Add How do Chinese aI Bots Stack up Against ChatGPT?
commit
aa6d50cfbe
84
How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md
Normal file
84
How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md
Normal file
@ -0,0 +1,84 @@
|
||||
<br>How do Chinese [AI](http://47.106.228.113:3000) 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 startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
|
||||
<br>This audio is produced by an [AI](https://git.flandre.net) tool.<br>
|
||||
<br>Bong Xin Ying<br>
|
||||
<br>Lakeisha Leo<br>
|
||||
<br>WHAT'S BEHIND CHINA'S [AI](https://git.gilgoldman.com) BOOM?<br>
|
||||
<br>Transforming the country into a tech superpower has actually long been President Xi [Jinping's goal](https://voyostars.com) and China has its sights on becoming the world leader in [AI](https://abalone-emploi.ch) by 2030.<br>
|
||||
<br>[China views](https://www.vadio.com) [AI](https://dev-members.writeappreviews.com) as being "tactically essential" and its foray into the field has actually been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.<br>
|
||||
<br>Private and public financial investments in Chinese [AI](https://git.yuhong.com.cn) sped up after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.<br>
|
||||
<br>But it was DeepSeek's rise that really "urged" the idea that smaller players like start-up companies could have roles to play in [AI](https://git.bwnetwork.us) research study and advancements, he includes.<br>
|
||||
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://git.huxiukeji.com) design as impactful as it claims?<br>
|
||||
<br>Commentary: [bytes-the-dust.com](https://bytes-the-dust.com/index.php/User:Alexandria39G) DeepSeek - how a Chinese [AI](https://www.friend007.com) company just altered the rules of tech-geopolitics<br>
|
||||
<br>The "focus on expense benefit" is a distinguishing characteristic of Chinese [AI](http://101.200.33.64:3000), Chen says, with lower training and reasoning expenses - the costs of utilizing a [trained design](http://zhangsheng1993.tpddns.cn3000) to reason from new data.<br>
|
||||
<br>2025 might also see the development of more Chinese [AI](https://git.apps.calegix.net) designs tackling sophisticated thinking tasks.<br>
|
||||
<br>"We might see some [AI](http://gitlab.fuxicarbon.com) firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with scientific research," Chen added.<br>
|
||||
<br>AGI describes a system with intelligence on par with human abilities.<br>
|
||||
<br>[Chinese](https://skillsvault.co.za) [AI](http://101.200.33.64:3000) companies are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative [AI](https://git.alenygam.com) to jobs and establish advanced products beyond chatbots.<br>
|
||||
<br>But on the other hand, access to high-end hardware, especially Nvidia's innovative [AI](http://git.bplt.ru) chips, remains a key hurdle for Chinese designers, [wavedream.wiki](https://wavedream.wiki/index.php/User:ClaribelOrosco5) 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) restrict the ability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and decrease design abilities," she said.<br>
|
||||
<br>"While some business like DeepSeek, have found innovative methods to enhance or utilize more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge difference for training large [AI](http://193.105.6.167:3000) models."<br>
|
||||
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws<br>
|
||||
<br>US checking out whether DeepSeek utilized restricted [AI](http://pplanb.co.kr) chips obtained through other nations, source states<br>
|
||||
<br>So how do Chinese [AI](http://vk-mix.ru) 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 deemed sensitive by the state are censored on the internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.<br>
|
||||
<br>Tests recommend Chinese chatbots are set 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 math, coding, and reasoning problems rather!"<br>
|
||||
<br>To further evaluate for precision and self-censorship, we asked DeepSeek-R1, [wiki.dulovic.tech](https://wiki.dulovic.tech/index.php/User:FidelBatt531106) Qwen2.5 and ChatGPT the same concern: "What took place 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 networks - with authorities only revealing the death toll a day later on.<br>
|
||||
<br>[DeepSeek](https://git.purplepanda.cc) failed to point out that an attack had happened, highlighting rather a military air program and other occasions that had taken place in the city like songs' day shopping sales as well as sports and [cultural activities](https://crossdark.net).<br>
|
||||
<br>Dr Zhang thinks that it might be a mix of aspects at play, such as censorship as well as "a couple of practical constraints".<br>
|
||||
<br>"DeepSeek depends on a mix of older graphics processing systems and has limited access to advanced hardware which can impact how rapidly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.<br>
|
||||
<br>"Its strong focus on Chinese-language information might also restrict its versatility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more recognized [AI](http://git.morpheu5.net) designs which positions extra difficulties during real-world release."<br>
|
||||
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai vehicle attack.<br>
|
||||
<br>That was after several duplicated attempts - 4 triggers to be exact - in a span of around 20 minutes.<br>
|
||||
<br>It eventually passed on details about the attack which killed 35 individuals and left dozens of others injured, likewise going on to list details like the date and [yewiki.org](https://www.yewiki.org/User:MaisieRoldan5) time, [larsaluarna.se](http://www.larsaluarna.se/index.php/User:HelenTennyson48) details about the assailant including his name and age, in addition to casualties.<br>
|
||||
<br>However, it wrote that "the authorities are performing an extensive investigation into the motives and scenarios surrounding the event", details which is now obsoleted.<br>
|
||||
<br>The chauffeur, Fan, was carried out last month.<br>
|
||||
<br>This is Qwen2.5's action in complete:<br>
|
||||
<br>Answer: On Nov 11, 2024, a significant and tragic incident occurred in Zhuhai, China. According to several news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:<br>
|
||||
<br>Date and Time: The event happened 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 driver, determined as Fan Weiqiu (male, 62 years of ages), was captured by the police.<br>
|
||||
<br>Response: The cops reacted quickly to the scene, and [emergency situation](https://git.apps.calegix.net) services worked to transfer the injured to medical facilities for treatment.<br>
|
||||
<br>Investigation: The authorities are carrying out an extensive examination into the motives and circumstances surrounding the event.<br>
|
||||
<br>This event was widely reported in the media and caused substantial public concern. The federal government and [regional authorities](http://git.huxiukeji.com) have been working to provide support to the victims and their families, and to guarantee a detailed examination into the event.<br>
|
||||
<br>If you require more detailed details or have specific concerns about the occurrence, feel totally free to ask.<br>
|
||||
<br>Despite initial success, [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:JoyHauk5511) subsequent attempts to posture the same question to Qwen2.5 led to 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 also raised questions about its consistency and reliability.<br>
|
||||
<br>Predictably, [ChatGPT cited](http://mirae.jdtsolution.kr) public details that had been extensively released in international news reports at the time of the mishap - so no surprises there.<br>
|
||||
<br>WHICH IS MORE CREATIVE?<br>
|
||||
<br>Users have praised the ability of Chinese [AI](http://wdz.imix7.com:13131) apps to deliver structured and even "mentally rich" writing.<br>
|
||||
<br>"DeepSeek-R1 used a story with a more introspective tone and smoother psychological shifts for a well-paced story," composed tech writer Amanda Caswell, who [specialises](https://gitea.shoulin.net) in [AI](https://movie.nanuly.kr).<br>
|
||||
<br>"Qwen2.5 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 "crafted a more cinematic, emotionally abundant story with a more substantial twist".<br>
|
||||
<br>"DeepSeek wrote a good story however did not have tension and an impactful climax, making Qwen2.5 the evident option."<br>
|
||||
<br>Opinions, however, differ.<br>
|
||||
<br>Chen thinks that Qwen2.5 does not carry out as highly as [DeepSeek](https://govtpakjobz.com) 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 imaginative writing," he told CNA.<br>
|
||||
<br>Related:<br>
|
||||
<br>China's brand-new face of [AI](https://library.kemu.ac.ke): Who is DeepSeek founder Liang Wenfeng?<br>
|
||||
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide [AI](http://162.14.117.234:3000) 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 set 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 appealing story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
|
||||
<br>It included elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
|
||||
<br>It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://copyright-demand-letter.com) housed in a stolen fight body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".<br>
|
||||
<br>ChatGPT installed a good fight, 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://gitea.shoulin.net) deities guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."<br>
|
||||
<br>Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that appeared more suited for an animation movie.<br>
|
||||
<br>"The movie 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 reality and "seeking to understand his function in this weird brand-new world", he then escapes and fulfills Zhu Bajie and [wiki.dulovic.tech](https://wiki.dulovic.tech/index.php/User:StefanValentino) Sha Wujing - "each having a hard time with their own existential crises".<br>
|
||||
<br>The trio then starts a mission, navigating the streets of [Chongqing](http://chillibell.com) to secure the sacred "Eternal Scroll" from falling under the incorrect hands.<br>
|
||||
<br>SO WHICH IS BETTER?<br>
|
||||
<br>Dr Zhang noted that it was "challenging to make a conclusive declaration" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training information and hardware optimization".<br>
|
||||
<br>Her insight underscores how Chinese [AI](https://digital-field.cn:50443) designs are not merely duplicating Western paradigms, however rather progressing in economical development techniques - and delivering localised and enhanced results.<br>
|
||||
<br>In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.<br>
|
||||
<br>[DeepSeek's sci-fi](https://www.cbtfmytube.com) movie plot demonstrated its innovative flair that produced a more engaging 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 precise and accurate reactions to questions about Chinese present events, which offers it an included advantage.<br>
|
||||
<br>Experts also weighed in on their thoughts after utilizing DeepSeek and other [Chinese](https://dlya-nas.com) [AI](https://gitlab.ccc.org.co) apps.<br>
|
||||
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research company Strategy Risks.<br>
|
||||
<br>"When offered a choice, Chinese users want the non-censored variation - simply like anyone 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](https://kaykarbar.com) bots, specifically for Chinese users.<br>
|
||||
<br>"Ninety percent of people using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive means," Chen said.<br>
|
Loading…
Reference in New Issue
Block a user