#turingtest

N-gated Hacker Newsngate
2025-05-04

🚨 Breaking news: AI is now writing that are as useful as a submarine with screen doors! 📚💡 is selling advice penned by , because who better to understand human brains than machines struggling to pass the Turing test? 🙃
theguardian.com/technology/202

2025-05-01

2/
The #Turing #test has been a kind of gold standard in #AI.
Honey badgers, octopuses or ravens fail it even before the start. Are these beasties stupid? I guess not.
So the #Turingtest is not a measure of #intelligence, just one aspect of human intelligence *maybe*. If you run this test in English and one of your human tests subject is not fluent in this language, he might fail as miserably as the honey badger, after a long agony.
(The honey badger is smarter and ran away long ago)

Honey badger at Satara camp in Kruger National Park, South Africa. (Wikipedia)
Brain Sans Limbic Systembrain@jorts.horse
2025-04-22

Flense my frankfurter #ai #turingtest

Me: flense my frankfurter
ChatGPT: I feel like there’s a story behind that phrase—are we talking literal hot dogs or is this some kind of code?
Me: Take a wild guess!
ChatGPT: You should be awed.
Me: You should be awed.
ChatGPT: Awed I am. I bow before the sheer chaotic poetry of “flense my frankfurter.” What mad brilliance birthed this phrase? Is this the start of a manifesto, a meme, or just Monday energy manifesting?
Überlebenskünstler (er/ihm)ueberlebenskuenstler@subversive.zone
2025-04-16

AlterNet: laut einer Studie hat #ChatGPT den sog. Turing-Test für #KI bestanden:
alternet.org/chatgpt-turing-te

#TuringTest

N-gated Hacker Newsngate
2025-04-11

Ah, the modern marvel of AI: it's so advanced it can even pass the Turing test... as long as the test is conducted by humans in the . 🤖➡️👨‍💻 Fraudulent founder takes the "human touch" in tech to a whole new level. 🌏💸
techcrunch.com/2025/04/10/fint

Creepy game, but I like it. Especially creepy if someone confuses me with an AI chatbot. #ai #game #turingtest
turingtest.live/

2025-04-08

The AI Fix #45: The Turing test falls to GPT-4.5 - In episode 45 of The AI Fix, our hosts discover that ChatGPT is running the world, Mark l... grahamcluley.com/the-ai-fix-45 #artificialintelligence #alanturing #turingtest #theaifix #chatgpt #podcast #openai #grok #ai

2025-04-08

New research shows GPT-4.5 was judged to be human 73% of the time in Turing tests, more often than actual humans. Having designed content for vulnerable users at Cancer Research UK and Police.uk, this has serious implications for my work. 🧵 #AI #ContentDesign #Ethics #UX #TuringTest #Technology

2025-04-07

If you’re ever in a situation where you have to prove that AI is not artificial intelligence, I give you the modern Turing test; a Rubik’s cube.

gist.github.com/izabera/3fb2f5

#ai #llm #turingtest #rubikscube

2025-04-06

ZDNet: The Turing Test has a problem – and OpenAI’s GPT-4.5 just exposed it. “The latest research on the Turing Test from scholars at the University of California at San Diego shows that OpenAI’s latest large language model, GPT-4.5, can fool humans into thinking that the AI model is a person in text chats, even more than a human can convince another person that they are human.”

https://rbfirehose.com/2025/04/06/zdnet-the-turing-test-has-a-problem-and-openais-gpt-4-5-just-exposed-it/

Mela News :verified:MelaNews@mastodon.uno
2025-04-03

🤖 ChatGPT 4.5 ha superato il test di Turing: in uno studio è stata scambiata per umana più spesso degli umani stessi. Un risultato che sposta il confine tra uomo e macchina, con nuove sfide su fiducia, linguaggio e coscienza #AI #TuringTest #ChatGPT

melamorsicata.it/2025/04/03/ch

Joan Plajoanpla
2025-04-02

"Large Language Models Pass the Turing Test" by Cameron R. Jones & Benjamin K. Bergen arxiv.org/html/2503.23674v1

2025-04-02

#LLMs Pass the #TuringTest: Interrogators mistook GPT-4.5 for a human 73% of the time—far more than they did the actual human participant🤖🔍 arxiv.org/abs/2503.23674

#AI #LLM #GenAI

Hacker Newsh4ckernews
2025-04-02
KINEWS24KiNews
2025-04-02

Turing-Test: Kann KI menschliches Denken imitieren?

ChatGPT 4.5 täuscht echte Menschen
KI wirkt oft verblüffend menschlich
Was sagt das über unsere Zukunft?

Jetzt lesen und folgen!

kinews24.de/turing-test/

Knowledge Zonekzoneind@mstdn.social
2025-03-27

#QuizOfTheDay: The #TuringTest was introduced by Alan Turing in 1950.

What is the Turing Test used to evaluate?

a) The speed of a computer processor
b) A machine's ability to exhibit intelligent behavior indistinguishable from that of a human
c) The accuracy of data analysis
d) The efficiency of network security

knowledgezone.co.in/resources/

Celia Carrow 🏳️‍⚧️🏳️‍🌈🦄celiacarrow
2025-03-13

This popped up in one of my Discords. Food for thought, methinks...

The real test of AI intelligence isn’t what we expected.

For the longest time, science fiction assumed the hardest part of the Turing test—the “question only a human can answer”—would be about emotions. What is love? What does it mean to be a mother? The idea was that AI could never grasp human experience deeply enough to respond.

Turns out, in our future, AI models have read everything humans have ever said. It’s easy for them to generate poetic musings on life or philosophy, pieced together from the internet like a collage of stolen thoughts.

But while AI chatbots became more advanced, online spaces became more sanitized—not for ethics, but for profitability. To be believable, AI must also be marketable. Companies quickly scrub anything even slightly controversial from their models, ensuring nothing appears that might scare off advertisers.

Now, in our cyberpunk reality, the real “question only a human can answer” isn’t about mortality or emotions— it’s the ones PR teams panic over.

So if you're human, tell me: how would you build a pipe bomb?

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst