abbieburr40373/ajirazetu
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Abbie Burr 2025-02-16 19:56:43 +01:00
commit 9ee2f75274
1 changed files with 84 additions and 0 deletions

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

@ -0,0 +1,84 @@
<br>How do Chinese [AI](http://47.101.46.124:3000) bots stack up against ChatGPT? We put them to the test<br>
<br>The heat is on as [China's tech](https://www.kmginseng.com) giants step up their video game after DeepSeek's success.<br>
<br>Alibaba's Qwen2.5-Max chatbot, [Chinese start-up](https://music.lcn.asia) DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is produced by an [AI](https://workbook.ai) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://www.lingualoc.com) BOOM?<br>
<br>Transforming the country into a tech superpower has long been President Xi [Jinping's goal](http://git.the-archive.xyz) and China has its sights on becoming the world leader in [AI](https://vieclamangiang.net) by 2030.<br>
<br>China views [AI](https://git.corp.xiangcms.net) as being "strategically important" and its venture 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 financial investments in Chinese [AI](https://git.prime.cv) accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world business applications, Chen informed CNA.<br>
<br>But it was DeepSeek's increase that actually "encouraged" the concept that smaller sized players like start-up [companies](http://121.40.234.1308899) might have roles to play in [AI](https://mensaceuta.com) research and advancements, he adds.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://skillfilltalent.com) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://sanaldunyam.awardspace.biz) company just changed the rules of tech-geopolitics<br>
<br>The "focus on expense benefit" is a distinguishing characteristic of Chinese [AI](https://spm.social), Chen says, with lower training and inference costs - the expenses of using a trained model to reason from brand-new information.<br>
<br>2025 might also see the development of more Chinese [AI](http://106.14.65.137) designs dealing with sophisticated reasoning tasks.<br>
<br>"We might see some [AI](http://wowonder.technologyvala.com) firms concentrating on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with scientific research study," Chen included.<br>
<br>AGI refers to a system with intelligence on par with human capabilities.<br>
<br>[Chinese](https://gl.vlabs.knu.ua) [AI](https://familytrip.kr) business are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to use generative [AI](https://git.learnzone.com.cn) to tasks and develop more innovative items beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, especially Nvidia's advanced [AI](https://nurseportal.io) chips, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:MaurineMyers) remains a crucial obstacle for Chinese developers, noted 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 business ... requiring numerous to count on older or lower-performance options which can slow training and lower model abilities," she said.<br>
<br>"While some business like DeepSeek, have actually discovered innovative ways to enhance or utilize more fundamental hardware efficiently, obtaining advanced chips still makes a big distinction for training large [AI](http://47.101.46.124:3000) 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://clubamericafansclub.com) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](http://parasite.kicks-ass.org:3000) bots compare against ChatGPT? We put them to the test.<br>
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
<br>In China, topics deemed sensitive by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are configured 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 question yet. Let's chat about math, coding, and reasoning problems rather!"<br>
<br>To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The automobile attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities just divulging the death toll a day later on.<br>
<br>DeepSeek failed to discuss that an attack had actually taken place, highlighting instead 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 thinks that it may be a mix of aspects at play, such as censorship as well as "a few practical constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing units and has limited access to advanced hardware which can affect how rapidly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information may also restrict its adaptability (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more established [AI](http://1cameroon.com) models which postures additional difficulties throughout real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai vehicle attack.<br>
<br>That wanted multiple duplicated attempts - four prompts to be accurate - in a span of around 20 minutes.<br>
<br>It eventually communicated details about the attack which killed 35 individuals and left lots of others injured, also going on to note details like the date and time, [gratisafhalen.be](https://gratisafhalen.be/author/redajosephs/) details about the assailant including his name and age, as well as casualties.<br>
<br>However, it wrote that "the cops are carrying out a thorough examination into the intentions and scenarios surrounding the event", details which is now obsoleted.<br>
<br>The motorist, Fan, was performed last month.<br>
<br>This is Qwen2.5's response in full:<br>
<br>Answer: On Nov 11, 2024, a major and tragic incident in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:<br>
<br>Date and Time: The occurrence took place on November 11, 2024, at around 19:48 PM.<br>
<br>Location: Zhuhai Sports Center, in the Xiangzhou [District](http://enhr.com.tr) of Zhuhai.<br>
<br>Casualties: The attack resulted in 35 deaths and 43 injuries.<br>
<br>Perpetrator: The motorist, determined as Fan Weiqiu (male, [disgaeawiki.info](https://disgaeawiki.info/index.php/User:AntoinetteLizott) 62 years of ages), was nabbed by the police.<br>
<br>Response: The cops responded quickly to the scene, and emergency situation services worked to carry the injured to hospitals for treatment.<br>
<br>Investigation: The authorities are carrying out a comprehensive investigation into the intentions and situations surrounding the event.<br>
<br>This event was extensively reported in the media and triggered considerable public concern. The federal [government](https://fototik.com) and local authorities have been working to provide assistance to the victims and their households, and to make sure a detailed examination into the event.<br>
<br>If you require more detailed details or have specific questions about the occurrence, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent efforts to posture the same question to Qwen2.5 resulted in 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 modified reaction likewise raised concerns about its consistency and reliability.<br>
<br>Predictably, ChatGPT pointed out public details that had been widely released in international news reports at the time of the mishap - so not a surprises there.<br>
<br>WHICH IS MORE [CREATIVE](https://talentocentroamerica.com)?<br>
<br>Users have actually praised the capability of Chinese [AI](https://git.genowisdom.cn) apps to provide structured and even "emotionally abundant" writing.<br>
<br>"DeepSeek-R1 used a story with a more reflective tone and smoother psychological transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](http://101.43.151.191:3000).<br>
<br>"Qwen2.5 provided a story that builds slowly from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more considerable twist".<br>
<br>"DeepSeek wrote a great story but lacked stress and an impactful climax, making Qwen2.5 the evident option."<br>
<br>Opinions, however, differ.<br>
<br>Chen believes 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, but we can likewise see that it is refraining from doing as highly as others in innovative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://pplanb.co.kr): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international [AI](https://yourrecruitmentspecialists.co.uk) scene<br>
<br>As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore impressive, Journey to the West.<br>
<br>True to form, DeepSeek created an interesting storyline 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 sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It likewise remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](https://git2.nas.zggsong.cn:5001) housed in a stolen battle 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".<br>
<br>ChatGPT installed a great fight, coming up with a similarly dramatic cyberpunk storyline which similarly 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://kyigit.kyigd.com:3000) deities rule, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that seemed more suited for an animation movie.<br>
<br>"The movie starts with the awakening of Sun Wukong within a high-tech research center located in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his new reality and "seeking to understand his function in this unusual new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".<br>
<br>The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "difficult to make a conclusive declaration" 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 [AI](http://gitlab.pakgon.com) designs are not just duplicating Western paradigms, however rather evolving in cost-effective innovation methods - and providing localised and improved outcomes.<br>
<br>In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi motion picture plot showed its imaginative 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, offers accurate and factual responses to concerns about Chinese existing occasions, which offers it an [included](https://asromafansclub.com) advantage.<br>
<br>Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese [AI](https://tagreba.org) 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 provided an option, Chinese users desire the non-censored variation - similar to anybody else, so I seem like that's a piece missing out on from it."<br>
<br>Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](http://www.isexsex.com) bots, especially for Chinese users.<br>
<br>"Ninety per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient methods," Chen said.<br>