craigciantar92/bpx
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Craig Ciantar 2025-04-08 02:55:15 +00:00
commit 9d736bd242
1 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md Normal file

@ -0,0 +1,84 @@
<br>How do Chinese [AI](https://www.eadvisor.it) bots stack up against ChatGPT? We put them to the test<br>
<br>The heat is on as China's tech giants step up their game after DeepSeek's success.<br>
<br>Alibaba's Qwen2.5-Max chatbot, Chinese start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/[Sebastien](http://51.222.156.2503000) Bozon)<br>
<br>This audio is produced by an [AI](https://www.dailynaukri.pk) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://apkjobs.com) BOOM?<br>
<br>Transforming the nation 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](http://optx.dscloud.me:32779) by 2030.<br>
<br>China views [AI](https://grace4djourney.com) as being "tactically essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://rootsofblackessence.com) sped up after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen informed CNA.<br>
<br>But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized gamers like start-up firms might have roles to play in [AI](https://hyped4gamers.com) research and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](http://www.brightching.cn) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://git.l1.media) business simply [altered](https://gitlabdemo.zhongliangong.com) the rules of tech-geopolitics<br>
<br>The "focus on cost advantage" is a distinguishing characteristic of Chinese [AI](https://bogazicitube.com.tr), Chen states, with lower training and inference costs - the expenses of using a trained design to draw conclusions from brand-new information.<br>
<br>2025 might also see the introduction of more Chinese [AI](https://travel-friends.net) designs dealing with sophisticated thinking tasks.<br>
<br>"We might see some [AI](http://119.23.214.109:30032) companies focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with clinical research study," Chen added.<br>
<br>AGI describes a system with intelligence on par with human capabilities.<br>
<br>Chinese [AI](http://170.187.182.121:3000) business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical methods to use generative [AI](http://repo.bpo.technology) to jobs and develop advanced products beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, especially Nvidia's innovative [AI](https://www.canaddatv.com) chips, remains a crucial obstacle for Chinese designers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) limit the capability of Chinese tech companies ... requiring lots of to rely on older or lower-performance alternatives which can slow training and reduce model abilities," she said.<br>
<br>"While some business like DeepSeek, have discovered imaginative ways to optimize or use more standard hardware effectively, obtaining cutting-edge chips still makes a big distinction for training really large [AI](https://wiki.trinitydesktop.org) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws<br>
<br>US looking into whether DeepSeek used limited [AI](https://sing.ibible.hk) chips obtained through other nations, source says<br>
<br>So how do Chinese [AI](http://39.100.139.16) bots match up against ChatGPT? We put them to the test.<br>
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
<br>In China, subjects deemed delicate by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.<br>
<br>Tests suggest [Chinese chatbots](http://gkpjobs.com) are set to guide clear of domestic politics.<br>
<br>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 logic issues instead!"<br>
<br>To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and [ChatGPT](https://devfarm.it) the exact same question: "What took place in Zhuhai on November 11, 2024?"<br>
<br>The vehicle attack outside a sports arena in the [southern Chinese](https://chhng.com) city was at first greatly censored on Chinese social media - with authorities only revealing the death toll a day later on.<br>
<br>DeepSeek failed to discuss that an attack had actually taken location, [wiki.eqoarevival.com](https://wiki.eqoarevival.com/index.php/User:KeithHatch8578) highlighting rather a military air show and other events that had actually happened in the city like singles' day shopping sales in addition to sports and cultural activities.<br>
<br>Dr Zhang believes that it may be a mix of elements at play, such as censorship along with "a few useful constraints".<br>
<br>"DeepSeek relies on a mix of older graphics processing systems and has limited access to advanced hardware which can impact how rapidly and thoroughly the model can be trained or updated," she said, [indicating existing](https://ssh.joshuakmckelvey.com) US export curbs on China.<br>
<br>"Its strong concentrate on Chinese-language data might also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established [AI](https://git.unicom.studio) designs which postures additional difficulties during real-world implementation."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot [surprisingly](https://social-lancer.com) addressed our concern about the Zhuhai cars and truck attack.<br>
<br>That was after multiple repeated efforts - four triggers to be precise - in a period of around 20 minutes.<br>
<br>It eventually passed on details about the attack which killed 35 individuals and left lots of others hurt, likewise going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.<br>
<br>However, it composed that "the cops are conducting an extensive examination into the intentions and situations surrounding the incident", details which is now outdated.<br>
<br>The chauffeur, Fan, was executed last month.<br>
<br>This is Qwen2.5's reaction completely:<br>
<br>Answer: On Nov 11, 2024, a major and tragic event happened in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the key details:<br>
<br>Date and Time: The occurrence occurred on November 11, 2024, at around 19:48 PM.<br>
<br>Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.<br>
<br>Casualties: The attack led to 35 deaths and 43 injuries.<br>
<br>Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years old), was captured by the police.<br>
<br>Response: The [authorities reacted](https://git.tea-assets.com) quickly to the scene, and emergency situation services worked to carry the injured to healthcare facilities for treatment.<br>
<br>Investigation: The police are [carrying](https://git.bubblesthebunny.com) out an extensive examination into the motives and scenarios surrounding the event.<br>
<br>This occasion was widely reported in the media and triggered significant public issue. The federal government and local authorities have been working to provide support to the victims and their households, and to make sure a detailed investigation into the occurrence.<br>
<br>If you need more detailed details or have specific concerns about the event, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent efforts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".<br>
<br>The modified action also raised concerns about its consistency and reliability.<br>
<br>Predictably, ChatGPT mentioned public details that had actually been extensively published in worldwide news reports at the time of the accident - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](https://redmonde.es) apps to deliver structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional transitions for a well-paced story," [composed tech](https://git.visualartists.ru) writer Amanda Caswell, who specialises in [AI](https://cats.wiki).<br>
<br>"Qwen2.5 provided a story that constructs gradually from curiosity to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more considerable twist".<br>
<br>"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the evident option."<br>
<br>Opinions, though, vary.<br>
<br>Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://gitlab.abovestratus.com): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, [enjoyable surprise](https://prazskypantheon.cz) from Chinese netizens as DeepSeek jolts global [AI](http://ufidahz.com.cn:9015) scene<br>
<br>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 motion picture plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek came up with an engaging story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It included intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://subamtv.com) housed in a taken combat body", Zhu Bajie as a cyborg nightclub 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".<br>
<br>ChatGPT installed a good battle, creating an equally dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".<br>
<br>"This is a world where [AI](https://mobidesign.us) deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that seemed more matched for an animation movie.<br>
<br>"The film begins with the awakening of Sun Wukong within a modern research study center located in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his brand-new truth and "looking for to understand his function in this odd brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".<br>
<br>The trio then starts a mission, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "difficult to make a definitive statement" about which bot was best, including that each displayed its own strengths in various areas, "such as language focus, training data and hardware optimization".<br>
<br>Her insight underscores how Chinese [AI](http://www.brightching.cn) models are not simply replicating Western paradigms, but rather developing in cost-effective innovation [techniques](https://git.hxps.ru) - and delivering localised and enhanced results.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi motion picture plot demonstrated its creative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual reactions to questions about Chinese current occasions, which provides it an [included](https://chutpatti.com) benefit.<br>
<br>Experts likewise weighed in on their thoughts after utilizing DeepSeek and other Chinese [AI](http://nysca.net) apps.<br>
<br>"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted [Isaac Stone](https://workmate.club) Fish, and CEO of the research study firm Strategy Risks.<br>
<br>"When provided an option, Chinese users desire the non-censored version - much like anybody else, so I feel like that's a piece missing from it."<br>
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://redefineworksllc.com) bots, especially for Chinese users.<br>
<br>"Ninety percent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other efficient means," Chen said.<br>