sabinau7570202
/
idiosys
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

master
Sabina Worthy 2025-02-21 02:32:04 +08:00
commit 13e46d1b10
1 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
How-do-Chinese-aI-Bots-Stack-up-Against-ChatGPT%3F.md Normal file

@ -0,0 +1,84 @@
<br>How do Chinese [AI](https://ddsbyowner.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 created by an [AI](https://bld.lat) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://git.foxarmy.org) BOOM?<br>
<br>Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on ending up being the world leader in [AI](https://letustalk.co.in) by 2030.<br>
<br>China views [AI](https://raida-bw.com) as being "strategically important" and [fishtanklive.wiki](https://fishtanklive.wiki/User:DouglasWhitney) its venture into the field has actually been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.<br>
<br>Private and [public investments](http://ptube.site) in Chinese [AI](http://124.221.76.28:13000) accelerated after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen informed CNA.<br>
<br>But it was [DeepSeek's increase](https://vishwakarmacommunity.org) that truly "urged" the concept that smaller sized players like start-up firms could have roles to play in [AI](https://git.lunch.org.uk) research and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://xnxxsex.in) model as impactful as it claims?<br>
<br>Commentary: [DeepSeek -](http://119.130.113.2453000) how a Chinese [AI](https://coptr.digipres.org) company just altered the rules of tech-geopolitics<br>
<br>The "focus on cost benefit" is a distinguishing characteristic of Chinese [AI](https://www.89u89.com), Chen states, with lower training and reasoning costs - the expenses of utilizing a trained model to reason from new information.<br>
<br>2025 could also see the introduction of more Chinese [AI](https://www.app.telegraphyx.ru) models taking on innovative reasoning jobs.<br>
<br>"We might see some [AI](http://4blabla.ru) companies focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate 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](https://gitlab.profi.travel) companies are moving rapidly, experts say, building on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative [AI](https://sss.ung.si) to jobs and [develop advanced](https://gitea.offends.cn) items beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, especially Nvidia's advanced [AI](http://www.larsaluarna.se) chips, remains a key hurdle for Chinese designers, 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 capability of Chinese tech business ... forcing numerous to depend on older or lower-performance options which can slow training and reduce model abilities," she said.<br>
<br>"While some business like DeepSeek, have found imaginative methods to enhance or use more basic hardware efficiently, obtaining innovative chips still makes a huge difference for training extremely large [AI](https://eukariyer.net) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore says it [anticipates companies](https://blazblue.wiki) to comply with its laws<br>
<br>US looking into whether DeepSeek used limited [AI](https://git.camus.cat) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://git.progamma.com.ua) 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 internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what happened in Tiananmen Square in 1989.<br>
<br>Tests recommend Chinese chatbots are set to avoid domestic politics.<br>
<br>When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and reasoning problems instead!"<br>
<br>To further check for accuracy 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 automobile attack outside a sports arena in the southern Chinese city was initially 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 taken place, highlighting rather a military air program and other occasions that had actually [occurred](https://login.discomfort.kz) 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 aspects at play, such as censorship in addition to "a few useful constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing units and has limited access to innovative hardware which can impact how rapidly and extensively the model can be trained or upgraded," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information may likewise limit its adaptability (to carry out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized [AI](https://blackfinn.de) designs which poses extra challenges during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai vehicle attack.<br>
<br>That was after numerous duplicated attempts - 4 prompts to be precise - in a span of around 20 minutes.<br>
<br>It eventually communicated details about the attack which killed 35 individuals and left dozens of others hurt, 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 cops are conducting a comprehensive examination into the intentions and scenarios surrounding the occurrence", [details](https://xn--114-2k0oi50d.com) which is now obsoleted.<br>
<br>The chauffeur, Fan, was executed last month.<br>
<br>This is Qwen2.5's action in full:<br>
<br>Answer: On Nov 11, 2024, a major and tragic occurrence occurred in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the crucial details:<br>
<br>Date and Time: The incident occurred on November 11, 2024, at around 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, identified as Fan Weiqiu (male, 62 years of ages), was collared by the police.<br>
<br>Response: The cops reacted rapidly to the scene, and emergency situation services worked to transport the injured to health centers for treatment.<br>
<br>Investigation: The cops are performing a comprehensive investigation into the motives and circumstances surrounding the incident.<br>
<br>This event was extensively reported in the media and caused considerable public issue. The government and local authorities have been working to provide support to the victims and their families, and to ensure a detailed examination into the incident.<br>
<br>If you need more detailed details or have particular concerns about the occurrence, do not hesitate to ask.<br>
<br>Despite initial success, subsequent efforts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".<br>
<br>The modified reaction also raised concerns about its consistency and [larsaluarna.se](http://www.larsaluarna.se/index.php/User:MaximoJauncey28) dependability.<br>
<br>Predictably, ChatGPT pointed out public details that had actually been widely released in worldwide news reports at the time of the mishap - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](http://gitfrieds.nackenbox.xyz) apps to deliver structured and even "mentally abundant" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in [AI](https://asesordocente.com).<br>
<br>"Qwen2.5 provided a story that develops gradually from curiosity to urgency, keeping the reader engaged. It offers 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, emotionally rich story with a more considerable twist".<br>
<br>"DeepSeek composed a good story but lacked tension and an impactful climax, making Qwen2.5 the obvious choice."<br>
<br>Opinions, however, vary.<br>
<br>Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly as others in creative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://188.68.40.103:3000): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international [AI](http://43.139.182.87:1111) scene<br>
<br>As reporters and writers, [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:IraBvi6733883) we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek created an engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It included sophisticated 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 [standard heroes](https://gogs.lnart.com) Sun Wukong as "a sarcastic, self-aware [AI](https://wiki.lspace.org) housed in a taken combat body", [Zhu Bajie](https://gitea.nasilot.me) 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 become waterlogged and fragmented".<br>
<br>ChatGPT put up an excellent battle, developing a similarly dramatic cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".<br>
<br>"This is a world where [AI](https://www.ministryboard.org) deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that appeared more matched for an animation movie.<br>
<br>"The film begins 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 brand-new truth and "looking for to understand his function in this unusual brand-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 embarks on a mission, navigating the streets of Chongqing to safeguard 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 "tough to make a definitive statement" about which bot was best, including that each displayed its own strengths in various areas, "such as language focus, training information and hardware optimization".<br>
<br>Her insight underscores how Chinese [AI](https://thefreedommovement.ca) models are not just replicating Western paradigms, however rather developing in cost-efficient development methods - and providing localised and [improved](https://www.bolsadetrabajotafer.com) 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 movie plot demonstrated its innovative flair that produced a more appealing 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 existing events, which offers it an included advantage.<br>
<br>Experts also weighed in on their thoughts after using DeepSeek and other [AI](http://tktko.com:3000) 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 a choice, Chinese users want the non-censored version - just like anyone else, so I seem like that's a piece missing out on from it."<br>
<br>Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it [pertains](https://thefreedommovement.ca) to [AI](https://ipmanage.sumedangkab.go.id) bots, particularly for Chinese users.<br>
<br>"Ninety percent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive ways," Chen said.<br>