angelikavalent/satori
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Angelika Valentine
2025-04-07 08:44:28 +09:00
commit 3e1b401faf
1 changed files with 84 additions and 0 deletions
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://git.spitkov.hu) 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 created by an [AI](https://biiut.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://recrutevite.com) BOOM?<br>
<br>Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in [AI](https://www.ayuujk.com) by 2030.<br>
<br>China views [AI](http://team.pocketuniversity.cn) 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](http://218.17.2.103:3000) accelerated after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.<br>
<br>But it was [DeepSeek's increase](https://sebagai.com) that truly "urged" the idea that smaller [sized players](https://git.lewd.wtf) like [start-up firms](https://topstours.com) could have roles to play in [AI](https://www.freeadzforum.com) research and developments, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://115.238.48.210:9015) design as [impactful](https://www.flirtywoo.com) as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://maram.marketing) business just altered the rules of tech-geopolitics<br>
<br>The "emphasis on expense advantage" is a distinguishing characteristic of Chinese [AI](https://dreamtvhd.com), Chen says, with lower training and inference expenses - the expenses of utilizing a trained model to draw conclusions from new information.<br>
<br>2025 might likewise see the introduction of more Chinese [AI](https://www.hi-kl.com) designs taking on sophisticated thinking jobs.<br>
<br>"We might see some [AI](http://git.tbd.yanzuoguang.com) companies concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with scientific research," Chen included.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://116.203.22.201) [companies](http://115.124.96.1793000) are moving rapidly, analysts state, on DeepSeek's momentum to come up with their own [innovative](http://129.211.184.1848090) and affordable methods to apply generative [AI](https://www.schoenerechner.de) to tasks and establish more sophisticated products beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, particularly Nvidia's innovative [AI](http://47.110.248.43:13000) chips, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:Shari085648510) remains a crucial difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at [University](http://47.108.140.33) of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) limit the capability of Chinese tech companies ... requiring lots of to count on older or lower-performance alternatives which can slow training and lower model capabilities," she said.<br>
<br>"While some business like DeepSeek, have actually discovered creative methods to enhance or use more standard hardware effectively, obtaining advanced chips still makes a big distinction for training very big [AI](https://rassi.tv) models."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects business to adhere to its laws<br>
<br>US checking out whether DeepSeek used restricted [AI](https://clik.social) chips obtained through other nations, source says<br>
<br>So how do Chinese [AI](https://git.bloade.com) 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 on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened 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 type of question yet. Let's chat about math, coding, and logic issues rather!"<br>
<br>To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The automobile attack outside a sports arena in the [southern Chinese](https://love63.ru) city was at first greatly censored on Chinese social media - with authorities just divulging the death toll a day later on.<br>
<br>DeepSeek failed to point out that an attack had actually taken place, highlighting rather a military air show and other events that had happened in the city like singles' day shopping sales along with sports and cultural activities.<br>
<br>Dr Zhang believes that it might be a mix of aspects at play, such as censorship along with "a couple of practical constraints".<br>
<br>"DeepSeek relies on a mix of older graphics processing units and has restricted access to innovative hardware which can affect how rapidly and thoroughly the model can be trained or upgraded," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong concentrate on Chinese-language information might also limit its adaptability (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more established [AI](http://175.178.71.89:3000) designs which postures extra difficulties during real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai car attack.<br>
<br>That wanted numerous repeated attempts - 4 [triggers](https://git.skyviewfund.com) to be precise - in a period of around 20 minutes.<br>
<br>It ultimately relayed [details](https://git2.ujin.tech) about the attack which eliminated 35 individuals and left lots of others hurt, likewise going on to list details like the date and time, details about the [assailant including](https://social.oneworldonesai.com) his name and age, in addition to [casualties](https://git.touhou.dev).<br>
<br>However, it composed that "the police are carrying out an extensive examination into the intentions and situations surrounding the incident", details which is now dated.<br>
<br>The chauffeur, Fan, was [performed](https://signedsociety.com) last month.<br>
<br>This is Qwen2.5's action completely:<br>
<br>Answer: On Nov 11, 2024, a significant and awful occurrence happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck 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 roughly 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, determined as Fan Weiqiu (male, 62 years old), was captured by the authorities.<br>
<br>Response: The authorities reacted rapidly to the scene, and emergency services worked to transport the hurt to health centers for [treatment](https://bizad.io).<br>
<br>Investigation: The police are conducting a thorough investigation into the motives and scenarios surrounding the incident.<br>
<br>This occasion was commonly reported in the media and triggered considerable public issue. The federal government and local authorities have been working to provide assistance to the victims and their households, and to make sure a detailed investigation into the occurrence.<br>
<br>If you require more detailed details or have specific questions about the occurrence, do not hesitate to ask.<br>
<br>Despite initial success, subsequent efforts to pose the exact same question to Qwen2.5 led to 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 modified action likewise raised questions about its consistency and reliability.<br>
<br>Predictably, ChatGPT cited public details that had been widely [published](https://codes.tools.asitavsen.com) 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 capability of Chinese [AI](http://203.171.20.94:3000) apps to provide structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://biiut.com).<br>
<br>"Qwen2.5 provided a story that builds gradually from curiosity 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 [eventually](https://www.flughafen-jobs.com) "crafted a more cinematic, mentally rich story with a more substantial twist".<br>
<br>"DeepSeek wrote a great story but did not have tension and an impactful climax, making Qwen2.5 the obvious choice."<br>
<br>Opinions, however, differ.<br>
<br>Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he told CNA.<br>
<br>Related:<br>
<br>China's brand-new face of [AI](https://git.komp.family): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks [international](https://career.ltu.bg) [AI](https://www.egomiliinteriors.com.ng) scene<br>
<br>As reporters and writers, 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](http://gitlab.lecanal.fr) plot set in the [futuristic megacity](https://talentocentroamerica.com) of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek created an appealing storyline embeded 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 sophisticated 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 also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](https://thankguard.com) housed in a stolen combat 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, whose "memory cores become waterlogged and fragmented".<br>
<br>ChatGPT put up a good fight, coming up with a similarly 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://www.jobseeker.my) deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this challenge - delivering a story that seemed more suited for an animation movie.<br>
<br>"The film starts with the awakening of Sun Wukong within a high-tech research facility situated in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his brand-new reality and "looking for to understand his function in this odd brand-new world", he then leaves and meets Zhu Bajie and [Sha Wujing](http://47.97.6.98081) - "each having problem with their own existential crises".<br>
<br>The trio then starts a mission, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "hard to make a conclusive declaration" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](https://redefineworksllc.com) models are not simply reproducing Western paradigms, but rather evolving in cost-effective 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 challenging.<br>
<br>DeepSeek's sci-fi movie plot demonstrated its [innovative flair](https://propveda.com) that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate actions to concerns about Chinese current occasions, which gives it an included advantage.<br>
<br>Experts likewise weighed in on their ideas after using DeepSeek and other Chinese [AI](http://revoltsoft.ru:3000) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.<br>
<br>"When offered an option, Chinese users want the non-censored version - simply like 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](http://web.joang.com:8088) bots, particularly for Chinese users.<br>
<br>"Ninety percent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other efficient methods," Chen said.<br>