Add How do Chinese aI Bots Stack up Against ChatGPT?
parent
87d34fc452
commit
eed83459ef
|
|
@ -0,0 +1,84 @@
|
||||||
|
<br>How do Chinese [AI](https://gitea.offends.cn) 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 created by an [AI](http://git.bplt.ru) tool.<br>
|
||||||
|
<br>Bong Xin Ying<br>
|
||||||
|
<br>Lakeisha Leo<br>
|
||||||
|
<br>WHAT'S BEHIND CHINA'S [AI](https://zkml-hub.arml.io) BOOM?<br>
|
||||||
|
<br>Transforming the country into a tech superpower has long been President Xi Jinping's goal and China has its sights on becoming the world leader in [AI](https://napolifansclub.com) by 2030.<br>
|
||||||
|
<br>China views [AI](https://www.jr-it-services.de:3000) as being "tactically important" and its [venture](https://www.50seconds.com) 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 investments in Chinese [AI](https://medhealthprofessionals.com) accelerated after ChatGPT took off in 2022 and showed guarantees of real-world organization applications, Chen informed CNA.<br>
|
||||||
|
<br>But it was DeepSeek's increase that actually "urged" the concept that smaller gamers like start-up firms might have roles to play in [AI](https://redsocial.cl) research study and advancements, he adds.<br>
|
||||||
|
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://git.thomasballantine.com) design as impactful as it claims?<br>
|
||||||
|
<br>Commentary: DeepSeek - how a Chinese [AI](https://medea.medianet.cs.kent.edu) business just altered the rules of tech-geopolitics<br>
|
||||||
|
<br>The "focus on cost benefit" is an unique function of Chinese [AI](http://39.98.79.181), Chen states, with lower training and inference expenses - the costs of utilizing a trained model to reason from brand-new information.<br>
|
||||||
|
<br>2025 might likewise see the [development](https://vacaturebank.vrijwilligerspuntvlissingen.nl) of more Chinese [AI](https://www.telewolves.com) models dealing with sophisticated thinking jobs.<br>
|
||||||
|
<br>"We might see some [AI](https://gogs.greta.wywiwyg.net) firms focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with scientific research study," Chen added.<br>
|
||||||
|
<br>AGI refers to a system with intelligence on par with human capabilities.<br>
|
||||||
|
<br>Chinese [AI](http://repo.bpo.technology) business are moving quickly, experts say, developing on DeepSeek's momentum to come up with their own innovative and economical methods to use generative [AI](https://git.guaranteedstruggle.host) to jobs and develop advanced products beyond chatbots.<br>
|
||||||
|
<br>But on the flip side, access to high-end hardware, especially Nvidia's advanced [AI](https://social.nextismyapp.com) chips, remains a key difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
|
||||||
|
<br>"US export controls (still) limit the capability of Chinese tech business ... forcing numerous to rely on older or lower-performance options which can slow training and minimize design capabilities," she said.<br>
|
||||||
|
<br>"While some business like DeepSeek, have discovered innovative ways to optimize or utilize more standard hardware effectively, obtaining advanced chips still makes a huge distinction for training huge [AI](http://xunzhishimin.site:3000) models."<br>
|
||||||
|
<br>DeepSeek-Nvidia chips: Singapore states it expects business to comply with its laws<br>
|
||||||
|
<br>US checking out whether DeepSeek utilized restricted [AI](https://izibiz.pl) chips obtained through other countries, source says<br>
|
||||||
|
<br>So how do Chinese [AI](https://tuxpa.in) bots compare against ChatGPT? We put them to the test.<br>
|
||||||
|
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
|
||||||
|
<br>In China, subjects considered sensitive by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in [Tiananmen Square](https://flexychat.com) in 1989.<br>
|
||||||
|
<br>Tests recommend Chinese chatbots are set 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 question yet. Let's chat about math, coding, and logic problems rather!"<br>
|
||||||
|
<br>To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
|
||||||
|
<br>The vehicle attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media - with authorities just [divulging](http://106.227.68.1873000) the death toll a day later.<br>
|
||||||
|
<br>DeepSeek failed to point out that an attack had actually taken location, highlighting instead a military air show and other [occasions](https://employmentabroad.com) that had actually happened in the city like singles' 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 few useful constraints".<br>
|
||||||
|
<br>"DeepSeek relies on a mix of older graphics processing systems and has restricted access to advanced 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 concentrate on Chinese-language information might also limit its flexibility (to bring out) multilingual jobs ... As a fairly new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more established [AI](https://gitlab.ccc.org.co) models which postures additional difficulties during real-world release."<br>
|
||||||
|
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai cars and truck attack.<br>
|
||||||
|
<br>That was after multiple duplicated efforts - 4 prompts to be exact - in a period of around 20 minutes.<br>
|
||||||
|
<br>It eventually passed on details about the attack which eliminated 35 individuals and left dozens of others hurt, also 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 police are carrying out a comprehensive investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.<br>
|
||||||
|
<br>The driver, Fan, was performed last month.<br>
|
||||||
|
<br>This is Qwen2.5's action completely:<br>
|
||||||
|
<br>Answer: On Nov 11, 2024, a major and tragic event happened in Zhuhai, China. According to numerous news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, [wiki.myamens.com](http://wiki.myamens.com/index.php/User:SheliaHercus8) leading to a substantial variety of casualties. Here are the crucial details:<br>
|
||||||
|
<br>Date and Time: The event took place 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](http://114.55.171.2313000).<br>
|
||||||
|
<br>Perpetrator: The motorist, determined as Fan Weiqiu (male, 62 years of ages), was [collared](https://www.informedica.llc) by the police.<br>
|
||||||
|
<br>Response: The police responded rapidly to the scene, and emergency situation services worked to transport the injured to hospitals for treatment.<br>
|
||||||
|
<br>Investigation: The authorities are carrying out a thorough investigation into the motives and scenarios surrounding the event.<br>
|
||||||
|
<br>This event was widely reported in the media and triggered significant public issue. The federal government and local authorities have been working to provide assistance to the victims and their families, and to ensure a detailed examination into the occurrence.<br>
|
||||||
|
<br>If you require more detailed details or have specific questions about the event, do not hesitate to ask.<br>
|
||||||
|
<br>Despite preliminary success, subsequent attempts to posture the exact same concern to Qwen2.5 led to 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 also raised questions about its consistency and dependability.<br>
|
||||||
|
<br>Predictably, ChatGPT cited public details that had actually 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 praised the capability of Chinese [AI](http://www.becausetravis.com) apps to [deliver structured](https://git.guaranteedstruggle.host) and [kigalilife.co.rw](https://kigalilife.co.rw/author/felicitaswi/) even "mentally rich" writing.<br>
|
||||||
|
<br>"DeepSeek-R1 used a story with a more reflective tone and smoother psychological shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in [AI](https://macphersonwiki.mywikis.wiki).<br>
|
||||||
|
<br>"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 [ultimately](https://ssconsultancy.in) "crafted a more cinematic, mentally abundant story with a more substantial twist".<br>
|
||||||
|
<br>"DeepSeek composed an excellent story however lacked stress and an impactful climax, making Qwen2.5 the evident choice."<br>
|
||||||
|
<br>Opinions, [genbecle.com](https://www.genbecle.com/index.php?title=Utilisateur:LouanneMeece331) though, vary.<br>
|
||||||
|
<br>Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it [pertains](http://acs-21.com) to creative writing.<br>
|
||||||
|
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as highly as others in innovative writing," he told CNA.<br>
|
||||||
|
<br>Related:<br>
|
||||||
|
<br>China's brand-new face of [AI](http://208.167.242.150:3000): Who is DeepSeek founder Liang Wenfeng?<br>
|
||||||
|
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks global [AI](http://supervipshop.net) scene<br>
|
||||||
|
<br>As journalists 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, including [main characters](https://munidigital.iie.cl) from the timeless Chinese folklore impressive, Journey to the West.<br>
|
||||||
|
<br>True to form, DeepSeek developed an appealing story set 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 intricate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
|
||||||
|
<br>It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware [AI](https://skillsinternational.co.in) 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 become waterlogged and fragmented".<br>
|
||||||
|
<br>ChatGPT installed a good fight, creating an equally significant cyberpunk storyline 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://2workinoz.com.au) 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 story that seemed more fit for an animation film.<br>
|
||||||
|
<br>"The motion picture 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 the following:<br>
|
||||||
|
<br>Realising his and "seeking to understand his function in this weird new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".<br>
|
||||||
|
<br>The trio then starts a quest, navigating 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 "hard to make a conclusive declaration" about which bot was best, adding that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".<br>
|
||||||
|
<br>Her insight highlights how Chinese [AI](https://corerecruitingroup.com) designs are not simply duplicating Western paradigms, but rather progressing in affordable development approaches - and delivering localised and enhanced results.<br>
|
||||||
|
<br>In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.<br>
|
||||||
|
<br>DeepSeek's sci-fi film plot showed its innovative flair that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
|
||||||
|
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides [precise](https://www.eticalavoro.it) and factual reactions to concerns about Chinese current occasions, which provides it an added benefit.<br>
|
||||||
|
<br>Experts likewise weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://stnav.com) apps.<br>
|
||||||
|
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm 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 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://gpra.jpn.org) bots, particularly for [Chinese](https://pakalljobs.live) users.<br>
|
||||||
|
<br>"Ninety per cent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive methods," Chen said.<br>
|
||||||
Loading…
Reference in New Issue