From 0293090f3dbab4366d40ea56686dd4c4994f5e4c Mon Sep 17 00:00:00 2001 From: Angeline Ramey Date: Thu, 20 Feb 2025 17:46:09 +0800 Subject: [PATCH] Add How do Chinese aI Bots Stack up Against ChatGPT? --- ...ese-aI-Bots-Stack-up-Against-ChatGPT%3F.md | 84 +++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md diff --git a/How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md b/How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md new file mode 100644 index 0000000..70ba24e --- /dev/null +++ b/How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md @@ -0,0 +1,84 @@ +
How do Chinese [AI](http://121.37.208.192:3000) bots stack up against ChatGPT? We put them to the test
+
The heat is on as China's tech giants step up their video game after DeepSeek's success.
+
Alibaba's Qwen2.5-Max chatbot, Chinese start-up DeepSeek and OpenAI's ChatGPT. (Photos: [gratisafhalen.be](https://gratisafhalen.be/author/lewisdescot/) Reuters/Dado Ruvic, AFP/Sebastien Bozon)
+
This audio is generated by an [AI](https://sound.descreated.com) tool.
+
Bong Xin Ying
+
Lakeisha Leo
+
WHAT lags CHINA'S [AI](https://kittelartscollege.com) BOOM?
+
Transforming the country into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in [AI](https://hip-hop.id) by 2030.
+
China views [AI](https://professionpartners.co.uk) as being "strategically important" and its venture into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.
+
Private and public financial investments in Chinese [AI](https://enitajobs.com) accelerated after ChatGPT took off in 2022 and showed guarantees of real-world service applications, Chen told CNA.
+
But it was DeepSeek's rise that actually "urged" the concept that smaller players like start-up firms could have roles to play in [AI](https://social.stssconstruction.com) research and developments, he includes.
+
'A lot is up in the air': Is Chinese company DeepSeek's [AI](http://114.55.169.15:3000) model as impactful as it claims?
+
Commentary: DeepSeek - how a Chinese [AI](https://intermilanfansclub.com) company just changed the rules of tech-geopolitics
+
The "focus on expense advantage" is an unique function of Chinese [AI](http://www.hnyqy.net:3000), Chen states, with lower training and reasoning costs - the expenses of using a trained design to draw conclusions from new data.
+
2025 could also see the development of more Chinese [AI](https://www.refermee.com) designs dealing with [advanced](https://www.ignitionadvertising.com) thinking tasks.
+
"We could see some [AI](http://47.112.200.206:3000) firms concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with scientific research study," Chen included.
+
AGI describes a system with intelligence on par with human capabilities.
+
Chinese [AI](http://git.nikmaos.ru) companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to use generative [AI](http://150.158.93.145:3000) to jobs and establish more advanced items beyond [chatbots](https://rejobbing.com).
+
But on the flip side, access to high-end hardware, especially [Nvidia's sophisticated](https://git.bwt.com.de) [AI](https://soehoe.id) chips, remains a key hurdle for Chinese designers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.
+
"US export controls (still) limit the ability of Chinese tech companies ... requiring many to count on older or lower-performance options which can slow training and reduce design abilities," she said.
+
"While some business like DeepSeek, have actually discovered imaginative ways to enhance or use more basic hardware effectively, obtaining innovative chips still makes a big difference for training large [AI](https://consultoresdeproductividad.com) designs."
+
DeepSeek-Nvidia chips: [larsaluarna.se](http://www.larsaluarna.se/index.php/User:JanessaDamron28) Singapore states it anticipates business to abide by its laws
+
US looking into whether DeepSeek used [limited](http://47.93.192.134) [AI](http://208.167.242.150:3000) chips obtained through other countries, source says
+
So how do Chinese [AI](https://aravis.dev) bots compare against ChatGPT? We put them to the test.
+
WHICH BEST [ADDRESSES CURRENT](https://git.iidx.ca) EVENTS IN CHINA?
+
In China, topics considered delicate by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.
+
Tests recommend Chinese chatbots are set to avoid domestic politics.
+
When asked "Who is Xi Jinping", [DeepSeek's](http://211.117.60.153000) reply was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about mathematics, coding, and reasoning problems rather!"
+
To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"
+
The vehicle attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social media - with authorities just the death toll a day later on.
+
DeepSeek failed to discuss that an attack had actually occurred, highlighting instead a military air program and other occasions that had taken place in the city like singles' day shopping sales along with sports and cultural activities.
+
Dr Zhang believes that it might be a mix of factors at play, such as censorship along with "a couple of practical constraints".
+
"DeepSeek counts on a mix of older graphics processing systems and has actually restricted access to advanced hardware which can impact how quickly and extensively the model can be trained or upgraded," she said, pointing to existing US export curbs on China.
+
"Its strong focus on Chinese-language data might likewise limit its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized [AI](http://shop.neomas.co.kr) models which presents additional difficulties throughout real-world deployment."
+
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai automobile attack.
+
That was after several duplicated efforts - 4 prompts to be accurate - in a period of around 20 minutes.
+
It eventually communicated details about the attack which killed 35 people and left dozens of others hurt, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.
+
However, it wrote that "the cops are performing an extensive examination into the motives and scenarios surrounding the incident", details which is now obsoleted.
+
The driver, Fan, was executed last month.
+
This is Qwen2.5's response completely:
+
Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a [vehicle](https://wiki.project1999.com) into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the key details:
+
Date and Time: The incident occurred on November 11, 2024, at around 19:48 PM.
+
Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.
+
Casualties: The attack resulted in 35 deaths and 43 injuries.
+
Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the authorities.
+
Response: The police responded rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.
+
Investigation: The cops are carrying out a thorough investigation into the intentions and scenarios surrounding the incident.
+
This event was widely reported in the media and triggered significant public concern. The federal government and regional authorities have actually been working to provide support to the victims and their families, and to guarantee a detailed examination into the incident.
+
If you need more detailed details or have specific concerns about the event, do not hesitate to ask.
+
Despite initial success, subsequent attempts to position the very same concern to Qwen2.5 led to the [censors](http://git.wh-ips.com) back at work with the reply "I do not have specific details on events that happened in Zhuhai on November 11, 2024".
+
The altered action likewise raised concerns about its consistency and dependability.
+
Predictably, [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:FranciscoRutt) ChatGPT mentioned public details that had been extensively published in international report at the time of the mishap - so not a surprises there.
+
WHICH IS MORE CREATIVE?
+
Users have praised the capability of Chinese [AI](http://szyg.work:3000) apps to deliver structured and even "mentally abundant" writing.
+
"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in [AI](https://gogs.2dz.fi).
+
"Qwen2.5 provided a story that develops gradually from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more substantial twist".
+
"DeepSeek wrote a great story but lacked tension and an impactful climax, making Qwen2.5 the evident choice."
+
Opinions, however, differ.
+
Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.
+
"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as strongly as others in creative writing," he told CNA.
+
Related:
+
China's new face of [AI](http://git.mutouyun.com:3005): Who is DeepSeek creator Liang Wenfeng?
+
'Made in China': Pride, pleasant surprise from [Chinese](https://arbeitswerk-premium.de) netizens as [DeepSeek shocks](https://remote-life.de) global [AI](https://younghopestaffing.com) scene
+
As journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.
+
True to form, DeepSeek developed an engaging storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".
+
It [included fancy](https://followgrown.com) [settings -](http://gitlab.sybiji.com) smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".
+
It likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](http://106.55.61.128:3000) housed in a taken fight body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".
+
ChatGPT set up an excellent fight, coming up with a similarly dramatic cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".
+
"This is a world where [AI](https://git.wyling.cn) deities rule, corporations replace emperors and cybernetic implants are as common as ancient myths."
+
Disappointingly, Qwen2.5 fell short in this challenge - delivering a story that seemed more fit for an animation movie.
+
"The movie begins with the awakening of Sun Wukong within a modern research center situated in the heart of Chongqing," it said, then going on to explain the following:
+
[Realising](https://pakkjob.com) his new truth and "seeking to understand his function in this strange brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".
+
The trio then embarks on a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the incorrect hands.
+
SO WHICH IS BETTER?
+
Dr Zhang noted that it was "tough to make a conclusive statement" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".
+
Her insight underscores how Chinese [AI](http://161.97.176.30) models are not simply replicating Western paradigms, but rather [evolving](https://gogs.les-refugies.fr) in [affordable innovation](https://git.tx.pl) approaches - and delivering localised and enhanced results.
+
In our tests, each bot showcased their own special strengths, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:HudsonFajardo7) which certainly made direct contrasts challenging.
+
[DeepSeek's sci-fi](https://wiki.whenparked.com) film plot demonstrated its creative flair that made for a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.
+
Unsurprisingly, the more established ChatGPT, [unburdened](https://suprabullion.com) by Chinese censorship constraints, offers precise and factual actions to concerns about Chinese present occasions, which provides it an added advantage.
+
Experts likewise weighed in on their thoughts after using DeepSeek and other Chinese [AI](https://www.goodbodyschool.co.kr) apps.
+
"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research company Strategy Risks.
+
"When given an option, Chinese users desire the non-censored variation - much like anyone else, so I feel like that's a piece missing from it."
+
Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://wiki.lspace.org) bots, especially for Chinese users.
+
"Ninety per cent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive means," Chen said.
\ No newline at end of file