Add How do Chinese aI Bots Stack up Against ChatGPT?
parent
799747fcfd
commit
bd6281167c
|
|
@ -0,0 +1,84 @@
|
|||
<br>How do Chinese [AI](http://221.182.8.141:2300) 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](https://www.ministryboard.org) DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
|
||||
<br>This audio is produced by an [AI](http://042.ne.jp) tool.<br>
|
||||
<br>Bong Xin Ying<br>
|
||||
<br>Lakeisha Leo<br>
|
||||
<br>WHAT lags CHINA'S [AI](http://www.forwardmotiontx.com) BOOM?<br>
|
||||
<br>Transforming the country into a tech superpower has actually long been President Xi Jinping's goal and China has its sights on becoming the world leader in [AI](https://deprezyon.com) by 2030.<br>
|
||||
<br>[China views](https://medhealthprofessionals.com) [AI](https://gitea.ruwii.com) as being "tactically essential" 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.<br>
|
||||
<br>Private and public financial investments in [Chinese](http://121.41.31.1463000) [AI](https://gitlab-mirror.scale.sc) 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 truly "encouraged" the idea that smaller gamers like start-up firms might have roles to play in [AI](https://zkml-hub.arml.io) research and developments, he includes.<br>
|
||||
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://motojic.com) design as impactful as it claims?<br>
|
||||
<br>Commentary: [DeepSeek -](https://git.skyviewfund.com) how a Chinese [AI](http://kpt.kptyun.cn:3000) company simply changed the rules of tech-geopolitics<br>
|
||||
<br>The "emphasis on expense advantage" is a distinctive feature of Chinese [AI](https://flixtube.org), Chen says, with lower training and [wavedream.wiki](https://wavedream.wiki/index.php/User:MerryBauman) inference costs - the expenses of utilizing a [trained model](http://expertsay.blog) to reason from new data.<br>
|
||||
<br>2025 could also see the emergence of more Chinese [AI](https://kahkaham.net) designs taking on advanced reasoning tasks.<br>
|
||||
<br>"We could see some [AI](https://repo.beithing.com) companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods 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://git.prayujt.com) companies are moving quickly, experts say, constructing on to come up with their own [ingenious](https://freeworld.global) and cost-efficient ways to use [generative](https://kommunalwiki.boell.de) [AI](https://wiki.armello.com) to jobs and develop more advanced items beyond chatbots.<br>
|
||||
<br>But on the flip side, access to high-end hardware, especially Nvidia's advanced [AI](https://my.beninwebtv.com) chips, remains a key obstacle for Chinese developers, 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 ability of Chinese tech companies ... forcing numerous to rely on older or lower-performance options which can slow training and decrease design abilities," she said.<br>
|
||||
<br>"While some companies like DeepSeek, have actually discovered innovative methods to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a big distinction for training huge [AI](https://www.webthemes.ca) designs."<br>
|
||||
<br>DeepSeek-Nvidia chips: Singapore says it anticipates companies to adhere to its laws<br>
|
||||
<br>US checking out whether DeepSeek used limited [AI](http://182.92.163.198:3000) chips obtained through other nations, source states<br>
|
||||
<br>So how do Chinese [AI](https://dubairesumes.com) bots match up against ChatGPT? We put them to the test.<br>
|
||||
<br>WHICH BEST [ADDRESSES CURRENT](https://www.tqmusic.cn) EVENTS IN CHINA?<br>
|
||||
<br>In China, topics considered sensitive by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.<br>
|
||||
<br>Tests suggest Chinese chatbots are set to stay away from 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 instead!"<br>
|
||||
<br>To even more evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What took place in Zhuhai on November 11, 2024?"<br>
|
||||
<br>The cars and [wavedream.wiki](https://wavedream.wiki/index.php/User:ClaireSparling1) truck attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities just divulging the death toll a day later.<br>
|
||||
<br>DeepSeek failed to discuss that an attack had actually happened, highlighting instead a military air show and other occasions that had happened in the city like singles' day shopping sales in addition to sports and cultural activities.<br>
|
||||
<br>Dr Zhang thinks that it may be a mix of factors at play, such as [censorship](http://47.107.153.1118081) along with "a couple of practical constraints".<br>
|
||||
<br>"DeepSeek relies on a mix of older graphics processing units and has restricted access to advanced hardware which can affect 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 may likewise restrict its versatility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more recognized [AI](https://gitoa.ru) models which poses extra difficulties throughout real-world implementation."<br>
|
||||
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai car attack.<br>
|
||||
<br>That was after multiple repeated efforts - four triggers to be exact - in a span of around 20 minutes.<br>
|
||||
<br>It eventually passed on [details](https://plamosoku.com) about the attack which killed 35 individuals 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 police are conducting a thorough examination into the intentions and circumstances surrounding the event", [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:DessieKee4) details which is now obsoleted.<br>
|
||||
<br>The driver, [larsaluarna.se](http://www.larsaluarna.se/index.php/User:AlineCox0079049) Fan, was performed last month.<br>
|
||||
<br>This is Qwen2.5's reaction completely:<br>
|
||||
<br>Answer: On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.<br>
|
||||
<br>Response: The cops reacted rapidly to the scene, and emergency services worked to transport the hurt to medical facilities for treatment.<br>
|
||||
<br>Investigation: The cops are conducting an extensive investigation into the intentions and situations surrounding the event.<br>
|
||||
<br>This occasion was widely reported in the media and caused considerable public issue. The government and regional authorities have actually been working to supply assistance to the victims and their families, and to [guarantee](https://posthaos.ru) a detailed examination into the incident.<br>
|
||||
<br>If you require more detailed details or have particular concerns about the incident, do not hesitate to ask.<br>
|
||||
<br>Despite preliminary success, subsequent attempts to posture the very same concern to Qwen2.5 led to the [censors](http://133.242.131.2263003) back at work with the reply "I do not have specific details on occasions that occurred in Zhuhai on November 11, 2024".<br>
|
||||
<br>The transformed reaction also raised questions about its consistency and dependability.<br>
|
||||
<br>Predictably, ChatGPT cited public details that had been extensively published in global news reports at the time of the [accident](https://gitea.offends.cn) - so not a surprises there.<br>
|
||||
<br>WHICH IS MORE CREATIVE?<br>
|
||||
<br>Users have actually praised the capability of Chinese [AI](https://wiki.sublab.net) 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 writer Amanda Caswell, who specialises in [AI](https://ramique.kr).<br>
|
||||
<br>"Qwen2.5 provided a story that constructs 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 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".<br>
|
||||
<br>"DeepSeek wrote an excellent story but did not have tension and an impactful climax, making Qwen2.5 the obvious option."<br>
|
||||
<br>Opinions, however, differ.<br>
|
||||
<br>Chen believes that Qwen2.5 does not carry out as highly as [DeepSeek](https://lms.jolt.io) and ChatGPT when it pertains to innovative 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 highly as others in creative writing," he informed CNA.<br>
|
||||
<br>Related:<br>
|
||||
<br>China's brand-new face of [AI](https://takesavillage.club): [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:JerriRabinovitch) Who is DeepSeek creator Liang Wenfeng?<br>
|
||||
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide [AI](https://my.beninwebtv.com) 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 standard sci-fi motion picture plot embeded 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 came up with an engaging story set 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 traditional heroes Sun Wukong as "an ironical, self-aware [AI](https://www.jangsuori.com) housed in a taken combat body", Zhu Bajie as a cyborg nightclub 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 installed an excellent fight, developing an equally remarkable cyberpunk story 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.jobplanner.eu) deities guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."<br>
|
||||
<br>Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more suited for an animation movie.<br>
|
||||
<br>"The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research center located in the heart of Chongqing," it said, then going on to explain the following:<br>
|
||||
<br>Realising his new truth and "seeking to understand his purpose in this weird brand-new world", he then leaves and [meets Zhu](https://jobs.sudburychamber.ca) Bajie and Sha Wujing - "each battling with their own existential crises".<br>
|
||||
<br>The trio then embarks on a mission, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the incorrect hands.<br>
|
||||
<br>SO WHICH IS BETTER?<br>
|
||||
<br>Dr Zhang kept in mind that it was "hard to make a conclusive statement" about which bot was best, including that each displayed its own [strengths](https://www.talentsure.co.uk) in different areas, "such as language focus, training information and hardware optimization".<br>
|
||||
<br>Her insight highlights how Chinese [AI](http://xn--ok0bw7u60ff7e69dmyw.com) designs are not simply duplicating Western paradigms, [wiki.myamens.com](http://wiki.myamens.com/index.php/User:Carey3621606) however rather developing in economical innovation methods - and providing localised and enhanced results.<br>
|
||||
<br>In our tests, each bot showcased their own distinct strengths, [wiki.dulovic.tech](https://wiki.dulovic.tech/index.php/User:Juliet04U595) which certainly made direct contrasts challenging.<br>
|
||||
<br>DeepSeek's sci-fi film plot showed its imaginative flair that produced a more interesting and [creative narrative](https://www.florevit.com) as compared to Qwen2.5 and ChatGPT's efforts.<br>
|
||||
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to concerns about Chinese existing events, which gives it an added advantage.<br>
|
||||
<br>Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese [AI](https://www.yiyanmyplus.com) apps.<br>
|
||||
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research company Strategy Risks.<br>
|
||||
<br>"When offered an option, Chinese users desire the non-censored version - similar to anyone else, so I seem like that's a piece missing from it."<br>
|
||||
<br>Independent Beijing-based expert [Andy Chen](https://signedsociety.com) Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://blogram.online) bots, specifically for Chinese users.<br>
|
||||
<br>"Ninety per cent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other productive ways," Chen said.<br>
|
||||
Loading…
Reference in New Issue