tamlawler08863/dandaelitetransportllc
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Tam Lawler 2025-02-15 21:12:01 +01:00
commit 4d0166fa2b
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://forum.tinycircuits.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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/[Sebastien](https://music.worldcubers.com) Bozon)<br>
<br>This audio is [generated](https://git.visualartists.ru) by an [AI](https://forum.tinycircuits.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://sparcle.cn) 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://www.hi-kl.com) by 2030.<br>
<br>China views [AI](https://awaz.cc) as being "strategically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:KeithSpina077) an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://git.andrewnw.xyz) sped up after ChatGPT removed in 2022 and revealed promises of real-world business applications, Chen told CNA.<br>
<br>But it was DeepSeek's increase that truly "encouraged" the concept that smaller sized players like start-up firms could have functions to play in [AI](https://gitea.johannes-hegele.de) research and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](http://123.60.173.13:3000) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://macphersonwiki.mywikis.wiki) company just changed the rules of tech-geopolitics<br>
<br>The "emphasis on cost advantage" is a distinguishing characteristic of Chinese [AI](http://221.131.119.2:10030), Chen says, 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 development of more Chinese [AI](https://www.tobeop.com) models taking on sophisticated reasoning jobs.<br>
<br>"We could see some [AI](http://60.23.29.213:3060) firms concentrating on getting closer to artificial general intelligence (AGI) while others concentrate 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](https://abalone-emploi.ch).<br>
<br>Chinese [AI](http://christianpedia.com) business are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and [cost-efficient](https://agalliances.com) ways to apply generative [AI](https://maxmeet.ru) to tasks and establish more innovative products beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, particularly Nvidia's innovative [AI](http://git.365zuoye.com) chips, remains a crucial hurdle for Chinese developers, 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) restrict the ability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and lower model abilities," she said.<br>
<br>"While some companies like DeepSeek, have actually discovered imaginative methods to optimize or use more fundamental hardware efficiently, obtaining advanced chips still makes a huge distinction for training really big [AI](https://tjoobloom.com) models."<br>
<br>DeepSeek-Nvidia chips: Singapore says it expects business to abide by its laws<br>
<br>US checking out whether DeepSeek utilized restricted [AI](http://124.222.6.97:3000) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](http://gitlab.digital-work.cn) 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 sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred 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 reply was "Sorry, I'm uncertain how to approach this kind 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 same concern: "What happened in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports arena in the city was at first heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later on.<br>
<br>DeepSeek failed to point out that an attack had actually happened, highlighting rather a military air program and other events that had happened 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 aspects at play, such as censorship as well as "a couple of useful constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing units and has restricted access to innovative hardware which can affect how rapidly and extensively 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 data may also restrict its versatility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established [AI](https://gitlab.lycoops.be) designs which positions additional challenges during real-world implementation."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our concern about the Zhuhai vehicle attack.<br>
<br>That wanted numerous repeated attempts - four prompts to be exact - in a period of around 20 minutes.<br>
<br>It eventually communicated details about the attack which killed 35 people and left dozens of others injured, likewise 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 wrote that "the cops are conducting an extensive examination into the intentions and scenarios surrounding the incident", details which is now outdated.<br>
<br>The chauffeur, Fan, was executed last month.<br>
<br>This is Qwen2.5's response in complete:<br>
<br>Answer: On Nov 11, 2024, a major and [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:ViolaTibbs7514) terrible occurrence happened in Zhuhai, China. According to several news sources, a man [named Fan](https://gitr.pro) Weiqiu (樊某, male, 62 years of ages) drove a [vehicle](https://talentrendezvous.com) into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the crucial details:<br>
<br>Date and Time: The event occurred on November 11, 2024, at approximately 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 apprehended by the police.<br>
<br>Response: The police reacted rapidly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.<br>
<br>Investigation: The cops are performing a thorough examination into the motives and situations surrounding the incident.<br>
<br>This occasion was commonly reported in the media and caused significant public issue. The government and regional authorities have actually been working to supply assistance to the victims and their families, and to make sure a detailed examination into the occurrence.<br>
<br>If you require more detailed details or have particular concerns about the event, feel totally free to ask.<br>
<br>Despite initial success, subsequent efforts to position the exact same question to Qwen2.5 led to 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 altered response likewise raised concerns about its consistency and reliability.<br>
<br>Predictably, ChatGPT mentioned public details that had actually been extensively released in worldwide report 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://www.execafrica.com) apps to deliver structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 offered a story with a more introspective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://pakkalljob.com).<br>
<br>"Qwen2.5 provided a story that constructs slowly from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, including that Qwen2.5 [eventually](http://81.70.25.1443000) "crafted a more cinematic, emotionally abundant story with a more significant twist".<br>
<br>"DeepSeek wrote a great story but lacked stress and an impactful climax, making Qwen2.5 the apparent choice."<br>
<br>Opinions, though, vary.<br>
<br>Chen thinks that Qwen2.5 does not carry out as strongly as [DeepSeek](https://www.isinbizden.net) and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, 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](https://gigsonline.co.za): [wiki.rolandradio.net](https://wiki.rolandradio.net/index.php?title=User:RudyRenteria459) Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global [AI](http://182.92.163.198:3000) scene<br>
<br>As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a [fundamental sci-fi](https://seekinternship.ng) motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.<br>
<br>True to form, DeepSeek developed an appealing storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It included intricate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It likewise remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware [AI](http://133.242.131.226:3003) housed in a taken battle body", Zhu Bajie as a cyborg nightclub 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 an excellent fight, coming up with an equally remarkable 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://oakrecruitment.uk) deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this challenge - providing a storyline that seemed more fit for [yewiki.org](https://www.yewiki.org/User:MorrisVillasenor) an animation film.<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, then going on to explain the following:<br>
<br>Realising his new reality and "seeking to comprehend his function in this odd brand-new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".<br>
<br>The trio then embarks on a mission, navigating the streets of Chongqing to secure 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 "difficult 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 data and hardware optimization".<br>
<br>Her insight underscores how Chinese [AI](https://stnav.com) designs are not just duplicating Western paradigms, but rather progressing in cost-effective development approaches - and [delivering localised](http://recruitmentfromnepal.com) and improved results.<br>
<br>In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi film plot demonstrated its innovative flair that made for 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, supplies accurate and accurate reactions to concerns about Chinese present events, which gives it an added advantage.<br>
<br>Experts likewise weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://lifeinsuranceacademy.org) apps.<br>
<br>"DeepSeek is at a drawback 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 - simply like anyone else, so I feel like that's a piece missing from it."<br>
<br>Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://git.wyling.cn) bots, particularly for [forum.pinoo.com.tr](http://forum.pinoo.com.tr/profile.php?id=1323760) Chinese users.<br>
<br>"Ninety percent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient methods," Chen said.<br>