classes.) The b=
ot
>>>> clearly passed the Turing test ;-)
>>>>
>>>> But...
>>>>
>>>> I don't think the interaction was helpful for somebody who is learning
>>>> to program. It is probably less helpful than conversing with other als=
o
>>>> not very knowledgeable students as they are at least reasoning humans.
>>>>
>>>> Talking to the bot might be fun to do in the last lesson before
>>>> christmas or so. Entertaining until you realise the software is
>>>> "simulating" intelligent conversation - not really talking with insigh=
t.
>>>> And that could turn out to be a waste of time.
>>>>
>>>> Happy new year
>>>>
>>>> Christian
>>>>
>>>> Am 03.01.2023 um 04:06 schrieb Jurgis Pralgauskis:
>>>> > Hi, happy NY!
>>>> >
>>>> > ChatGPT can create, fix and explain code
>>>> > https://openai.com/blog/chatgpt/#samples
>>>> > <https://openai.com/blog/chatgpt/#samples>
>>>> >
>>>> > Anyone tried to incorporate it into teaching process?
>>>> > Or have ideas/doubts how it ciuld help?
>>>> >
>>>> > _______________________________________________
>>>> > Edu-sig mailing list -- [email protected]
>>>> > To unsubscribe send an email to [email protected]
>>>> > https://mail.python.org/mailman3/lists/edu-sig.python.org/
>>>> > Member address: [email protected]
>>>> _______________________________________________
>>>> Edu-sig mailing list -- [email protected]
>>>> To unsubscribe send an email to [email protected]
>>>> https://mail.python.org/mailman3/lists/edu-sig.python.org/
>>>> Member address: [email protected]
>>>>
>>>

--0000000000000d87f405f7ab04e9
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"auto"><div dir=3D"auto">Khanmigo is a new (2023-03-14) Khan Aca=
demy tutoring AI:=C2=A0</div><a href=3D"https://blog.khanacademy.org/harnes=
sing-ai-so-that-all-students-benefit-a-nonprofit-approach-for-equal-access/=
">https://blog.khanacademy.org/harnessing-ai-so-that-all-students-benefit-a=
-nonprofit-approach-for-equal-access/</a> :<div dir=3D"auto"><br></div><div=
 dir=3D"auto">&quot;&quot;&quot;</div><div dir=3D"auto">Participants in our=
 limited pilot can use Khanmigo to:<br></div><div dir=3D"auto"><br></div><d=
iv dir=3D"auto">- Get help with math=C2=A0</div><div dir=3D"auto">- Write a=
 story together through back-and-forth idea generation (but Khanmigo won=E2=
=80=99t write the story for them!)</div><div dir=3D"auto">- Prep for AP exa=
ms</div><div dir=3D"auto">- Practice new vocabulary words</div><div dir=3D"=
auto">- Learn computer programming</div><div dir=3D"auto">Interview a histo=
rical figure like Cleopatra or Jane Austen</div><div dir=3D"auto">- Debate =
a topic like =E2=80=9CShould schools ban AI?=E2=80=9D</div><div dir=3D"auto=
"><br></div><div dir=3D"auto">Khanmigo does not, however, give students ans=
wers. Nobody learns anything by being given the answer. Instead, Khanmigo a=
sks questions. Questions are thought-provoking. Questions are open-ended. A=
nd most importantly, questions lead to learning</div><div dir=3D"auto">&quo=
t;&quot;&quot;</div><div dir=3D"auto"><br></div><div dir=3D"auto">What is t=
he Socratic method?=C2=A0</div><div dir=3D"auto"><a href=3D"https://en.wiki=
pedia.org/wiki/Socratic_method">https://en.wikipedia.org/wiki/Socratic_meth=
od</a></div><div dir=3D"auto"><br></div><div dir=3D"auto">Why are LLMs pick=
ing random positive integers 42 and 7 most frequently?</div></div><br><div =
class=3D"gmail_quote"><div dir=3D"ltr" class=3D"gmail_attr">On Fri, Mar 24,=
 2023, 12:20 AM Jurgis Pralgauskis &lt;<a href=3D"mailto:jurgis.pralgauskis=
@gmail.com">[email protected]</a>&gt; wrote:<br></div><blockquot=
e class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc sol=
id;padding-left:1ex"><div dir=3D"auto">I suspect some nice things are commi=
ng - see examples of &quot;Socratic tutor&quot; :)<div dir=3D"auto"><br></d=
iv><div dir=3D"auto"><a href=3D"https://openai.com/research/gpt-4" target=
=3D"_blank" rel=3D"noreferrer">https://openai.com/research/gpt-4</a><br></d=
iv></div><br><div class=3D"gmail_quote"><div dir=3D"ltr" class=3D"gmail_att=
r">2023-01-06, pn 19:03, Wes Turner &lt;<a href=3D"mailto:wes.turner@gmail.=
com" target=3D"_blank" rel=3D"noreferrer">[email protected]</a>&gt; ra=
=C5=A1=C4=97:<br></div><blockquote class=3D"gmail_quote" style=3D"margin:0 =
0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir=3D"ltr"><div=
 dir=3D"ltr"><br></div><br><div class=3D"gmail_quote"><div dir=3D"ltr" clas=
s=3D"gmail_attr">On Wed, Jan 4, 2023 at 4:34 PM Wes Turner &lt;<a href=3D"m=
ailto:[email protected]" rel=3D"noreferrer noreferrer" target=3D"_blank"=
>[email protected]</a>&gt; wrote:<br></div><blockquote class=3D"gmail_qu=
ote" style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,20=
4);padding-left:1ex"><div dir=3D"auto">What are the expected limitations of=
 [ChatGPT]?<div dir=3D"auto"><br></div><div dir=3D"auto">What is &quot;Prom=
pt Engineering&quot;?</div><div dir=3D"auto">[Prompt engineering - Wikipedi=
a]( <a href=3D"https://en.wikipedia.org/wiki/Prompt_engineering" rel=3D"nor=
eferrer noreferrer" target=3D"_blank">https://en.wikipedia.org/wiki/Prompt_=
engineering</a> )<br><div dir=3D"auto"><br></div><div dir=3D"auto">What les=
sons about technology reliance could you teach, in regards to Clippy?</div>=
<div dir=3D"auto"><br></div><div dir=3D"auto">- &quot;What is ChatGPT? Wron=
g answers only&quot;</div><div dir=3D"auto">=C2=A0 - Human_n: EDGES WITH RE=
ASONING</div><div dir=3D"auto"><br></div><div dir=3D"auto">- &quot;Tell me =
IDK (&quot;I don&#39;t know&quot;) when you don&#39;t know&quot;</div></div=
></div></blockquote><div><br></div><div>- What are &quot;Truthiness&quot;, =
Confidence Intervals and Error Propagation?</div><div>- What is Convergence=
?</div><div>- What does it mean for algorithmic outputs to converge given a=
dditional parametric noise?</div><div>=C2=A0</div><blockquote class=3D"gmai=
l_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,20=
4,204);padding-left:1ex"><div dir=3D"auto"><div dir=3D"auto"><div dir=3D"au=
to"><br></div><div dir=3D"auto">- &quot;How certain are you that that is th=
e correct answer?&quot;</div></div></div></blockquote><div><br></div><div>-=
 How does=C2=A0[ChatGPT] handle known-to-be or presumed-to-be unsolved math=
 and physics problems?</div><div><br></div><div>- &quot;How do we create ro=
om-temperature superconductivity?&quot;</div><div><br></div><div>- &quot;Ho=
w will planetary orbital trajectories change in the n-body gravity problem =
if another dense probably interstellar mass passes through our local system=
?&quot;</div><div>=C2=A0</div><blockquote class=3D"gmail_quote" style=3D"ma=
rgin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:=
1ex"><div dir=3D"auto"><div dir=3D"auto"><div dir=3D"auto"><br></div><div d=
ir=3D"auto">- &quot;Are static analysis code metrics sufficient for Safety =
Critical code?&quot;</div></div></div></blockquote><div><br></div><div>- Wh=
ere in the DevOpSec software development lifecycle=C2=A0should human code r=
eview for security best practices and common vulnerabilities and weaknesses=
?</div><div>=C2=A0 - Is the [ChatGPT] model trained from *only* Formally Ve=
rified code with associated tests?</div><div>=C2=A0 =C2=A0 - Branch and lin=
e coverage metrics indicate which tests run which lines of which functions.=
 Code coverage typically implies dynamic analysis?</div><div>=C2=A0</div><b=
lockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-le=
ft:1px solid rgb(204,204,204);padding-left:1ex"><div dir=3D"auto"><div dir=
=3D"auto"><div dir=3D"auto"><br></div><div dir=3D"auto">- &quot;Whose code =
is this based on?&quot;</div><div dir=3D"auto"><br></div><div dir=3D"auto">=
- &quot;Where and when did you learn this?&quot;</div></div></div></blockqu=
ote><div><br></div><div>- Explainability (XAI)</div><div>- How can models &=
quot;Unlearn&quot; or &quot;Learn over&quot; given a sufficient meta-analyt=
ic procedure given the information available at that point in spacetime?</d=
iv><div><br></div><div>=C2=A0</div><blockquote class=3D"gmail_quote" style=
=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding=
-left:1ex"><div dir=3D"auto"><div dir=3D"auto"><div dir=3D"auto"></div><div=
 dir=3D"auto">- &quot;Why would a US President abstain from using ChatGPT o=
r similar to fill speeches &#39;just like what I said before&#39;?&quot;</d=
iv><div dir=3D"auto"><br></div><div dir=3D"auto">#Burgundy</div></div></div=
></blockquote><div><br></div><div>- How can we use [ChatGPT] and other Prom=
pt Engineering approaches to perform Evidence-Based Policy with supporting =
computational analyses prepared in form for meta-analysis given verificatio=
n of data quality and experimental controls?</div><div>=C2=A0</div><blockqu=
ote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left:1px=
 solid rgb(204,204,204);padding-left:1ex"><div dir=3D"auto"><div dir=3D"aut=
o"><div dir=3D"auto"><br></div><div dir=3D"auto">GPT or similar trained on =
only Formally-Verified code with associated tests</div><div dir=3D"auto">an=
d/or e.g. Lean Mathlib, or e.g. the Principia in SymPy &amp; Cirq; that cou=
ld probably eliminate my job, but maybe still not teaching=C2=A0</div></div=
></div></blockquote><div><br></div><div>- &quot;Q: ChatGPT etc. trained on =
mathlib and tests&quot;</div><div>=C2=A0 <a href=3D"https://github.com/lean=
prover-community/mathlib/issues/17919" rel=3D"noreferrer noreferrer" target=
=3D"_blank">https://github.com/leanprover-community/mathlib/issues/17919</a=
></div><div><br></div><div>- &quot;Port the QuantumQ game to Cirq (SymPy (P=
ython))?&quot;</div><div>=C2=A0 -=C2=A0<a href=3D"https://quantumai.google/=
cirq/start/start" rel=3D"noreferrer noreferrer" target=3D"_blank">https://q=
uantumai.google/cirq/start/start</a></div><div>=C2=A0 =C2=A0 -=C2=A0<a href=
=3D"https://colab.research.google.com/drive/11WGNX8TKOmjpmvJWO7v19gXKoEwIwx=
yw?usp=3Dsharing" rel=3D"noreferrer noreferrer" target=3D"_blank">https://c=
olab.research.google.com/drive/11WGNX8TKOmjpmvJWO7v19gXKoEwIwxyw?usp=3Dshar=
ing</a></div><div><br></div><div>- &quot;How does [ChatGPT] compare to Crit=
ical Thinking, Reasoning, Logic, and Rationality?</div><div>=C2=A0=C2=A0<a =
href=3D"https://en.wikipedia.org/wiki/Critical_thinking#Logic_and_rationali=
ty" rel=3D"noreferrer noreferrer" target=3D"_blank">https://en.wikipedia.or=
g/wiki/Critical_thinking#Logic_and_rationality</a></div><div>=C2=A0=C2=A0</=
div><div><br></div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0p=
x 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br><d=
iv class=3D"gmail_quote"><div dir=3D"ltr" class=3D"gmail_attr">On Wed, Jan =
4, 2023, 6:28 AM Christian Mascher &lt;<a href=3D"mailto:christian.mascher@=
gmx.de" rel=3D"noreferrer noreferrer noreferrer" target=3D"_blank">christia=
[email protected]</a>&gt; wrote:<br></div><blockquote class=3D"gmail_quote" =
style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);pa=
dding-left:1ex">Hi,<br>
<br>
a student of mine was aware of this chatbot and asked it about a<br>
class-assignment of his own accord. We program in Java with some extra<br>
homemade library class used by some schools in our region.<br>
<br>
The bot came up with a &quot;solution&quot; which was flawed in several res=
pects:<br>
1. It used some other (unimported) classes - solution doesn&#39;t work and<=
br>
doesn&#39;t fit the assignment.<br>
2. It put all the code into the constructor, a typical (design and<br>
style) error for students beginning with Java.<br>
<br>
When confronted with the problem number one above, it acknowledged the<br>
fault and produced a different unrelated solution.<br>
<br>
Sooo....<br>
<br>
I was impressed how well the chatbot simulated a typical clueless human<br>
who even thinks he is smart, while his code is basically bullshit.<br>
(Probably a result of googling forums, where other learners posted their<br=
>
solutions to assignments with the given school library classes.) The bot<br=
>
clearly passed the Turing test ;-)<br>
<br>
But...<br>
<br>
I don&#39;t think the interaction was helpful for somebody who is learning<=
br>
to program. It is probably less helpful than conversing with other also<br>
not very knowledgeable students as they are at least reasoning humans.<br>
<br>
Talking to the bot might be fun to do in the last lesson before<br>
christmas or so. Entertaining until you realise the software is<br>
&quot;simulating&quot; intelligent conversation - not really talking with i=
nsight.<br>
And that could turn out to be a waste of time.<br>
<br>
Happy new year<br>
<br>
Christian<br>
<br>
Am 03.01.2023 um 04:06 schrieb Jurgis Pralgauskis:<br>
&gt; Hi, happy NY!<br>
&gt;<br>
&gt; ChatGPT can create, fix and explain code<br>
&gt; <a href=3D"https://openai.com/blog/chatgpt/#samples" rel=3D"noreferrer=
 noreferrer noreferrer noreferrer noreferrer" target=3D"_blank">https://ope=
nai.com/blog/chatgpt/#samples</a><br>
&gt; &lt;<a href=3D"https://openai.com/blog/chatgpt/#samples" rel=3D"norefe=
rrer noreferrer noreferrer noreferrer noreferrer" target=3D"_blank">https:/=
/openai.com/blog/chatgpt/#samples</a>&gt;<br>
&gt;<br>
&gt; Anyone tried to incorporate it into teaching process?<br>
&gt; Or have ideas/doubts how it ciuld help?<br>
&gt;<br>
&gt; _______________________________________________<br>
&gt; Edu-sig mailing list -- <a href=3D"mailto:[email protected]" rel=3D"n=
oreferrer noreferrer noreferrer noreferrer" target=3D"_blank">edu-sig@pytho=
n.org</a><br>
&gt; To unsubscribe send an email to <a href=3D"mailto:edu-sig-leave@python=
.org" rel=3D"noreferrer noreferrer noreferrer noreferrer" target=3D"_blank"=
>[email protected]</a><br>
&gt; <a href=3D"https://mail.python.org/mailman3/lists/edu-sig.python.org/"=
 rel=3D"noreferrer noreferrer noreferrer noreferrer noreferrer" target=3D"_=
blank">https://mail.python.org/mailman3/lists/edu-sig.python.org/</a><br>
&gt; Member address: <a href=3D"mailto:[email protected]" rel=3D"nor=
eferrer noreferrer noreferrer noreferrer" target=3D"_blank">christian.masch=
[email protected]</a><br>
_______________________________________________<br>
Edu-sig mailing list -- <a href=3D"mailto:[email protected]" rel=3D"norefe=
rrer noreferrer noreferrer noreferrer" target=3D"_blank">[email protected]=
</a><br>
To unsubscribe send an email to <a href=3D"mailto:[email protected]"=
 rel=3D"noreferrer noreferrer noreferrer noreferrer" target=3D"_blank">edu-=
[email protected]</a><br>
<a href=3D"https://mail.python.org/mailman3/lists/edu-sig.python.org/" rel=
=3D"noreferrer noreferrer noreferrer noreferrer noreferrer" target=3D"_blan=
k">https://mail.python.org/mailman3/lists/edu-sig.python.org/</a><br>
Member address: <a href=3D"mailto:[email protected]" rel=3D"noreferrer n=
oreferrer noreferrer noreferrer" target=3D"_blank">[email protected]</a>=
<br>
</blockquote></div>
</blockquote></div></div>
</blockquote></div>
</blockquote></div>

--0000000000000d87f405f7ab04e9--

--===============7107119619413045032==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Edu-sig mailing list -- [email protected]
To unsubscribe send an email to [email protected]
https://mail.python.org/mailman3/lists/edu-sig.python.org/
Member address: [email protected]

--===============7107119619413045032==--