shereea5271312/gtanet
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Sheree Saragosa 2025-02-21 04:45:34 +00:00
commit 5638efc2cf
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](https://cosplaybook.de) [AI](https://hyg.w-websoft.co.kr) 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. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is produced by an [AI](https://kennetjobs.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://git.pleasantprogrammer.com) BOOM?<br>
<br>Transforming the country into a tech superpower has actually long been President Xi Jinping's goal and China has its sights on ending up being the world leader in [AI](http://122.51.46.213) by 2030.<br>
<br>China views [AI](http://gnu5.hisystem.com.ar) as being "strategically essential" and its venture into the field has 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 in Chinese [AI](https://dubai.risqueteam.com) accelerated after ChatGPT took off in 2022 and showed pledges of real-world business applications, Chen told CNA.<br>
<br>But it was DeepSeek's rise that truly "encouraged" the idea that smaller sized players like [start-up](http://123.206.9.273000) firms might have roles to play in [AI](https://social.netverseventures.com) research and advancements, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](https://www.huntsrecruitment.com) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://116.62.159.194) business simply altered the [guidelines](https://gogs.lnart.com) of tech-geopolitics<br>
<br>The "focus on cost benefit" is a [distinctive feature](https://hellovivat.com) of [Chinese](https://code.3err0.ru) [AI](https://51.75.215.219), Chen states, with lower training and inference expenses - the costs of using a trained model to draw conclusions from brand-new data.<br>
<br>2025 could likewise see the introduction of more Chinese [AI](https://gitea.aambinnes.com) designs taking on sophisticated thinking tasks.<br>
<br>"We could see some [AI](http://gitlab.iyunfish.com) companies concentrating on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods 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.<br>
<br>Chinese [AI](https://www.jobsalert.ai) companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative [AI](https://notitia.tv) to tasks and establish more innovative products beyond chatbots.<br>
<br>But on the flip side, access to high-end hardware, especially Nvidia's innovative [AI](https://freakish.life) chips, remains an essential difficulty for Chinese developers, noted Dr Marina Zhang, an associate professor at [University](https://www.nepaliworker.com) of Technology [Sydney's](http://yanghaoran.space6003) (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) restrict the ability of Chinese tech business ... requiring lots of to count on older or lower-performance alternatives which can slow training and reduce model abilities," she said.<br>
<br>"While some business like DeepSeek, have found imaginative ways to optimize or use more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge difference for training huge [AI](http://www.andreagorini.it) models."<br>
<br>DeepSeek-Nvidia chips: [Singapore](http://193.105.6.1673000) states it expects companies to abide by its laws<br>
<br>US checking out whether DeepSeek used restricted [AI](https://tubechretien.com) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](http://git.spaceio.xyz) bots compare against [ChatGPT](https://www.smfsimple.com)? 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 internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place 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 type of concern yet. Let's chat about math, coding, and logic problems rather!"<br>
<br>To even more test 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 arena in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only revealing the death toll a day later.<br>
<br>DeepSeek failed to mention that an attack had actually taken location, [highlighting](https://coding.activcount.info) instead a military air program and other occasions that had occurred in the city like songs' day shopping sales as well as sports and cultural activities.<br>
<br>Dr Zhang thinks 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 limited access to cutting-edge 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 might also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more recognized [AI](https://git.emalm.com) models which positions additional difficulties during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai automobile attack.<br>
<br>That wanted multiple duplicated attempts - 4 prompts to be precise - in a span of around 20 minutes.<br>
<br>It eventually passed on details about the attack which eliminated 35 individuals and left lots of others hurt, also going on to list details like the date and time, [details](https://gitlab.kitware.com) about the assailant including his name and age, as well as casualties.<br>
<br>However, it wrote that "the authorities are performing a thorough investigation into the intentions and circumstances surrounding the occurrence", details which is now dated.<br>
<br>The driver, Fan, was performed last month.<br>
<br>This is Qwen2.5's action in full:<br>
<br>Answer: On Nov 11, 2024, a significant and awful event took place in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an [automobile](http://111.35.141.53000) into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the essential details:<br>
<br>Date and Time: The event occurred on November 11, 2024, at approximately 19:48 PM.<br>
<br>Location: [yewiki.org](https://www.yewiki.org/User:EltonDalziel) Zhuhai Sports Center, in the [Xiangzhou District](https://git.tissue.works) of Zhuhai.<br>
<br>Casualties: The attack resulted in 35 deaths and 43 injuries.<br>
<br>Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the authorities.<br>
<br>Response: The cops responded rapidly to the scene, and emergency situation services worked to transfer the hurt to hospitals for treatment.<br>
<br>Investigation: The cops are performing a comprehensive investigation into the motives and scenarios surrounding the incident.<br>
<br>This occasion was extensively reported in the media and triggered substantial public concern. The federal government and local authorities have been working to supply assistance to the victims and their families, and to guarantee a detailed examination into the occurrence.<br>
<br>If you need more detailed details or have specific questions about the event, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent attempts to pose the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that occurred in Zhuhai on November 11, 2024".<br>
<br>The transformed reaction also raised [questions](https://quicklancer.bylancer.com) about its consistency and reliability.<br>
<br>Predictably, ChatGPT mentioned [public details](https://ifairy.world) that had been widely published in worldwide report at the time of the mishap - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](https://seconddialog.com) apps to provide structured and even "mentally rich" writing.<br>
<br>"DeepSeek-R1 used a story with a more reflective tone and smoother emotional shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](http://120.78.74.94:3000).<br>
<br>"Qwen2.5 delivered a story that develops slowly from interest to urgency, 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, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".<br>
<br>"DeepSeek wrote a great story however lacked tension and an impactful climax, making Qwen2.5 the evident choice."<br>
<br>Opinions, though, vary.<br>
<br>Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he [informed CNA](https://inspiredcollectors.com).<br>
<br>Related:<br>
<br>China's brand-new face of [AI](http://101.34.87.71): Who is DeepSeek creator Liang [Wenfeng](https://code.thintz.com)?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide [AI](https://www.uaehire.com) 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 basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek created an appealing 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 high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware [AI](https://gitlab.payamake-sefid.com) housed in a stolen battle body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".<br>
<br>ChatGPT set up a good fight, developing an equally significant cyberpunk storyline 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](https://southwales.com) deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that seemed more fit for an animation film.<br>
<br>"The motion picture begins with the awakening of Sun Wukong within a modern research study facility situated 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 comprehend his function in this odd brand-new world", he then leaves and satisfies Zhu Bajie and - "each having problem with their own existential crises".<br>
<br>The trio then embarks on a mission, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the [incorrect hands](https://www.smfsimple.com).<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "tough to make a conclusive statement" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training information and hardware optimization".<br>
<br>Her insight underscores how Chinese [AI](https://www.netrecruit.al) designs are not just duplicating Western paradigms, but rather evolving in cost-efficient development methods - and delivering localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi film plot showed its innovative 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 accurate reactions to concerns about Chinese existing occasions, which provides it an added benefit.<br>
<br>Experts also weighed in on their ideas after using DeepSeek and other Chinese [AI](https://git.mxr612.top) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.<br>
<br>"When provided an option, Chinese users want 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 specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://code.smolnet.org) bots, specifically for Chinese users.<br>
<br>"Ninety percent of people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive ways," Chen said.<br>