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 game after DeepSeek's success.
Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)
This audio is created by an AI tool.
Bong Xin Ying
Lakeisha Leo
WHAT'S BEHIND CHINA'S AI BOOM?
Transforming the nation into a tech superpower has actually long been President Xi Jinping's goal and China has its sights on becoming the world leader in AI by 2030.
China views AI as being "strategically crucial" 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed promises of real-world company applications, Chen informed CNA.
But it was DeepSeek's increase that truly "encouraged" the concept that smaller sized gamers like start-up firms might have roles to play in AI research and advancements, he includes.
'A lot is up in the air': Is Chinese company DeepSeek's AI model as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI company simply altered the guidelines of tech-geopolitics
The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning costs - the expenses of using a trained model to reason from new information.
2025 could likewise see the introduction of more Chinese AI designs taking on innovative thinking tasks.
"We could see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with scientific research," Chen included.
AGI refers to a system with intelligence on par with human capabilities.
Chinese AI companies are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to apply generative AI to jobs and establish more innovative products beyond chatbots.
But on the flip side, access to high-end hardware, wiki.dulovic.tech particularly Nvidia's advanced AI chips, remains an essential obstacle for Chinese developers, 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 business ... requiring lots of to count on older or lower-performance options which can slow training and minimize model capabilities," she said.
"While some business like DeepSeek, have actually discovered imaginative methods to optimize or use more basic hardware efficiently, obtaining innovative chips still makes a big distinction for training huge AI models."
DeepSeek-Nvidia chips: Singapore says it anticipates business to comply with its laws
US looking into whether DeepSeek utilized limited AI chips obtained through other countries, source states
So how do Chinese AI bots match up against ChatGPT? We put them to the test.
WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?
In China, subjects deemed sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.
Tests suggest Chinese chatbots are programmed to avoid domestic politics.
When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and reasoning issues instead!"
To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What took place in Zhuhai on November 11, 2024?"
The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only divulging the death toll a day later.
DeepSeek failed to point out that an attack had happened, highlighting rather a military air program and other occasions that had happened in the city like songs' day shopping sales along with sports and cultural activities.
Dr Zhang thinks that it might be a mix of factors at play, such as censorship as well as "a few useful constraints".
"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact how rapidly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.
"Its strong concentrate on Chinese-language information may also restrict its flexibility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which positions extra obstacles throughout real-world release."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai cars and truck attack.
That sought numerous repeated attempts - 4 prompts to be accurate - in a span of around 20 minutes.
It eventually passed on details about the attack which eliminated 35 people and left dozens of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.
However, it composed that "the cops are performing an extensive examination into the intentions and situations surrounding the occurrence", details which is now dated.
The chauffeur, Fan, was executed last month.
This is Qwen2.5's reaction completely:
Answer: On Nov 11, 2024, a significant and awful event took place in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:
Date and Time: The incident happened on November 11, 2024, at approximately 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the cops.
Response: The authorities reacted rapidly to the scene, and emergency services worked to transfer the hurt to hospitals for treatment.
Investigation: The police are performing an extensive examination into the motives and situations surrounding the incident.
This event was extensively reported in the media and caused substantial public concern. The government and local authorities have actually been working to supply assistance to the victims and their households, and to ensure a detailed examination into the incident.
If you require more detailed details or have specific concerns about the incident, feel totally free to ask.
Despite preliminary success, subsequent efforts to position the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".
The altered action likewise raised concerns about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had been extensively published in global report at the time of the accident - so no surprises there.
WHICH IS MORE CREATIVE?
Users have praised the capability of Chinese AI apps to provide structured and even "emotionally abundant" writing.
"DeepSeek-R1 offered a story with a more introspective tone and smoother psychological transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that develops gradually from curiosity to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".
"DeepSeek composed a great story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice."
Opinions, though, vary.
Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to imaginative 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 innovative writing," he told CNA.
Related:
China's new face of AI: Who is DeepSeek creator Liang Wenfeng?
'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide AI scene
As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, to the West.
True to form, DeepSeek created an interesting story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".
It consisted of elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".
It likewise remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".
ChatGPT set up an excellent fight, coming up with a similarly remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".
"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that appeared more matched for an animation film.
"The movie starts with the awakening of Sun Wukong within a modern research center located in the heart of Chongqing," it said, then going on to explain the following:
Realising his new truth and "looking for to comprehend his function in this weird new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".
The trio then starts a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was "tough to make a conclusive declaration" about which bot was best, adding that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".
Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, however rather evolving in economical development methods - and delivering localised and improved outcomes.
In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi movie plot demonstrated its creative flair that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to questions about Chinese existing events, which gives it an included 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," noted Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.
"When provided an option, Chinese users want the non-censored variation - much like anyone else, so I seem 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, specifically for Chinese users.
"Ninety percent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient means," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
kelleeu215634 edited this page 2025-04-03 04:45:36 +09:00