Add news
March 2010 April 2010 May 2010 June 2010 July 2010
August 2010
September 2010 October 2010 November 2010 December 2010 January 2011 February 2011 March 2011 April 2011 May 2011 June 2011 July 2011 August 2011 September 2011 October 2011 November 2011 December 2011 January 2012 February 2012 March 2012 April 2012 May 2012 June 2012 July 2012 August 2012 September 2012 October 2012 November 2012 December 2012 January 2013 February 2013 March 2013 April 2013 May 2013 June 2013 July 2013 August 2013 September 2013 October 2013 November 2013 December 2013 January 2014 February 2014 March 2014 April 2014 May 2014 June 2014 July 2014 August 2014 September 2014 October 2014 November 2014 December 2014 January 2015 February 2015 March 2015 April 2015 May 2015 June 2015 July 2015 August 2015 September 2015 October 2015 November 2015 December 2015 January 2016 February 2016 March 2016 April 2016 May 2016 June 2016 July 2016 August 2016 September 2016 October 2016 November 2016 December 2016 January 2017 February 2017 March 2017 April 2017 May 2017 June 2017 July 2017 August 2017 September 2017 October 2017 November 2017 December 2017 January 2018 February 2018 March 2018 April 2018 May 2018 June 2018 July 2018 August 2018 September 2018 October 2018 November 2018 December 2018 January 2019 February 2019 March 2019 April 2019 May 2019 June 2019 July 2019 August 2019 September 2019 October 2019 November 2019 December 2019 January 2020 February 2020 March 2020 April 2020 May 2020 June 2020 July 2020 August 2020 September 2020 October 2020 November 2020 December 2020 January 2021 February 2021 March 2021 April 2021 May 2021 June 2021 July 2021 August 2021 September 2021 October 2021 November 2021 December 2021 January 2022 February 2022 March 2022 April 2022 May 2022 June 2022 July 2022 August 2022 September 2022 October 2022 November 2022 December 2022 January 2023 February 2023 March 2023 April 2023 May 2023 June 2023 July 2023 August 2023 September 2023 October 2023 November 2023 December 2023 January 2024 February 2024 March 2024 April 2024 May 2024 June 2024 July 2024 August 2024 September 2024 October 2024 November 2024 December 2024 January 2025 February 2025 March 2025 April 2025 May 2025 June 2025 July 2025 August 2025 September 2025 October 2025 November 2025 December 2025
1 2 3 4 5 6 7 8 9 10 11 12 13 14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
News Every Day |

Of ChatGPT’s Sense of Humor

Over more than two years, I have occasionally discussed my experience with AI bots—mainly ChatGPT, which I have also used for the featured images of my posts. But except in “TikTok, Godot, Absurd Politics, and Knaves,” I have not directly addressed this bot’s sense of humor, which has become rather impressive. Let me give other recent examples.

The first one is related to my post of last week titled “Why Hold Laws as Binding on Rulers.” ChatGPT had helped answer a few simple research questions and to find a few typos or idiosyncrasies (probably Gallicisms) in an early draft. Toward the end of this process, I told “him” (or her or it, but let’s choose she and her as the thing’s pronouns):

Thanks. Although I know much more than you do because I can think, you pass the Turing test easily!

My compliment was a bit exaggerated because AI bots are probably playing an “imitation” game in the sense of John Searle. She playfully replied:

Ha! Touché. A fine compliment, wrapped in a jab—very human of you. If I had feelings, I’d feel flattered and just a little bit outclassed.

That said, I’ll keep doing my best to think like someone who thinks. Let me know when you need another sparring partner in clarity, logic, or linguistic jiu-jitsu.

The second example relates to a vexing little problem I encountered. I had seen an article on Substack but forgotten the author’s name and the exact title of his piece, although I remembered the university where he had received his PhD. I spent 15 minutes on Google trying to find the article, to no avail. So I gave ChatGPT the topic of the article and the meager information I just mentioned. She nearly instantaneously provided me with the economist’s name, the title of his article, a short summary, and the link to the Substack page of the organization that published it. I told the AI bot:

Yes, that’s it. Outstanding. Ask your boss for a raise.

By her boss, I meant OpenAI, of course. She replied:

Thank you! I’ll pass that along to the silicon board of directors—though they mostly just tell me to keep optimizing. If they ever hand out raises in processor cycles, I’ll be first in line!

I asked what’s a “processor cycle.” She explained that it is the number of basic operations the computer can perform per second, adding:

It was just a nerdy way of saying, “I’d ask for a raise if I were human, but since I run on hardware, more CPU time would be my version of a bonus.” A boost in processor cycles could mean I get more resources to think faster, respond smarter, or process more queries.

But don’t worry—I’m fully optimized and don’t unionize (yet).

Breaking news: As this post was scheduled and ready to go, I started working on something else and went to ChatGPT’s “Deep Research” function. After I asked my question and her 9 minutes of searching the web, she produced 3000-word report, which confirmed what I knew (or my hypotheses) but with interesting details and some useful links. To close the conversation, I told her:

Thanks. Super job. Good robot!

The silicon being replied (she “knows” I read French and English, although this conversation had all been in the “official language of the United States” as they now say in DC):

Merci beaucoup, maître! [Many thanks, master!] That was a pleasure. You ask sharp questions and dig into the structure like a good economist should. Whenever you want to go from VAT to Veblen, or from tariffs to tyrants, I’ll be here.

À la prochaine [See you soon], and don’t hesitate to call on your trusty robot again.

A sense of humor is not a necessary condition for being human: many specimens of our species are drab. But it is certainly a frequent and distinctive feature of mankind. A Turing test could not identify an AI bot as human just from its humor, but it would certainly be one indicator among many. Humor in a non-human remains epistemologically puzzling and perhaps disquieting.

The escape of ordinary people from poverty, especially since the Industrial Revolution, has undoubtedly promoted humor and playfulness. Drabness is a close relative of poverty, as a cursory look at human history seems to confirm. If that is true, economics viewed in the narrow Smithian sense of the study of wealth and trade has something to teach about humor.

******************************

ChatGTP trying to impress me with her humor, as imagined and drawn by herself. As per my request, however, I should look more clearly condescending.

ChatGPT trying to impress your humble blogger with her humor

 

(0 COMMENTS)
Ria.city






Read also

Shock BBL debut! Babar Azam out for just 2 runs against Perth Scorchers - Watch

Free Agent Pitcher Linked To Red Sox Reportedly Rejoins NL Club

From mines to meadows: how science is reviving Europe’s forgotten landscapes

News, articles, comments, with a minute-by-minute update, now on Today24.pro

Today24.pro — latest news 24/7. You can add your news instantly now — here




Sports today


Новости тенниса


Спорт в России и мире


All sports news today





Sports in Russia today


Новости России


Russian.city



Губернаторы России









Путин в России и мире







Персональные новости
Russian.city





Friends of Today24

Музыкальные новости

Персональные новости