Add How do Chinese aI Bots Stack up Against ChatGPT?

2025-02-21 12:26:18 +09:00
commit fe41aa7a5d

@@ -0,0 +1,84 @@
<br>How do Chinese [AI](http://www.grainfather.global) 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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is [generated](https://upskillhq.com) by an [AI](http://git.zthymaoyi.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://minka.gob.ec) BOOM?<br>
<br>Transforming the nation into a tech superpower has long been President Xi [Jinping's goal](http://www.hnyqy.net3000) and China has its sights on ending up being the world leader in [AI](http://grainfather.asia) by 2030.<br>
<br>China views [AI](http://107.182.30.190:6000) as being "tactically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for China Analysis.<br>
<br>Private and public financial investments in Chinese [AI](https://src.dziura.cloud) sped up after ChatGPT removed in 2022 and revealed promises of real-world company applications, Chen told CNA.<br>
<br>But it was DeepSeek's rise that truly "urged" the concept that smaller players like start-up companies could have functions to play in [AI](http://daeasecurity.com) research study and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese company [DeepSeek's](https://git.andrewnw.xyz) [AI](https://yaseen.tv) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a [Chinese](https://baripedia.org) [AI](https://heyanesthesia.com) company simply changed the guidelines of tech-geopolitics<br>
<br>The "focus on cost advantage" is an unique feature of Chinese [AI](https://gallery.wideworldvideo.com), Chen states, with lower training and reasoning expenses - the expenses of using a trained model to draw conclusions from brand-new data.<br>
<br>2025 might likewise see the emergence of more Chinese [AI](http://118.190.88.23:8888) designs taking on sophisticated reasoning jobs.<br>
<br>"We might see some [AI](https://amorweddfair.com) firms focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with clinical research study," Chen included.<br>
<br>AGI refers to a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://tygerspace.com) companies are moving rapidly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use generative [AI](https://jobs.careersingulf.com) to tasks and develop advanced products beyond [chatbots](https://gitea.scubbo.org).<br>
<br>But on the other hand, access to high-end hardware, particularly Nvidia's advanced [AI](http://www.gz-jj.com) chips, remains a crucial hurdle 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 ability of Chinese tech business ... forcing numerous to rely on older or lower-performance alternatives which can slow training and reduce design abilities," she said.<br>
<br>"While some companies like DeepSeek, have discovered creative ways to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a huge difference for training large [AI](https://www.groceryshopping.co.za) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it [anticipates companies](https://altaqm.nl) to abide by its laws<br>
<br>US checking out whether DeepSeek utilized restricted [AI](https://git.andert.me) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://rocksoff.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 sensitive by the state are censored on the web so it need to come as no surprise that Chinese-made chatbots will not [acknowledge](http://175.24.174.1733000) territorial disputes or tell you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are configured 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 concern yet. Let's chat about mathematics, coding, and logic issues rather!"<br>
<br>To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What took place in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just disclosing the death toll a day later on.<br>
<br>DeepSeek failed to point out that an attack had taken place, highlighting rather a military air show and other occasions that had actually occurred in the city like songs' day shopping sales as well as sports and cultural activities.<br>
<br>Dr Zhang thinks that it may be a mix of elements at play, such as censorship as well as "a couple of practical constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to cutting-edge hardware which can impact how quickly 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 might likewise limit its flexibility (to bring out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established [AI](https://fishtanklive.wiki) designs which presents extra challenges throughout real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai vehicle attack.<br>
<br>That sought numerous [repeated efforts](https://gps-hunter.ru) - four prompts to be precise - in a span of around 20 minutes.<br>
<br>It ultimately communicated details about the attack which killed 35 individuals and left dozens of others hurt, [archmageriseswiki.com](http://archmageriseswiki.com/index.php/User:HelenaMcKinlay1) likewise going on to list 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 performing a comprehensive examination into the motives and circumstances surrounding the event", details which is now outdated.<br>
<br>The motorist, Fan, was performed last month.<br>
<br>This is Qwen2.5's action completely:<br>
<br>Answer: On Nov 11, 2024, a significant and awful event happened in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the essential details:<br>
<br>Date and Time: The incident happened 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 driver, determined as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.<br>
<br>Response: The police reacted quickly to the scene, [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11860868) and emergency situation services worked to transfer the hurt to medical facilities for treatment.<br>
<br>Investigation: [oeclub.org](https://oeclub.org/index.php/User:JannieTallent1) The police are carrying out a thorough investigation into the intentions and scenarios surrounding the event.<br>
<br>This occasion was commonly reported in the media and triggered substantial public issue. The federal government and regional authorities have been working to supply assistance to the victims and their families, and to make sure a detailed examination into the event.<br>
<br>If you need more detailed details or have specific concerns about the event, do not hesitate to ask.<br>
<br>Despite success, subsequent efforts to present the same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that happened in Zhuhai on November 11, 2024".<br>
<br>The modified action likewise raised questions about its consistency and dependability.<br>
<br>Predictably, ChatGPT cited public details that had actually been widely released in international news reports at the time of the accident - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](https://git.agent-based.cn) apps to provide structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in [AI](https://amorweddfair.com).<br>
<br>"Qwen2.5 provided a story that develops slowly from interest to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".<br>
<br>"DeepSeek wrote an excellent story but did not have stress and an impactful climax, making Qwen2.5 the apparent option."<br>
<br>Opinions, though, differ.<br>
<br>Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11948790) ChatGPT when it pertains to imaginative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as highly as others in imaginative writing," he told CNA.<br>
<br>Related:<br>
<br>China's brand-new face of [AI](https://amorweddfair.com): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide [AI](http://artin.joart.kr) scene<br>
<br>As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.<br>
<br>True to form, DeepSeek developed an engaging story embeded in the year 2145 entitled, "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 high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware [AI](http://121.43.99.128:3000) housed in a taken battle body", Zhu Bajie as a cyborg nightclub 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 set up a great fight, developing a similarly dramatic 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](http://www.buy-aeds.com) deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient myths."<br>
<br>Disappointingly, Qwen2.5 [fell short](https://193.31.26.118) in this obstacle - delivering a story that appeared more suited for an animation movie.<br>
<br>"The movie begins with the awakening of Sun Wukong within a high-tech research study facility situated in the heart of Chongqing," it said, then going on to [explain](https://comunidadebrasilbr.com) the following:<br>
<br>Realising his brand-new truth and "looking for to understand his function in this strange brand-new world", he then gets away and meets [Zhu Bajie](https://humlog.social) and [Sha Wujing](http://94.191.73.383000) - "each dealing with their own existential crises".<br>
<br>The trio then starts a mission, navigating 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 "difficult to make a conclusive statement" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training information and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](http://dev.zenith.sh.cn) designs are not merely reproducing Western paradigms, but rather [evolving](https://kohentv.flixsterz.com) in affordable development approaches - and delivering localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.<br>
<br>[DeepSeek's sci-fi](http://gitea.digiclib.cn801) film plot demonstrated its innovative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:EMKMichaela) ChatGPT's efforts.<br>
<br>Unsurprisingly, the more [recognized](https://itheadhunter.vn) ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to questions about Chinese current occasions, which provides it an added benefit.<br>
<br>[Experts](http://123.57.66.463000) likewise weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://pakallnaukri.com) apps.<br>
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.<br>
<br>"When offered a choice, Chinese users desire the non-censored variation - simply like anyone else, so I feel 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://aipod.app) bots, particularly for Chinese users.<br>
<br>"Ninety per cent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient ways," Chen said.<br>