martywalton753
/
yanghaoran
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Marty Walton 2025-05-30 04:17:20 +08:00
commit f00e5256a9
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://vcanhire.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 video 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://bizad.io) Bozon)<br>
<br>This audio is created by an [AI](https://gitea.ymyd.site) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](http://4blabla.ru) BOOM?<br>
<br>Transforming the country into a tech superpower has actually long been President Xi [Jinping's objective](https://fmstaffingsource.com) and China has its sights on ending up being the world leader in [AI](http://webheaydemo.co.uk) by 2030.<br>
<br>China views [AI](https://vibestream.tv) as being "tactically crucial" 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](https://careers.mycareconcierge.com) for China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://www.philthejob.nl) sped up after ChatGPT removed in 2022 and showed pledges of real-world service applications, Chen informed CNA.<br>
<br>But it was DeepSeek's increase that truly "urged" the idea that smaller gamers like start-up firms could have roles to play in [AI](https://xinh.pro.vn) research study and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://116.203.22.201) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://13.213.171.136:3000) business just changed the guidelines of tech-geopolitics<br>
<br>The "focus on expense advantage" is an unique feature of Chinese [AI](https://gitea.oo.co.rs), Chen says, with lower training and reasoning costs - the expenses of using a trained design to draw conclusions from brand-new information.<br>
<br>2025 could likewise see the emergence of more Chinese [AI](https://www.garagesale.es) models taking on innovative thinking tasks.<br>
<br>"We might see some [AI](http://139.162.7.140:3000) companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with clinical research," Chen added.<br>
<br>AGI refers to a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://activitypub.software) companies are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to apply generative [AI](http://82.223.37.137) to tasks and develop more advanced products beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, particularly Nvidia's advanced [AI](http://47.120.57.226:3000) chips, remains a key obstacle for Chinese developers, kept in mind 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 companies ... requiring lots of to count on older or lower-performance alternatives which can slow training and decrease model abilities," she said.<br>
<br>"While some companies like DeepSeek, have actually found imaginative methods to enhance or utilize more basic hardware efficiently, obtaining innovative chips still makes a huge difference for training huge [AI](https://gitlab.kicon.fri.uniza.sk) models."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws<br>
<br>US checking out whether DeepSeek utilized [restricted](https://1.214.207.4410333) [AI](https://deadreckoninggame.com) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](http://58.34.54.46:9092) bots match up against [ChatGPT](https://wellandfitnessgn.co.kr)? We put them to the test.<br>
<br>WHICH BEST [ADDRESSES CURRENT](http://orcz.com) EVENTS IN CHINA?<br>
<br>In China, subjects 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 disputes or tell you what occurred in Tiananmen Square in 1989.<br>
<br>Tests recommend 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 type of concern yet. Let's chat about math, coding, and reasoning issues rather!"<br>
<br>To even more evaluate for precision 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 vehicle attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just revealing the death toll a day later on.<br>
<br>DeepSeek failed to mention that an attack had taken place, highlighting instead a military air show and other events that had happened in the city like songs' day [shopping sales](http://121.196.13.116) 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 couple of useful constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing systems and has limited access to advanced hardware which can affect how rapidly and extensively the model can be trained or upgraded," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information might also restrict its adaptability (to carry out) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more recognized [AI](https://alapcari.com) models which postures extra challenges 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 was after numerous duplicated attempts - 4 prompts to be precise - in a span of around 20 minutes.<br>
<br>It ultimately communicated details about the attack which eliminated 35 people and left lots of others injured, likewise going on to note details like the date and time, details about the [assailant including](https://careers.ebas.co.ke) his name and age, along with casualties.<br>
<br>However, it wrote that "the police are carrying out an extensive examination into the intentions and circumstances surrounding the incident", details which is now obsoleted.<br>
<br>The chauffeur, Fan, was carried out last month.<br>
<br>This is Qwen2.5's reaction in complete:<br>
<br>Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle 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 incident happened on November 11, 2024, at roughly 19:48 PM.<br>
<br>Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.<br>
<br>Casualties: The [attack led](http://115.238.142.15820182) to 35 deaths and 43 injuries.<br>
<br>Perpetrator: The chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was by the cops.<br>
<br>Response: The police reacted quickly to the scene, and emergency services worked to [transfer](https://www.lizyum.com) the injured to medical facilities for treatment.<br>
<br>Investigation: The cops are conducting an extensive examination into the intentions and situations surrounding the incident.<br>
<br>This occasion was extensively reported in the media and [larsaluarna.se](http://www.larsaluarna.se/index.php/User:Shasta58P4) triggered considerable public issue. The federal government and local authorities have been working to supply support to the victims and their families, and to ensure a detailed investigation into the occurrence.<br>
<br>If you need more detailed details or have particular questions about the incident, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent attempts to posture the very same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that took place in Zhuhai on November 11, 2024".<br>
<br>The modified response also raised concerns about its consistency and dependability.<br>
<br>Predictably, ChatGPT cited public details that had actually been commonly published in worldwide news reports at the time of the accident - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have praised the capability of Chinese [AI](https://gitea.elkerton.ca) apps to provide structured and even "mentally abundant" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in [AI](https://hellovivat.com).<br>
<br>"Qwen2.5 provided a story that builds gradually from interest to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more substantial twist".<br>
<br>"DeepSeek wrote a great story however did not have tension and an impactful climax, making Qwen2.5 the evident choice."<br>
<br>Opinions, however, vary.<br>
<br>Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise see that it is refraining from doing as highly as others in creative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://code.snapstream.com): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global [AI](https://openedu.com) scene<br>
<br>As [reporters](https://express-work.com) and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the [classic](https://zamhi.net) Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek came up with an appealing 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 consisted of 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 also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](http://git.appedu.com.tw:3080) housed in a taken battle body", [Zhu Bajie](https://www.jjldaxuezhang.com) 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 end up being waterlogged and fragmented".<br>
<br>ChatGPT put up a good battle, 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://germanjob.eu) deities rule, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this challenge - providing a story that seemed more matched for an animation film.<br>
<br>"The motion picture starts with the awakening of Sun Wukong within a modern research study center situated in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his new truth and "looking for to comprehend his purpose in this weird new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".<br>
<br>The trio then starts a mission, browsing the [streets](http://8.134.61.1073000) of Chongqing to secure the sacred "Eternal Scroll" from falling under the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "challenging to make a definitive statement" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".<br>
<br>Her [insight highlights](https://foris.gr) how Chinese [AI](http://lesstagiaires.com) models are not just replicating Western paradigms, however rather progressing in affordable development approaches - and providing localised and enhanced results.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi movie plot showed its innovative flair that made for a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to concerns about Chinese present occasions, which provides it an added benefit.<br>
<br>Experts also [weighed](http://www.jobteck.co.in) in on their ideas after utilizing DeepSeek and other Chinese [AI](http://media.clear2work.com.au) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," kept in [mind Isaac](http://gagetaylor.com) Stone Fish, creator and CEO of the research study company Strategy Risks.<br>
<br>"When given an option, Chinese users want the non-censored variation - much like anybody else, so I seem like that's a piece missing from it."<br>
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://noinai.com) bots, especially for Chinese users.<br>
<br>"Ninety per cent of people using the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive means," Chen said.<br>