lorriwoolery04/liubin
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Lorri Woolery 2025-02-27 00:45:50 +02:00
commit b9a3981b10
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://www.dailynaukri.pk) bots stack up against ChatGPT? We put them to the test<br>
<br>The heat is on as [China's tech](http://chkkv.cn3000) 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://elitevacancies.co.za) Bozon)<br>
<br>This audio is generated by an [AI](http://gitea.infomagus.hu) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](http://skyfffire.com:3000) 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://vieclam.tuoitrethaibinh.vn) by 2030.<br>
<br>China views [AI](https://dev.ncot.uk) as being "strategically essential" and its venture into the field has been "years in the making", said Chen Qiheng, an associated [scientist](https://qdate.ru) at the Asia Society Policy Institute's Center for China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://gitlab.ccc.org.co) sped up after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen told CNA.<br>
<br>But it was DeepSeek's rise that really "encouraged" the concept that smaller gamers like start-up firms might have [functions](http://207.180.250.1143000) to play in [AI](http://sdongha.com) research study and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://musicplayer.hu) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://epcblind.org) business simply altered the guidelines of tech-geopolitics<br>
<br>The "focus on cost benefit" is a distinct function of Chinese [AI](https://chancefinders.com), Chen says, with lower training and reasoning costs - the expenses of utilizing a trained design to draw conclusions from brand-new information.<br>
<br>2025 could likewise see the development of more Chinese [AI](http://code.exploring.cn) designs taking on sophisticated reasoning jobs.<br>
<br>"We could see some [AI](https://git.wo.ai) companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and integrate them with clinical research," Chen added.<br>
<br>AGI describes a system with intelligence on par with human capabilities.<br>
<br>Chinese [AI](https://videopromotor.com) business are moving rapidly, analysts state, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:Joshua8632) building on DeepSeek's momentum to come up with their own innovative and to apply generative [AI](http://39.105.203.187:3000) to jobs and establish more sophisticated products beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, especially Nvidia's advanced [AI](https://www.homebasework.net) chips, remains an essential difficulty for Chinese designers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) limit the capability of Chinese tech companies ... forcing many to depend on older or lower-performance alternatives which can slow training and lower model capabilities," she said.<br>
<br>"While some companies like DeepSeek, have discovered innovative ways to optimize or utilize more basic hardware effectively, obtaining advanced chips still makes a huge difference for training large [AI](https://gitcode.cosmoplat.com) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws<br>
<br>US checking out whether DeepSeek used restricted [AI](https://www.ontheballpersonnel.com.au) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://asicwiki.org) 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 delicate by the state are [censored](https://chutpatti.com) on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in [Tiananmen Square](https://ramique.kr) in 1989.<br>
<br>Tests suggest Chinese chatbots are programmed 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 question yet. Let's chat about math, coding, and reasoning problems instead!"<br>
<br>To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What took place in Zhuhai on November 11, 2024?"<br>
<br>The vehicle attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only divulging the death toll a day later.<br>
<br>DeepSeek failed to point out that an attack had taken place, highlighting rather a military air show and other events that had happened in the city like songs' day [shopping sales](https://tuxpa.in) 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 along with "a few practical constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact 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 concentrate on Chinese-language information may also limit its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established [AI](https://tiwarempireprivatelimited.com) designs which positions additional difficulties throughout real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our concern about the Zhuhai automobile attack.<br>
<br>That was after numerous duplicated attempts - 4 prompts to be exact - in a span of around 20 minutes.<br>
<br>It ultimately relayed details about the attack which killed 35 people and left dozens of others injured, likewise going on to list 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 conducting a thorough examination into the intentions and situations surrounding the occurrence", details which is now obsoleted.<br>
<br>The motorist, Fan, was carried out last month.<br>
<br>This is Qwen2.5's response in full:<br>
<br>Answer: On Nov 11, [surgiteams.com](https://surgiteams.com/index.php/User:CameronG89) 2024, a significant and tragic event took place in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the crucial details:<br>
<br>Date and Time: The incident 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 motorist, determined as Fan Weiqiu (male, 62 years old), was apprehended by the authorities.<br>
<br>Response: The police reacted quickly to the scene, and emergency situation services worked to transport the hurt to health centers for treatment.<br>
<br>Investigation: The cops are performing a thorough investigation into the intentions and scenarios surrounding the event.<br>
<br>This event was widely reported in the media and triggered considerable public concern. The federal government and local authorities have been working to provide support to the victims and their families, and to guarantee a detailed investigation into the event.<br>
<br>If you require more detailed details or [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:MiquelAer064) have particular concerns about the event, feel totally free to ask.<br>
<br>Despite initial success, subsequent efforts to pose the same question to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on occasions that occurred in Zhuhai on November 11, 2024".<br>
<br>The modified reaction also raised concerns about its [consistency](https://tweecampus.com) and reliability.<br>
<br>Predictably, ChatGPT cited public details that had actually been widely released in global 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](http://httelecom.com.cn:3000) apps to provide structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 used a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, [genbecle.com](https://www.genbecle.com/index.php?title=Utilisateur:AnnaBoxer61535) who specialises in [AI](https://karjerosdienos.vilniustech.lt).<br>
<br>"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".<br>
<br>"DeepSeek composed a good story however lacked stress and an impactful climax, making Qwen2.5 the obvious option."<br>
<br>Opinions, though, vary.<br>
<br>Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to innovative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's brand-new face of [AI](https://tubechretien.com): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international [AI](https://cosplaybook.de) scene<br>
<br>As [journalists](http://gitlab.flyingmonkey.cn8929) and writers, we needed 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 in the futuristic megacity of Chongqing, featuring main [characters](https://wiki.idealirc.org) from the traditional Chinese folklore epic, [Journey](http://106.55.3.10520080) to the West.<br>
<br>True to form, DeepSeek came up with an interesting story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It included sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It likewise remarkably reimagined standard heroes Sun Wukong as "an ironical, self-aware [AI](https://git.devinmajor.com) housed in a taken battle body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, [it-viking.ch](http://it-viking.ch/index.php/User:Muhammad9849) whose "memory cores end up being waterlogged and fragmented".<br>
<br>ChatGPT set up a great fight, coming up with a similarly remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".<br>
<br>"This is a world where [AI](https://boonbac.com) deities guideline, corporations change emperors and cybernetic implants are as typical as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that seemed more fit for an animation movie.<br>
<br>"The movie begins with the awakening of Sun Wukong within a modern research facility located in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his brand-new reality and "seeking to understand his function in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".<br>
<br>The trio then starts a mission, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "hard to make a conclusive statement" about which bot was best, adding that each showed its own strengths in different locations, "such as language focus, training data and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](http://47.119.160.181:3000) models are not merely duplicating Western paradigms, but rather evolving in economical development methods - and delivering localised and improved results.<br>
<br>In our tests, each bot showcased their own distinct strengths, which certainly made [direct contrasts](https://wiki.armello.com) challenging.<br>
<br>DeepSeek's sci-fi motion picture plot demonstrated its creative flair that made for 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, supplies precise and factual reactions to concerns about Chinese present events, which offers it an added advantage.<br>
<br>Experts likewise weighed in on their thoughts after utilizing DeepSeek and other Chinese [AI](http://www.xn--1-2n1f41hm3fn0i3wcd3gi8ldhk.com) apps.<br>
<br>"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.<br>
<br>"When provided an option, Chinese users want the non-censored variation - just like anyone else, so I feel like that's a piece missing out on from it."<br>
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://jskenglish.com) bots, particularly for Chinese users.<br>
<br>"Ninety percent of people utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive methods," Chen said.<br>