commit
dc6e2fbeb1
@ -0,0 +1,84 @@
|
||||
<br>How do Chinese [AI](https://globalhospitalitycareer.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 Bozon)<br>
|
||||
<br>This audio is produced by an [AI](http://123.57.66.46:3000) tool.<br>
|
||||
<br>Bong Xin Ying<br>
|
||||
<br>Lakeisha Leo<br>
|
||||
<br>WHAT'S BEHIND CHINA'S [AI](http://154.9.255.198:3000) 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](https://www.assistantcareer.com) by 2030.<br>
|
||||
<br>China views [AI](http://gitea.smartscf.cn:8000) as being "strategically essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy [Institute's](http://sites-git.zx-tech.net) Center for China Analysis.<br>
|
||||
<br>Private and public investments in Chinese [AI](https://www.lizyum.com) accelerated after took off in 2022 and revealed guarantees of real-world service applications, Chen told CNA.<br>
|
||||
<br>But it was DeepSeek's increase that really "urged" the idea that smaller sized players like start-up firms could have functions to play in [AI](https://pioneerayurvedic.ac.in) research and advancements, he adds.<br>
|
||||
<br>'A lot is up in the air': Is [Chinese firm](http://120.79.7.1223000) DeepSeek's [AI](https://www.cdlcruzdasalmas.com.br) design as impactful as it claims?<br>
|
||||
<br>Commentary: DeepSeek - how a Chinese [AI](https://privamaxsecurity.co.ke) company just altered the guidelines of tech-geopolitics<br>
|
||||
<br>The "focus on expense benefit" is a [distinguishing characteristic](http://117.50.100.23410080) of Chinese [AI](https://git.tasu.ventures), Chen states, with lower training and inference costs - the expenses of using a trained design to reason from new information.<br>
|
||||
<br>2025 might also see the introduction of more Chinese [AI](https://xpressrh.com) designs tackling innovative reasoning tasks.<br>
|
||||
<br>"We could see some [AI](https://jobsubscribe.com) companies focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with scientific research," Chen included.<br>
|
||||
<br>AGI describes a system with intelligence on par with human capabilities.<br>
|
||||
<br>Chinese [AI](https://bcde.ru) [business](https://git.andert.me) are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective ways to use generative [AI](https://igazszavak.info) to jobs and establish advanced products beyond chatbots.<br>
|
||||
<br>But on the other side, access to high-end hardware, especially Nvidia's innovative [AI](https://www.rybalka.md) chips, remains a key hurdle for Chinese designers, kept in mind Dr Marina Zhang, an associate teacher at University of [Technology Sydney's](http://47.116.130.49) (UTS) Australia-China Relations Institute.<br>
|
||||
<br>"US export controls (still) limit the capability of Chinese tech business ... requiring lots of to rely on older or lower-performance options which can slow training and reduce design abilities," she said.<br>
|
||||
<br>"While some companies like DeepSeek, have discovered imaginative ways to optimize or use more fundamental hardware effectively, obtaining innovative chips still makes a huge difference for training really large [AI](http://mengqin.xyz:3000) designs."<br>
|
||||
<br>DeepSeek-Nvidia chips: Singapore states it anticipates business to abide by its laws<br>
|
||||
<br>US checking out whether DeepSeek used limited [AI](https://spotlessmusic.com) chips obtained through other nations, source says<br>
|
||||
<br>So how do Chinese [AI](https://social.vetmil.com.br) bots compare against ChatGPT? We put them to the test.<br>
|
||||
<br>WHICH BEST [ADDRESSES CURRENT](http://gitlab.signalbip.fr) EVENTS IN CHINA?<br>
|
||||
<br>In China, subjects deemed sensitive by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.<br>
|
||||
<br>Tests suggest [Chinese chatbots](https://armconnection.com) are programmed to avoid 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 problems rather!"<br>
|
||||
<br>To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What happened in Zhuhai on November 11, 2024?"<br>
|
||||
<br>The car attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities only divulging the death toll a day later on.<br>
|
||||
<br>DeepSeek failed to point out that an attack had actually happened, highlighting instead a military air program and other occasions that had taken place in the city like songs' day shopping sales along with sports and cultural activities.<br>
|
||||
<br>Dr Zhang thinks that it might be a mix of elements at play, such as censorship along with "a few practical constraints".<br>
|
||||
<br>"DeepSeek depends on a mix of older graphics processing systems and has restricted access to innovative hardware which can affect 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 concentrate on Chinese-language data may also restrict its flexibility (to bring out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more established [AI](https://prantle.com) models which positions extra challenges throughout real-world release."<br>
|
||||
<br>When it [pertained](http://1688dome.com) to Qwen2.5, Alibaba's chatbot surprisingly addressed our concern about the Zhuhai cars and truck attack.<br>
|
||||
<br>That sought several repeated attempts - 4 triggers to be precise - in a period of around 20 minutes.<br>
|
||||
<br>It ultimately passed on details about the attack which eliminated 35 individuals and left dozens of others injured, [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:Alisia1875) also going on to list details like the date and time, [kousokuwiki.org](http://kousokuwiki.org/wiki/%E5%88%A9%E7%94%A8%E8%80%85:MoniqueMerrick7) details about the assailant including his name and age, in addition to casualties.<br>
|
||||
<br>However, it wrote that "the police are carrying out an extensive examination into the motives and scenarios surrounding the occurrence", details which is now dated.<br>
|
||||
<br>The motorist, [pipewiki.org](https://pipewiki.org/wiki/index.php/User:BrigetteWhitmore) Fan, was performed last month.<br>
|
||||
<br>This is Qwen2.5's action completely:<br>
|
||||
<br>Answer: On Nov 11, 2024, a major and terrible event took place in Zhuhai, [wakewiki.de](https://www.wakewiki.de/index.php?title=Benutzer:AlexWoolnough3) China. According to multiple news sources, a man [named Fan](https://ayjmultiservices.com) Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the key 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 resulted in 35 deaths and 43 injuries.<br>
|
||||
<br>Perpetrator: [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:AlfieAmar1857) The chauffeur, [identified](http://unired.zz.com.ve) as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.<br>
|
||||
<br>Response: The cops reacted rapidly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.<br>
|
||||
<br>Investigation: The police are performing a comprehensive examination into the intentions and circumstances surrounding the incident.<br>
|
||||
<br>This event was commonly reported in the media and triggered considerable public concern. The federal government and local authorities have been working to supply assistance to the [victims](https://code.nwcomputermuseum.org.uk) and their households, and to guarantee a detailed examination into the event.<br>
|
||||
<br>If you require more [detailed details](http://git.zonaweb.com.br3000) or have particular concerns about the occurrence, do not hesitate to ask.<br>
|
||||
<br>Despite preliminary success, subsequent attempts to position the very same concern 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 transformed response likewise raised questions about its [consistency](https://tagreba.org) and dependability.<br>
|
||||
<br>Predictably, ChatGPT mentioned public details that had been [commonly published](https://flexychat.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 [ability](https://freeads.cloud) of Chinese [AI](https://willingjobs.com) apps to deliver structured and even "emotionally abundant" writing.<br>
|
||||
<br>"DeepSeek-R1 offered 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://quickservicesrecruits.com).<br>
|
||||
<br>"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unexpected 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, mentally abundant story with a more substantial twist".<br>
|
||||
<br>"DeepSeek wrote a good story but did not have stress and an impactful climax, making Qwen2.5 the evident option."<br>
|
||||
<br>Opinions, though, vary.<br>
|
||||
<br>Chen believes that Qwen2.5 does not perform 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, but we can also see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.<br>
|
||||
<br>Related:<br>
|
||||
<br>China's brand-new face of [AI](http://kiwoori.com): [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11951897) Who is DeepSeek founder Liang Wenfeng?<br>
|
||||
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide [AI](http://1688dome.com) 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 film](https://git.xiaoya360.com) plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, [Journey](http://sites-git.zx-tech.net) to the West.<br>
|
||||
<br>True to form, DeepSeek created an interesting 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 fancy 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](https://schubach-websocket.hopto.org) Sun Wukong as "an ironical, self-aware [AI](https://wiki.asexuality.org) 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 good battle, coming up with a similarly significant cyberpunk story 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://catvcommunity.com.tr) deities guideline, corporations change emperors and cybernetic implants are as common as ancient myths."<br>
|
||||
<br>Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more fit for an animation film.<br>
|
||||
<br>"The film begins with the awakening of Sun Wukong within a state-of-the-art research facility located in the heart of Chongqing," it said, then going on to explain the following:<br>
|
||||
<br>Realising his brand-new truth and "looking for to understand his purpose in this strange brand-new world", he then gets away and meets Zhu Bajie and [wiki.whenparked.com](https://wiki.whenparked.com/User:LatashaRutledge) Sha Wujing - "each dealing with their own existential crises".<br>
|
||||
<br>The trio then embarks on a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the wrong hands.<br>
|
||||
<br>SO WHICH IS BETTER?<br>
|
||||
<br>Dr Zhang kept in mind that it was "challenging to make a definitive statement" about which bot was best, including that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".<br>
|
||||
<br>Her insight underscores how Chinese [AI](http://98.27.190.224) models are not just replicating Western paradigms, however rather progressing in economical innovation approaches - and providing localised and improved outcomes.<br>
|
||||
<br>In our tests, each bot showcased their own distinct strengths, which certainly made direct contrasts challenging.<br>
|
||||
<br>DeepSeek's sci-fi film plot demonstrated its imaginative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
|
||||
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and accurate actions to questions about Chinese existing occasions, which offers it an added advantage.<br>
|
||||
<br>Experts also weighed in on their ideas after using DeepSeek and other Chinese [AI](https://git.schdbr.de) apps.<br>
|
||||
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.<br>
|
||||
<br>"When provided an option, Chinese users desire the non-censored variation - similar to anybody else, so I feel like that's a piece missing out on from it."<br>
|
||||
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](http://117.50.100.234:10080) bots, specifically for Chinese users.<br>
|
||||
<br>"Ninety per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other efficient ways," Chen said.<br>
|
||||
Loading…
Reference in new issue