adahonner24827/hireforeignworkers
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Ada Honner 2025-04-12 14:26:11 +02:00
parent 95a98d245e
commit 65ee651c62
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://jobsingulf.com) bots stack up against ChatGPT? We put them to the test<br>
<br>The heat is on as giants step up their video game after DeepSeek's [success](https://www.jccer.com2223).<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 generated by an [AI](https://coptr.digipres.org) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://git.kraft-werk.si) BOOM?<br>
<br>Transforming the nation into a tech superpower has long been [President](https://videoflixr.com) Xi Jinping's goal and China has its sights on becoming the world leader in [AI](http://forum.rcsubmarine.ru) by 2030.<br>
<br>China views [AI](http://47.111.127.134) as being "strategically crucial" and its foray 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 financial [investments](https://tylerwesleywilliamson.us) in Chinese [AI](https://gitlab.ccc.org.co) accelerated after ChatGPT removed in 2022 and showed pledges of real-world company applications, Chen informed CNA.<br>
<br>But it was DeepSeek's rise that really "encouraged" the idea that smaller players like start-up companies could have [functions](https://www.freetenders.co.za) to play in [AI](https://diversitycrejobs.com) research and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://shiningon.top) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://sujongsa.net) company just changed the guidelines of tech-geopolitics<br>
<br>The "focus on cost benefit" is a distinctive function of Chinese [AI](https://18plus.fun), Chen says, with lower training and reasoning costs - the expenses of using a trained model to draw conclusions from new information.<br>
<br>2025 might likewise see the introduction of more Chinese [AI](https://zenabifair.com) designs dealing with [innovative](http://120.79.218.1683000) thinking jobs.<br>
<br>"We might see some [AI](https://social.japrime.id) companies focusing on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with clinical research study," Chen [included](https://chat.app8station.com).<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](http://120.77.213.139:3389) companies are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical methods to use generative [AI](https://rrallytv.com) to jobs and establish advanced items beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, especially Nvidia's advanced [AI](http://128.199.175.152:9000) chips, remains an essential difficulty for [Chinese](https://event.genie-go.com) 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) restrict the capability of Chinese tech companies ... requiring many to depend on older or lower-performance options which can slow training and reduce design abilities," she said.<br>
<br>"While some companies like DeepSeek, have actually discovered innovative methods to enhance or use more standard hardware efficiently, obtaining advanced chips still makes a big distinction for training large [AI](http://gitlab.zbqdy666.com) models."<br>
<br>DeepSeek-Nvidia chips: Singapore says it anticipates business to abide by its laws<br>
<br>US looking into whether DeepSeek used limited [AI](http://gitlab.abovestratus.com) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](https://www.shwemusic.com) bots match up against ChatGPT? We put them to the test.<br>
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
<br>In China, topics considered delicate by the state are [censored](https://tube.denthubs.com) on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are programmed to guide clear of domestic politics.<br>
<br>When asked "Who is Xi Jinping", [DeepSeek's](https://supremecarelink.com) reply was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about math, coding, and reasoning issues rather!"<br>
<br>To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The cars and truck attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities only disclosing the death toll a day later.<br>
<br>DeepSeek failed to point out that an attack had actually happened, highlighting instead a military air program and other occasions that had occurred in the city like songs' day shopping sales in addition to sports and [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:JerroldSchiffman) cultural activities.<br>
<br>Dr Zhang thinks that it may be a mix of elements at play, such as [censorship](https://aaalabourhire.com) as well as "a few practical constraints".<br>
<br>"DeepSeek relies on a mix of older graphics processing systems and has actually limited access to advanced hardware which can affect how rapidly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information may likewise restrict its flexibility (to bring out) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more established [AI](https://projectblueberryserver.com) designs which positions extra obstacles throughout real-world implementation."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai car attack.<br>
<br>That sought numerous repeated attempts - 4 triggers to be exact - in a period of around 20 minutes.<br>
<br>It ultimately relayed details about the attack which killed 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.<br>
<br>However, it composed that "the authorities are carrying out a comprehensive investigation into the motives and situations surrounding the event", details which is now dated.<br>
<br>The chauffeur, Fan, was carried out last month.<br>
<br>This is Qwen2.5's response in complete:<br>
<br>Answer: On Nov 11, 2024, a major and tragic incident took place in Zhuhai, China. According to multiple news sources, [gratisafhalen.be](https://gratisafhalen.be/author/chasehuang/) a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the key details:<br>
<br>Date and Time: The [occurrence occurred](https://ipen.com.hk) 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 cops.<br>
<br>Response: The police reacted quickly to the scene, and emergency services worked to transfer the hurt to hospitals for treatment.<br>
<br>Investigation: The cops are conducting a thorough investigation into the motives and scenarios surrounding the incident.<br>
<br>This event was widely reported in the media and triggered significant [public concern](https://wegoemploi.com). The federal government and regional authorities have been working to provide support to the victims and their households, and to ensure a detailed examination into the incident.<br>
<br>If you require more detailed details or have specific questions about the event, feel free to ask.<br>
<br>Despite preliminary success, subsequent efforts to pose the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".<br>
<br>The modified action also raised concerns about its consistency and dependability.<br>
<br>Predictably, ChatGPT cited public details that had been widely published in global news reports at the time of the mishap - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the ability of Chinese [AI](https://ipen.com.hk) apps to provide structured and even "emotionally abundant" writing.<br>
<br>"DeepSeek-R1 offered a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in [AI](https://home.42-e.com:3000).<br>
<br>"Qwen2.5 delivered a story that constructs gradually from curiosity to seriousness, 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, emotionally abundant story with a more considerable twist".<br>
<br>"DeepSeek wrote a great story however did not have tension and an impactful climax, making Qwen2.5 the apparent choice."<br>
<br>Opinions, though, vary.<br>
<br>Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative writing.<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 imaginative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://212.64.10.162:7030): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global [AI](http://git.fmode.cn:3000) 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 fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek developed an interesting story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It included fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It also brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](https://euvisajobs.com) housed in a stolen battle 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 end up being waterlogged and fragmented".<br>
<br>ChatGPT set up a great battle, developing an equally significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".<br>
<br>"This is a world where [AI](http://47.106.205.140:8089) deities rule, corporations change emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that seemed more matched for an animation movie.<br>
<br>"The movie begins with the awakening of Sun Wukong within a state-of-the-art research center situated in the heart of Chongqing," it said, [wiki.whenparked.com](https://wiki.whenparked.com/User:Wade37577327) then going on to explain the following:<br>
<br>Realising his brand-new reality and "seeking to comprehend his purpose in this odd brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".<br>
<br>The trio then embarks on a quest, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "challenging to make a conclusive statement" about which bot was best, including that each [displayed](https://seconddialog.com) its own strengths in various areas, "such as language focus, training data and hardware optimization".<br>
<br>Her [insight highlights](https://snowboardwiki.net) how Chinese [AI](http://git.520hx.vip:3000) models are not just reproducing Western paradigms, but rather evolving in cost-effective development methods - and [delivering localised](https://myjobasia.com) and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.<br>
<br>[DeepSeek's sci-fi](http://121.37.166.03000) movie plot demonstrated its innovative flair that produced a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to [concerns](https://platform.giftedsoulsent.com) about Chinese present occasions, which provides it an added benefit.<br>
<br>Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://supardating.com) apps.<br>
<br>"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.<br>
<br>"When provided 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 expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://www.joboont.in) bots, particularly for Chinese users.<br>
<br>"Ninety per cent of individuals using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive means," Chen said.<br>