britneysif9525
/
harmonymart
1
0
Code Issues Packages Projects Wiki

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

master
Britney Courtney 5 months ago
commit 692b4fbc8d
1 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File

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

@ -0,0 +1,84 @@
<br>How do Chinese [AI](https://hitechjobs.me) bots stack up against ChatGPT? We put them to the test<br>
<br>The heat is on as [China's tech](https://www.belizetalent.com) giants step up their game after DeepSeek's success.<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](http://bertogram.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://rugraf.ru) BOOM?<br>
<br>Transforming the country into a tech superpower has long been President Xi Jinping's goal and China has its sights on ending up being the world leader in [AI](https://aubameyangclub.com) by 2030.<br>
<br>China views [AI](http://git.yang800.cn) as being "tactically important" 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 financial investments in Chinese [AI](http://124.221.255.92) accelerated after ChatGPT removed in 2022 and showed pledges of real-world service applications, [genbecle.com](https://www.genbecle.com/index.php?title=Utilisateur:QHKGerman64153) Chen told CNA.<br>
<br>But it was DeepSeek's rise that truly "urged" the idea that smaller sized gamers like start-up [companies](http://acs-21.com) could have functions to play in [AI](https://www.hb9lc.org) research study and advancements, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://34.236.28.152) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://gogs.eldarsoft.com) business simply changed the guidelines of tech-geopolitics<br>
<br>The "emphasis on cost benefit" is a distinctive function of [Chinese](https://223.130.175.1476501) [AI](https://gitea.potatox.net), Chen says, with lower training and inference expenses - the costs of using a trained design to reason from new data.<br>
<br>2025 could also see the introduction of more Chinese [AI](http://124.221.255.92) designs taking on [advanced reasoning](https://video.clicktruths.com) tasks.<br>
<br>"We could see some [AI](http://lophas.com) firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research study," Chen included.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://pandatube.de) business are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use generative [AI](https://wiki.uqm.stack.nl) to jobs and develop more [innovative products](https://git.gumoio.com) beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, especially Nvidia's sophisticated [AI](http://120.79.27.232:3000) chips, remains an essential obstacle for Chinese designers, kept in mind Dr Marina Zhang, an associate professor 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 lots of to rely on older or lower-performance alternatives which can slow training and lower design abilities," she said.<br>
<br>"While some companies like DeepSeek, have found innovative ways to enhance or use more fundamental hardware effectively, obtaining innovative chips still makes a big difference for training large [AI](http://120.196.85.174:3000) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws<br>
<br>US looking into whether DeepSeek utilized limited [AI](http://git.jihengcc.cn) chips obtained through other nations, source states<br>
<br>So how do Chinese [AI](https://tv.360climatechange.com) bots compare 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 on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial [disputes](http://63.32.145.226) or inform you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest 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 type of concern yet. Let's chat about math, coding, and reasoning issues instead!"<br>
<br>To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What happened in Zhuhai on November 11, 2024?"<br>
<br>The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities just disclosing the death toll a day later on.<br>
<br> failed to discuss that an attack had occurred, highlighting instead a military air show and other events that had actually occurred 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 elements at play, such as censorship in addition to "a few practical constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing systems and has limited access to innovative hardware which can impact how rapidly and extensively the design can be trained or upgraded," she said, indicating existing US export curbs on China.<br>
<br>"Its strong concentrate on Chinese-language information may also limit its flexibility (to bring out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established [AI](http://47.111.127.134) designs which postures additional challenges during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai car attack.<br>
<br>That wanted several repeated efforts - four triggers to be precise - in a span of around 20 minutes.<br>
<br>It eventually communicated details about the attack which killed 35 people and left dozens of others injured, also going on to note 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 authorities are performing a comprehensive investigation into the motives and circumstances surrounding the occurrence", details which is now obsoleted.<br>
<br>The chauffeur, Fan, was executed last month.<br>
<br>This is Qwen2.5's reaction in full:<br>
<br>Answer: On Nov 11, 2024, a significant and terrible incident took place in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a significant 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 resulted in 35 deaths and 43 injuries.<br>
<br>Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.<br>
<br>Response: The police responded quickly to the scene, and emergency situation services worked to transfer the injured to medical facilities for treatment.<br>
<br>Investigation: The authorities are carrying out an extensive investigation into the motives and [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11857434) circumstances surrounding the event.<br>
<br>This occasion was commonly reported in the media and caused substantial public concern. The government and local authorities have actually been working to offer assistance to the victims and their families, and to guarantee a detailed investigation into the occurrence.<br>
<br>If you need more detailed details or have specific concerns about the event, do not hesitate to ask.<br>
<br>Despite initial success, subsequent attempts to position 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 took place in Zhuhai on November 11, 2024".<br>
<br>The transformed action also raised concerns about its consistency and reliability.<br>
<br>Predictably, ChatGPT pointed out public details that had been widely published in international news reports 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](https://git.penwing.org) apps to deliver structured and even "mentally abundant" writing.<br>
<br>"DeepSeek-R1 offered a story with a more reflective tone and smoother psychological shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in [AI](https://git.mbyte.dev).<br>
<br>"Qwen2.5 delivered a story that builds gradually from interest to seriousness, keeping the reader engaged. It provides an unexpected 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, emotionally rich story with a more considerable twist".<br>
<br>"DeepSeek wrote a good story but did not have stress and an impactful climax, making Qwen2.5 the obvious option."<br>
<br>Opinions, though, differ.<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 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](https://topdubaijobs.ae): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global [AI](http://gitlab.ifsbank.com.cn) 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 standard sci-fi motion picture plot [embeded](https://ka4nem.ru) in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek developed an interesting storyline 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 intricate 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 likewise remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://gitlab.vp-yun.com) housed in a stolen fight body", Zhu Bajie as a cyborg club owner "drowning in financial obligation 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 battle, [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2672496) developing a similarly 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](https://wishjobs.in) deities guideline, corporations change 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 motion picture starts with the awakening of Sun Wukong within a state-of-the-art research study center 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 weird brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".<br>
<br>The trio then starts a quest, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from [falling](https://www.jjldaxuezhang.com) into the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "tough to make a definitive declaration" about which bot was best, including that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".<br>
<br>Her insight underscores how Chinese [AI](https://git.qiucl.cn) models are not simply duplicating Western paradigms, however rather evolving in cost-efficient development approaches - 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 creative flair that produced a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to concerns about Chinese current occasions, which provides it an included benefit.<br>
<br>Experts also weighed in on their thoughts after using DeepSeek and other Chinese [AI](https://coopervigrj.com.br) 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 provided an option, Chinese users desire the non-censored version - just like anybody else, so I feel 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://sdongha.com) bots, specifically for Chinese users.<br>
<br>"Ninety percent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive methods," Chen said.<br>
Write Preview
Loading…
Cancel
Save