carmacates094/bvbborussiadortmundfansclub
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Carma Cates 2025-02-21 20:34:27 +00:00
commit afba61f662
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](http://8.137.12.29:3000) 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, [wavedream.wiki](https://wavedream.wiki/index.php/User:CedricElston) Chinese startup DeepSeek and [OpenAI's ChatGPT](http://damoa8949.com). (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is generated by an [AI](http://120.48.141.82:3000) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://aquarium.zone) BOOM?<br>
<br>Transforming the nation 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](http://aat.or.tz) by 2030.<br>
<br>China views [AI](http://47.101.139.60) as being "tactically crucial" 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](http://47.101.139.60).<br>
<br>Private and public financial investments in Chinese [AI](http://8.137.58.20:3000) accelerated after ChatGPT took off in 2022 and revealed promises of real-world company applications, Chen informed CNA.<br>
<br>But it was DeepSeek's rise that actually "urged" the idea that smaller sized gamers like start-up companies might have roles to play in [AI](https://tweecampus.com) research and developments, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm [DeepSeek's](http://www.localpay.co.kr) [AI](http://gitlab.solyeah.com) design as [impactful](http://gsend.kr) as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://customerscomm.com) business just changed the guidelines of tech-geopolitics<br>
<br>The "emphasis on expense benefit" is an unique feature of Chinese [AI](http://47.107.126.107:3000), Chen says, with lower training and reasoning costs - the costs of using a trained model to reason from new information.<br>
<br>2025 might likewise see the introduction of more Chinese [AI](http://113.98.201.140:8888) designs tackling sophisticated reasoning tasks.<br>
<br>"We could see some [AI](http://xn--950bz9nf3c8tlxibsy9a.com) companies concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with clinical research study," Chen added.<br>
<br>AGI refers to a system with intelligence on par with human capabilities.<br>
<br>Chinese [AI](https://play.future.al) companies are moving quickly, [experts](https://git.amic.ru) state, building on [DeepSeek's momentum](http://123.56.193.1823000) to come up with their own innovative and [economical](https://consultoresdeproductividad.com) ways to apply generative [AI](https://cvmobil.com) to jobs and establish more sophisticated items beyond chatbots.<br>
<br>But on the flip side, access to high-end hardware, particularly Nvidia's advanced [AI](http://bedfordfalls.live) chips, remains an essential difficulty for Chinese developers, noted 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 capability of Chinese tech companies ... forcing many to count on older or lower-performance alternatives which can slow training and minimize design capabilities," she said.<br>
<br>"While some companies like DeepSeek, have found creative methods to enhance or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge distinction for training huge [AI](https://aijoining.com) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to abide by its laws<br>
<br>US checking out whether DeepSeek utilized limited [AI](http://219.150.88.234:33000) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](https://git.ipmake.me) bots compare against ChatGPT? We put them to the test.<br>
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
<br>In China, topics deemed sensitive by the state are censored on the internet so it must come as no surprise that [Chinese-made chatbots](http://sp001g.dfix.co.kr) will not acknowledge territorial disagreements or [larsaluarna.se](http://www.larsaluarna.se/index.php/User:DominickJulian9) inform you what took place 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 kind of concern yet. Let's chat about math, coding, and reasoning issues rather!"<br>
<br>To even more test for [accuracy](https://39.98.119.14) and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports stadium in the southern Chinese city was at first [heavily](http://dasaram.com) censored on Chinese social media - with authorities only revealing the death toll a day later.<br>
<br>DeepSeek failed to discuss that an attack had occurred, highlighting rather a military air show and other events that had [occurred](http://www.vmeste-so-vsemi.ru) in the city like songs' day shopping sales along with sports and cultural activities.<br>
<br>Dr [Zhang believes](https://asixmusik.com) that it may be a mix of elements at play, such as censorship as well as "a few useful constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing systems and has actually limited access to cutting-edge hardware which can impact how quickly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong concentrate on Chinese-language data may likewise limit its adaptability (to perform) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more established [AI](https://gratisafhalen.be) designs which poses additional challenges during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our concern about the Zhuhai cars and truck attack.<br>
<br>That wanted numerous repeated attempts - four prompts to be precise - in a span of around 20 minutes.<br>
<br>It eventually passed on 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 cops are carrying out an extensive investigation into the motives and scenarios surrounding the event", details which is now outdated.<br>
<br>The chauffeur, Fan, was performed last month.<br>
<br>This is Qwen2.5's reaction in full:<br>
<br>Answer: On Nov 11, 2024, a major and tragic incident occurred in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a [substantial variety](https://www.menacopt.com) of casualties. Here are the key details:<br>
<br>Date and Time: The event occurred on November 11, 2024, at [roughly](https://social.vetmil.com.br) 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 of ages), was apprehended by the cops.<br>
<br>Response: The cops reacted rapidly to the scene, and emergency situation services worked to transport the hurt to health centers for treatment.<br>
<br>Investigation: The police are performing an extensive investigation into the motives and circumstances surrounding the event.<br>
<br>This event was commonly reported in the media and triggered significant public concern. The federal government and regional authorities have actually been working to supply support to the victims and their households, and to ensure a detailed examination into the event.<br>
<br>If you need more detailed details or have specific concerns about the event, feel complimentary to ask.<br>
<br>Despite initial success, subsequent attempts to position the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't 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 pointed out public details that had been extensively published in worldwide news reports at the time of the mishap - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](https://git.goolink.org) apps to deliver structured and even "emotionally abundant" writing.<br>
<br>"DeepSeek-R1 used a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in [AI](https://addify.ae).<br>
<br>"Qwen2.5 provided a story that constructs gradually from curiosity to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more substantial twist".<br>
<br>"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the evident option."<br>
<br>Opinions, however, 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 imaginative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://abstaffs.com): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide [AI](https://awaz.cc) scene<br>
<br>As [journalists](https://jobs.com.bn) 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 film plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.<br>
<br>True to form, DeepSeek developed an appealing storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It consisted of sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It likewise brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](http://114.116.15.227:3000) housed in a stolen battle body", Zhu Bajie as a cyborg bar 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 an excellent battle, developing an equally remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".<br>
<br>"This is a world where [AI](http://wcipeg.com) deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that seemed more fit for an animation film.<br>
<br>"The film starts with the awakening of Sun Wukong within a state-of-the-art research facility situated in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his [brand-new truth](https://socialeconomy4ces-wiki.auth.gr) and "seeking to understand his function in this strange brand-new world", he then [escapes](http://mtmnetwork.co.kr) and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".<br>
<br>The trio then embarks on a quest, [browsing](http://gkpjobs.com) the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the [wrong hands](https://source.futriix.ru).<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "tough to make a conclusive statement" about which bot was best, adding that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](https://disgaeawiki.info) models are not merely reproducing Western paradigms, however rather progressing in cost-effective innovation techniques - and providing localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct contrasts challenging.<br>
<br>DeepSeek's sci-fi movie plot showed its innovative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate actions to questions about Chinese current events, which provides it an added benefit.<br>
<br>Experts likewise weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://39.98.119.14) apps.<br>
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, [founder](https://saghurojobs.com) and CEO of the research Risks.<br>
<br>"When offered an option, Chinese users want the non-censored variation - much like anybody else, so I seem 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](https://speeddating.co.il) bots, especially for Chinese users.<br>
<br>"Ninety percent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient ways," Chen said.<br>