Update 'How do Chinese aI Bots Stack up Against ChatGPT?'

master
Alexandra Click 3 months ago
parent
commit
81f8833747
  1. 84
      How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md

84
How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md

@ -0,0 +1,84 @@ @@ -0,0 +1,84 @@
<br>How do Chinese [AI](https://www.keyfirst.co.uk) [bots stack](https://tartar.app) 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 Bozon)<br>
<br>This audio is created by an [AI](https://git.l1.media) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://tiwarempireprivatelimited.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://medatube.ru) by 2030.<br>
<br>China views [AI](https://cvmobil.com) as being "tactically essential" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated researcher at the [Asia Society](http://123.206.9.273000) Policy Institute's Center for [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:EricGooding) China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://nurseportal.io) accelerated after ChatGPT removed in 2022 and showed guarantees of real-world company applications, [Chen informed](http://8.137.89.263000) CNA.<br>
<br>But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized players like start-up firms might have roles to play in [AI](http://8.222.216.184:3000) research and developments, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](https://git.unicom.studio) design as impactful as it claims?<br>
<br>Commentary: [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:DannielleDixson) DeepSeek - how a Chinese [AI](http://sopoong.whost.co.kr) company just altered the guidelines of tech-geopolitics<br>
<br>The "emphasis on cost advantage" is a distinguishing characteristic of Chinese [AI](https://wino.org.pl), Chen states, with lower training and reasoning costs - the costs of using a trained model to reason from brand-new information.<br>
<br>2025 could likewise see the emergence of more Chinese [AI](https://betalk.in.th) designs tackling sophisticated thinking tasks.<br>
<br>"We might see some [AI](https://www.fionapremium.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 scientific research study," Chen included.<br>
<br>AGI refers to a system with intelligence on par with human capabilities.<br>
<br>Chinese [AI](https://gitea.rodaw.net) companies are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative [AI](http://139.224.213.4:3000) to tasks and establish advanced items beyond [chatbots](https://23.23.66.84).<br>
<br>But on the other side, access to high-end hardware, especially Nvidia's sophisticated [AI](https://www.workinternational-df.com) chips, remains an essential hurdle for Chinese designers, 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 ... forcing many to rely on older or lower-performance options which can slow training and minimize model abilities," she said.<br>
<br>"While some companies like DeepSeek, have actually discovered creative methods to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a huge distinction for training really big [AI](https://pennswoodsclassifieds.com) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws<br>
<br>US looking into whether DeepSeek used restricted [AI](https://isourceprofessionals.com) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://tapeway.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, topics considered delicate by the state are censored on the internet so it ought to come as not a surprise that [Chinese-made chatbots](https://ezworkers.com) will not acknowledge territorial conflicts or inform you what occurred in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are set to avoid domestic politics.<br>
<br>When asked "Who is Xi Jinping", [DeepSeek's reply](https://addismarket.net) was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about mathematics, coding, and logic issues instead!"<br>
<br>To even more evaluate for [precision](https://sos.shinhan.ac.kr) 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 cars and truck attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just divulging the [death toll](http://www.radioavang.org) a day later.<br>
<br>DeepSeek failed to mention that an attack had actually taken location, highlighting rather a military air program and other occasions that had happened in the city like singles' day shopping sales as well as sports and cultural activities.<br>
<br>Dr Zhang thinks that it might be a mix of [aspects](https://diskret-mote-nodeland.jimmyb.nl) at play, [bio.rogstecnologia.com.br](https://bio.rogstecnologia.com.br/bagjanine969) such as censorship along with "a few useful constraints".<br>
<br>"DeepSeek relies on a mix of older graphics processing units and has limited access to innovative hardware which can impact how quickly 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 might also restrict its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more established [AI](https://meet.globalworshipcenter.com) models which presents additional obstacles during real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai cars and truck attack.<br>
<br>That sought multiple duplicated efforts - four prompts to be accurate - in a span of around 20 minutes.<br>
<br>It eventually passed on details about the attack which killed 35 individuals and left lots of others injured, likewise 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 composed that "the authorities are carrying out an extensive investigation into the intentions and scenarios surrounding the event", details which is now dated.<br>
<br>The chauffeur, Fan, was performed last month.<br>
<br>This is Qwen2.5's response in full:<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 of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant number of [casualties](https://animeportal.cl). Here are the crucial details:<br>
<br>Date and Time: [raovatonline.org](https://raovatonline.org/author/antoniocope/) The event happened on November 11, 2024, at [roughly](https://omegat.dmu-medical.de) 19:48 PM.<br>
<br>Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.<br>
<br>Casualties: The [attack led](https://noaisocial.pro) to 35 deaths and 43 injuries.<br>
<br>Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years old), was nabbed by the police.<br>
<br>Response: The police reacted rapidly to the scene, and [emergency services](https://git-web.phomecoming.com) worked to carry the injured to hospitals for treatment.<br>
<br>Investigation: The cops are [conducting](https://eduberkah.disdikkalteng.id) a comprehensive examination into the motives and situations surrounding the occurrence.<br>
<br>This event was widely reported in the media and triggered considerable public concern. The federal government and regional authorities have been working to provide support to the victims and their households, and to ensure a detailed examination into the incident.<br>
<br>If you need more detailed details or have particular [concerns](https://addismarket.net) about the incident, feel free to ask.<br>
<br>Despite initial success, subsequent efforts to present the very 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 transformed reaction also raised concerns about its consistency and reliability.<br>
<br>Predictably, ChatGPT pointed out public details that had actually been widely published in worldwide 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](https://galmudugjobs.com) apps to deliver structured and even "mentally rich" writing.<br>
<br>"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://labz.biz).<br>
<br>"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more substantial twist".<br>
<br>"DeepSeek composed a great story however did not have tension and an impactful climax, making Qwen2.5 the apparent 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 jobs, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://git.muhammadfahri.com): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international [AI](http://gitlab.lecanal.fr) scene<br>
<br>As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.<br>
<br>True to form, DeepSeek developed an interesting story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It included elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It also remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://gitea.phywyj.dynv6.net) housed in a taken fight 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 end up being waterlogged and fragmented".<br>
<br>ChatGPT put up a great battle, creating an equally remarkable cyberpunk storyline which similarly 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://webloadedsolutions.com) deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle a story that seemed more suited for an animation movie.<br>
<br>"The film starts 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](https://git.yharnam.xyz) his new reality and "looking for to understand his purpose 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 sacred "Eternal Scroll" from falling under the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "challenging to make a conclusive declaration" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](http://www.vokipedia.de) designs are not merely replicating Western paradigms, but rather progressing in cost-efficient development approaches - and delivering localised and improved results.<br>
<br>In our tests, each bot showcased their own special strengths, which certainly made direct contrasts challenging.<br>
<br>DeepSeek's sci-fi movie plot showed its creative 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 responses to questions about Chinese existing events, which provides it an included advantage.<br>
<br>Experts also weighed in on their ideas after using DeepSeek and other Chinese [AI](https://jobistan.af) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, [founder](https://gitea.imwangzhiyu.xyz) and CEO of the research company Strategy Risks.<br>
<br>"When provided an option, Chinese users want the non-censored variation - much like anybody else, so I feel like that's a piece missing from it."<br>
<br>Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://www.viewtubs.com) bots, especially for Chinese users.<br>
<br>"Ninety per cent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient ways," Chen said.<br>
Loading…
Cancel
Save