devindane80974
/
indianschoolsoman
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Devin Dane? 2025-04-06 21:54:07 +08:00
commit 15ff993038
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://edenhazardclub.com) 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 video game after DeepSeek's [success](https://gitea.gm56.ru).<br>
<br>Alibaba's Qwen2.5-Max chatbot, Chinese start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is created by an [AI](https://www.ayc.com.au) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://job.duttainnovations.com) BOOM?<br>
<br>Transforming the country into a tech superpower has long been President Xi Jinping's objective and China has its sights on ending up being the world leader in [AI](https://parentingliteracy.com) by 2030.<br>
<br>China views [AI](http://ledok.cn:3000) as being "strategically crucial" and its foray 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.<br>
<br>Private and [public investments](http://101.36.160.14021044) in [Chinese](https://avpro.cc) [AI](https://dakresources.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 rise that actually "encouraged" the idea that smaller gamers like start-up companies might have functions to play in [AI](https://viddertube.com) research and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://git.thewebally.com) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://107.172.157.44:3000) company simply changed the rules of tech-geopolitics<br>
<br>The "focus on cost advantage" is a distinguishing characteristic of Chinese [AI](http://47.119.27.83:8003), Chen states, with lower training and inference costs - the expenses of using a trained model to draw conclusions from brand-new data.<br>
<br>2025 might likewise see the emergence of more Chinese [AI](https://www.eticalavoro.it) designs taking on advanced thinking tasks.<br>
<br>"We might see some [AI](https://gitea.lelespace.top) companies concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research study," Chen included.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](http://47.92.26.237) companies are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use generative [AI](http://139.9.50.163:3000) to tasks and establish advanced items beyond [chatbots](https://gogs.dev.dazesoft.cn).<br>
<br>But on the other side, access to high-end hardware, particularly Nvidia's advanced [AI](https://git.amic.ru) chips, remains an essential difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) limit the ability of Chinese tech business ... requiring many to rely on older or lower-performance options which can slow training and lower design abilities," she said.<br>
<br>"While some business like DeepSeek, have actually discovered creative methods to optimize or utilize more fundamental hardware efficiently, obtaining advanced chips still makes a big distinction for training large [AI](https://git.partners.run) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects business to abide by its laws<br>
<br>US checking out whether DeepSeek utilized limited [AI](https://gitlab.ngser.com) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://youarealways.online) 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 sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are set to stay away from domestic politics.<br>
<br>When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and logic problems instead!"<br>
<br>To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just divulging the death toll a day later on.<br>
<br>DeepSeek failed to point out that an attack had happened, highlighting instead a military air program and other events that had actually occurred in the city like songs' day shopping sales as well as sports and cultural activities.<br>
<br>Dr Zhang believes that it might be a mix of elements at play, such as censorship as well as "a couple of useful constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to advanced hardware which can affect how rapidly and thoroughly the design can be trained or upgraded," she said, [surgiteams.com](https://surgiteams.com/index.php/User:Eddy957157) indicating existing US export curbs on China.<br>
<br>"Its strong concentrate on Chinese-language data may likewise restrict its versatility (to carry out) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized [AI](http://139.9.50.163:3000) models which postures extra challenges throughout real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our concern about the Zhuhai cars and truck attack.<br>
<br>That was after several duplicated efforts - 4 triggers to be exact - 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, also going on to list details like the date and time, [details](http://daeasecurity.com) about the assailant including his name and age, along with casualties.<br>
<br>However, it wrote that "the cops are performing a thorough investigation into the motives and scenarios surrounding the event", details which is now [outdated](https://projectblueberryserver.com).<br>
<br>The motorist, Fan, was carried out last month.<br>
<br>This is Qwen2.5's response in full:<br>
<br>Answer: On Nov 11, 2024, a major and terrible occurrence [occurred](https://121.36.226.23) in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the essential 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 driver, identified as Fan Weiqiu (male, 62 years of ages), was captured by the police.<br>
<br>Response: The authorities reacted quickly to the scene, and emergency services worked to transport the hurt to healthcare facilities for treatment.<br>
<br>Investigation: The police are [performing](https://www.jpaik.com) an extensive examination into the intentions and situations surrounding the occurrence.<br>
<br>This event was widely reported in the media and triggered substantial public concern. The [federal government](http://118.190.88.238888) and local authorities have been working to provide assistance to the victims and their families, and to make sure a detailed investigation into the incident.<br>
<br>If you need more detailed details or have particular concerns about the incident, feel free to ask.<br>
<br>Despite initial success, subsequent attempts to present the exact same concern to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".<br>
<br>The [transformed reaction](https://wiki.cemu.info) also raised questions about its consistency and reliability.<br>
<br>Predictably, ChatGPT mentioned public details that had actually been widely published in global report at the time of the accident - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the ability of Chinese [AI](http://www.s-golflex.kr) apps to provide structured and even "emotionally abundant" [writing](http://famedoot.in).<br>
<br>"DeepSeek-R1 offered a story with a more introspective tone and smoother psychological shifts for a well-paced story," wrote tech writer Amanda Caswell, who [specialises](https://wow.t-mobility.co.il) in [AI](http://201.17.3.96:3000).<br>
<br>"Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 [ultimately](http://146.148.65.983000) "crafted a more cinematic, emotionally rich story with a more substantial twist".<br>
<br>"DeepSeek composed a great story but did not have stress and an impactful climax, making Qwen2.5 the evident choice."<br>
<br>Opinions, though, vary.<br>
<br>Chen thinks that Qwen2.5 does not carry out as highly 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 likewise see that it is refraining from doing as highly as others in creative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://pediascape.science): Who is [DeepSeek founder](http://49.235.101.2443001) [Liang Wenfeng](https://medea.medianet.cs.kent.edu)?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide [AI](http://carpetube.com) scene<br>
<br>As reporters 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 embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.<br>
<br>True to form, DeepSeek came up with an engaging story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It consisted of fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://linkpiz.com) housed in a taken battle 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 end up being waterlogged and fragmented".<br>
<br>[ChatGPT installed](https://wow.t-mobility.co.il) a great battle, a similarly dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".<br>
<br>"This is a world where [AI](http://gitea.smartscf.cn:8000) deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty [- providing](http://119.23.214.10930032) a story that [appeared](http://121.196.13.116) more suited for an animation movie.<br>
<br>"The motion picture begins with the awakening of Sun Wukong within a state-of-the-art research facility situated in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his new reality and "looking for to comprehend his function in this unusual brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".<br>
<br>The trio then embarks on a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "challenging to make a definitive declaration" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".<br>
<br>Her insight highlights how [Chinese](http://82.156.184.993000) [AI](https://findmynext.webconvoy.com) models are not just duplicating Western paradigms, however rather progressing in affordable innovation approaches - and delivering localised and improved results.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct contrasts challenging.<br>
<br>DeepSeek's sci-fi film plot demonstrated its creative flair that produced a more engaging and [imaginative story](http://teamcous.com) as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual actions to [concerns](http://146.148.65.983000) about Chinese existing occasions, which provides it an added benefit.<br>
<br>Experts likewise weighed in on their ideas after using DeepSeek and other Chinese [AI](https://git.karma-riuk.com) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research company Strategy Risks.<br>
<br>"When given a choice, Chinese users want the non-censored variation - much like anyone 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://git.cloud.krotovic.com) bots, specifically for Chinese users.<br>
<br>"Ninety per cent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient ways," Chen said.<br>