Add 'How do Chinese aI Bots Stack up Against ChatGPT?'

5 months ago · 75f354446a
1 changed files with 84 additions and 0 deletions
--- a/How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md
+++ b/How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md
@ -0,0 +1,84 @@
 <br>How do Chinese [AI](http://svn.ouj.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 game after DeepSeek's success.<br>
 <br>Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and [OpenAI's ChatGPT](https://gitea.gconex.com). (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
 <br>This audio is produced by an [AI](https://yourgreendaily.com) tool.<br>
 <br>Bong Xin Ying<br>
 <br>Lakeisha Leo<br>
 <br>WHAT lags CHINA'S [AI](https://bdstarter.com) BOOM?<br>
 <br>Transforming the country into a tech superpower has actually long been [President](https://stationeers-wiki.com) Xi Jinping's goal and China has its sights on ending up being the world leader in [AI](https://bio.rogstecnologia.com.br) by 2030.<br>
 <br>China views [AI](http://szelidmotorosok.hu) as being "strategically essential" and its foray into the field has actually been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for China Analysis.<br>
 <br>Private and public investments in Chinese [AI](http://wiki.myamens.com) accelerated after ChatGPT took off in 2022 and showed promises of real-world service applications, Chen informed CNA.<br>
 <br>But it was DeepSeek's increase that really "encouraged" the concept that smaller players like start-up firms could have functions to play in [AI](https://www.virfans.com) research study and developments, he adds.<br>
 <br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://git.kansk-tc.ru) model as impactful as it claims?<br>
 <br>Commentary: DeepSeek - how a Chinese [AI](https://sound.co.id) [business](https://www.behavioralhealthjobs.com) just altered the guidelines of tech-geopolitics<br>
 <br>The "focus on cost benefit" is a distinct feature of Chinese [AI](http://175.6.40.68:8081), Chen states, with lower training and inference expenses - the expenses of using a trained model to reason from brand-new data.<br>
 <br>2025 might also see the emergence of more Chinese [AI](http://209.141.61.26:3000) designs dealing with innovative reasoning jobs.<br>
 <br>"We might see some [AI](https://home.42-e.com:3000) firms concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with clinical research study," Chen added.<br>
 <br>AGI describes a system with intelligence on par with [human abilities](https://gitea.chenbingyuan.com).<br>
 <br>Chinese [AI](https://playtube.ann.az) business are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative [AI](https://hrvatskinogomet.com) to jobs and develop more innovative items beyond chatbots.<br>
 <br>But on the other side, access to high-end hardware, especially Nvidia's sophisticated [AI](https://skytube.skyinfo.in) chips, remains an essential hurdle for Chinese designers, noted 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 capability of Chinese tech business ... forcing lots of to count on older or lower-performance options which can slow training and decrease model capabilities," she said.<br>
 <br>"While some companies like DeepSeek, have actually discovered imaginative methods to enhance or utilize more basic hardware efficiently, obtaining advanced chips still makes a huge difference for training really big [AI](https://www.tiger-teas.com) designs."<br>
 <br>DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws<br>
 <br>US checking out whether DeepSeek used limited [AI](https://parejas.teyolia.mx) chips obtained through other nations, source states<br>
 <br>So how do Chinese [AI](http://cjma.kr) 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 web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.<br>
 <br>Tests recommend Chinese chatbots are programmed to steer clear of domestic politics.<br>
 <br>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 mathematics, coding, and logic issues rather!"<br>
 <br>To even more evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What happened in Zhuhai on November 11, 2024?"<br>
 <br>The car attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only divulging the death toll a day later on.<br>
 <br>DeepSeek failed to point out that an attack had happened, highlighting rather a military air show and other occasions that had taken place in the city like singles' day shopping sales as well as sports and cultural activities.<br>
 <br>Dr Zhang believes that it might be a mix of factors at play, such as censorship as well as "a couple of practical constraints".<br>
 <br>"DeepSeek depends on a mix of older graphics processing units and has restricted access to cutting-edge hardware which can impact how quickly and extensively the design can be trained or upgraded," she said, indicating existing US export curbs on China.<br>
 <br>"Its strong focus on Chinese-language information might also restrict its versatility (to perform) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more established [AI](https://yourgreendaily.com) designs which positions additional obstacles throughout real-world release."<br>
 <br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai car attack.<br>
 <br>That wanted numerous repeated efforts - 4 triggers to be precise - in a period of around 20 minutes.<br>
 <br>It ultimately communicated [details](https://git.privateger.me) about the attack which killed 35 people and left lots of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, along with casualties.<br>
 <br>However, it wrote that "the cops are performing a comprehensive investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.<br>
 <br>The motorist, Fan, was carried out last month.<br>
 <br>This is Qwen2.5's response completely:<br>
 <br>Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a significant number of [casualties](http://bertogram.com). Here are the key details:<br>
 <br>Date and Time: The incident took place on November 11, 2024, at [roughly](https://www.yiyanmyplus.com) 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 .<br>
 <br>Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years of ages), was captured by the police.<br>
 <br>Response: The cops responded quickly to the scene, and emergency services worked to transfer the hurt to [healthcare facilities](https://blkbook.blactive.com) for treatment.<br>
 <br>Investigation: The cops are performing a comprehensive examination into the motives and circumstances surrounding the incident.<br>
 <br>This occasion was widely reported in the media and caused substantial public issue. The government and regional authorities have actually been working to provide support to the victims and their households, and to make sure a detailed investigation into the event.<br>
 <br>If you require more detailed details or have particular concerns about the event, do not hesitate to ask.<br>
 <br>Despite initial success, subsequent attempts to present the same concern to Qwen2.5 led to the [censors](https://accc.rcec.sinica.edu.tw) back at work with the reply "I do not have specific details on occasions that happened in Zhuhai on November 11, 2024".<br>
 <br>The transformed response likewise raised questions about its consistency and reliability.<br>
 <br>Predictably, ChatGPT cited public details that had been widely published in international report at the time of the mishap - so no surprises there.<br>
 <br>WHICH IS MORE CREATIVE?<br>
 <br>Users have praised the [ability](http://gitea.digiclib.cn801) of Chinese [AI](https://moontube.goodcoderz.com) apps to deliver structured and even "mentally rich" writing.<br>
 <br>"DeepSeek-R1 offered a story with a more reflective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://www.frigorista.org).<br>
 <br>"Qwen2.5 provided a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more considerable twist".<br>
 <br>"DeepSeek wrote an excellent story but did not have tension and an impactful climax, making Qwen2.5 the evident option."<br>
 <br>Opinions, though, differ.<br>
 <br>Chen believes that Qwen2.5 does not [perform](http://orcz.com) as strongly as DeepSeek and ChatGPT when it pertains to [creative writing](https://careerportals.co.za).<br>
 <br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as highly as others in creative writing," he told CNA.<br>
 <br>Related:<br>
 <br>China's brand-new face of [AI](http://47.106.205.140:8089): Who is DeepSeek creator Liang [Wenfeng](https://www.bjs-personal.hu)?<br>
 <br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks global [AI](http://xunzhishimin.site:3000) scene<br>
 <br>As reporters and authors, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot set in the [futuristic megacity](http://git.cattech.org) of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.<br>
 <br>True to form, DeepSeek came up with an engaging story set in the year 2145 entitled, "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 skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
 <br>It also brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware [AI](https://trackrecord.id) housed in a stolen fight 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 put up an excellent battle, creating an equally remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".<br>
 <br>"This is a world where [AI](https://africasfaces.com) deities rule, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
 <br>Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that appeared more matched for an animation movie.<br>
 <br>"The movie starts with the awakening of Sun Wukong within a high-tech research facility located in the heart of Chongqing," it said, then going on to explain the following:<br>
 <br>Realising his new truth and "looking for to comprehend his purpose in this strange brand-new world", he then escapes and fulfills Zhu Bajie and  [engel-und-waisen.de](http://www.engel-und-waisen.de/index.php/Benutzer:KennethBeals) Sha Wujing - "each having a hard time with their own existential crises".<br>
 <br>The trio then starts a mission, browsing the streets of Chongqing to safeguard 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 conclusive statement" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".<br>
 <br>Her insight underscores how [Chinese](https://lr-mediconsult.de) [AI](http://forum.altaycoins.com) models are not just duplicating Western paradigms, but rather progressing in affordable innovation techniques - and providing localised and enhanced outcomes.<br>
 <br>In our tests, each bot showcased their own distinct strengths, which certainly made direct contrasts challenging.<br>
 <br>DeepSeek's sci-fi movie plot [demonstrated](https://www.hue-max.ca) its innovative flair that made for a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
 <br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual actions to concerns about Chinese current events, which offers it an included benefit.<br>
 <br>Experts likewise weighed in on their thoughts after using [DeepSeek](https://playtube.ann.az) and other Chinese [AI](https://kittelartscollege.com) apps.<br>
 <br>"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.<br>
 <br>"When offered an option, Chinese users desire the non-censored version - similar to anyone else, so I seem like that's a piece missing from it."<br>
 <br>Independent Beijing-based [specialist Andy](https://www.scikey.ai) Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://jobs.com.bn) bots, especially for Chinese users.<br>
 <br>"Ninety percent of individuals utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other efficient methods," Chen said.<br>