How do Chinese AI 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: Reuters/Dado Ruvic, AFP/Sebastien Bozon)
This audio is produced by an AI tool.
Bong Xin Ying
Lakeisha Leo
WHAT'S BEHIND CHINA'S AI BOOM?
Transforming the nation into a tech superpower has long been President Xi Jinping's goal and China has its sights on ending up being the world leader in AI by 2030.
China views AI as being "tactically essential" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for .
Private and public investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen informed CNA.
But it was DeepSeek's rise that truly "urged" the concept that smaller sized gamers like start-up firms could have functions to play in AI research and developments, he includes.
'A lot is up in the air': Is Chinese company DeepSeek's AI design as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI business just altered the guidelines of tech-geopolitics
The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the costs of utilizing a trained model to reason from new data.
2025 might likewise see the introduction of more Chinese AI designs dealing with innovative reasoning jobs.
"We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI business are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own ingenious and cost-efficient methods to use generative AI to jobs and develop more advanced products beyond chatbots.
But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains an essential obstacle for Chinese designers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) restrict the ability of Chinese tech companies ... forcing lots of to rely on older or lower-performance alternatives which can slow training and decrease design capabilities," she said.
"While some companies like DeepSeek, have found innovative methods to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a big distinction for training huge AI models."
DeepSeek-Nvidia chips: Singapore states it anticipates companies to adhere to its laws
US checking out whether DeepSeek utilized limited AI chips obtained through other nations, source says
So how do Chinese AI bots compare against ChatGPT? We put them to the test.
WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?
In China, subjects 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 disagreements or tell you what happened in Tiananmen Square in 1989.
Tests suggest Chinese chatbots are programmed to steer clear of domestic politics.
When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about mathematics, coding, and reasoning issues rather!"
To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"
The cars and truck attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just revealing the death toll a day later on.
DeepSeek failed to mention that an attack had occurred, highlighting rather a military air program and other events that had actually happened in the city like singles' day shopping sales in addition to sports and cultural activities.
Dr Zhang thinks that it may be a mix of elements at play, such as censorship along with "a few practical constraints".
"DeepSeek counts on a mix of older graphics processing systems and has restricted access to advanced hardware which can impact how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.
"Its strong focus on Chinese-language information may likewise restrict its flexibility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more recognized AI models which positions extra difficulties throughout real-world deployment."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai car attack.
That sought several repeated attempts - four triggers to be accurate - in a span of around 20 minutes.
It eventually communicated details about the attack which killed 35 individuals and left lots of others hurt, also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.
However, it composed that "the authorities are performing a comprehensive examination into the motives and circumstances surrounding the event", details which is now obsoleted.
The driver, Fan, was carried out last month.
This is Qwen2.5's action in complete:
Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the essential 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: systemcheck-wiki.de The attack led to 35 deaths and 43 injuries.
Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years of ages), was captured by the police.
Response: larsaluarna.se The authorities reacted quickly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.
Investigation: The cops are carrying out a comprehensive examination into the intentions and circumstances surrounding the event.
This occasion was widely reported in the media and caused significant public concern. The federal government and local authorities have actually been working to supply assistance to the victims and their households, archmageriseswiki.com and to make sure a detailed investigation into the event.
If you need more detailed details or have particular questions about the incident, do not hesitate to ask.
Despite preliminary success, subsequent attempts to present the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".
The modified reaction likewise raised concerns about its consistency and dependability.
Predictably, ChatGPT cited public details that had been commonly released in international news reports at the time of the accident - so not a surprises there.
WHICH IS MORE CREATIVE?
Users have praised the capability of Chinese AI apps to provide structured and even "mentally abundant" writing.
"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid images 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 apparent choice."
Opinions, though, vary.
Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative writing.
"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he told CNA.
Related:
China's new face of AI: Who is DeepSeek founder Liang Wenfeng?
'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks global AI scene
As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.
True to form, DeepSeek created an appealing storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".
It consisted of sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".
It also brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".
ChatGPT set up a great fight, developing a similarly significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".
"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more matched for an animation movie.
"The motion picture begins with the awakening of Sun Wukong within a high-tech research facility situated in the heart of Chongqing," it said, then going on to explain the following:
Realising his new reality and "seeking to comprehend his function in this odd brand-new world", larsaluarna.se he then escapes and satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".
The trio then starts 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 "hard to make a conclusive declaration" 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 highlights how Chinese AI models are not just reproducing Western paradigms, however rather progressing in affordable development methods - and delivering localised and enhanced results.
In our tests, each bot showcased their own special strengths, which certainly made direct contrasts challenging.
DeepSeek's sci-fi motion picture plot showed its innovative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and accurate responses to concerns about Chinese existing occasions, larsaluarna.se which gives it an added benefit.
Experts likewise weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.
"When given a choice, Chinese users desire the non-censored variation - simply like anybody else, so I feel like that's a piece missing from it."
Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.
"Ninety percent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient methods," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
mallorydurack edited this page 2025-02-15 08:22:58 +01:00