kelley50i73393/chaowebserver
1
0
Code Issues Packages Projects Wiki

Add 'How do Chinese aI Bots Stack up Against ChatGPT?'

Kelley Pontiff 2025-02-07 02:58:11 -06:00
commit be4d87d1cc
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://service.aicloud.fit:50443) 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.keliuyun.com:55676) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT lags CHINA'S [AI](https://njspmaca.in) 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://git.thunraz.se) by 2030.<br>
<br>China views [AI](https://git.snaile.de) as being "strategically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for [it-viking.ch](http://it-viking.ch/index.php/User:Dianna01H6) China Analysis.<br>
<br>Private and public financial investments in [Chinese](https://adverts-socials.com) [AI](https://tube.denthubs.com) accelerated after ChatGPT took off in 2022 and revealed promises of applications, Chen told CNA.<br>
<br>But it was DeepSeek's rise that actually "encouraged" the idea that smaller sized gamers like start-up firms could have roles to play in [AI](http://116.204.119.171:3000) research study and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](https://upskillhq.com) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://www.unotravel.co.kr) business just altered the guidelines of tech-geopolitics<br>
<br>The "emphasis on cost benefit" is a distinguishing characteristic of Chinese [AI](https://littlebigempire.com), Chen says, with lower training and inference [costs -](https://minka.gob.ec) the expenses of utilizing a trained model to reason from new information.<br>
<br>2025 could likewise see the introduction of more Chinese [AI](http://123.60.67.64) designs taking on innovative reasoning tasks.<br>
<br>"We might see some [AI](http://8.222.216.184:3000) firms focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research study," Chen included.<br>
<br>AGI refers to a system with intelligence on par with human capabilities.<br>
<br>Chinese [AI](https://social-lancer.com) business are moving rapidly, [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:LawerenceIsenber) analysts say, developing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative [AI](https://sound.co.id) to jobs and develop more advanced products beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, especially Nvidia's advanced [AI](https://www.pkjobs.store) chips, remains a key obstacle for Chinese designers, noted Dr Marina Zhang, an associate professor at [University](https://thegoldenalbatross.com) of Technology Sydney's (UTS) [Australia-China](https://socials.chiragnahata.is-a.dev) Relations Institute.<br>
<br>"US export controls (still) limit the ability of Chinese tech companies ... forcing lots of to count on older or lower-performance alternatives which can slow training and decrease model capabilities," she said.<br>
<br>"While some companies like DeepSeek, have found creative methods to optimize or use more fundamental hardware effectively, obtaining advanced chips still makes a big difference for training huge [AI](http://bristol.rackons.com) models."<br>
<br>DeepSeek-Nvidia chips: Singapore says it expects business to adhere to its laws<br>
<br>US checking out whether DeepSeek used limited [AI](http://playtube.ythomas.fr) chips obtained through other nations, source says<br>
<br>So how do Chinese [AI](https://bartists.info) 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 delicate by the state are censored on the web so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place in Tiananmen Square in 1989.<br>
<br>Tests suggest 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 concern yet. Let's chat about math, coding, and reasoning issues rather!"<br>
<br>To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and [larsaluarna.se](http://www.larsaluarna.se/index.php/User:DominiqueCurmi) ChatGPT the very same question: "What happened in Zhuhai on November 11, 2024?"<br>
<br>The automobile attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only divulging the death toll a day later.<br>
<br>DeepSeek failed to point out that an attack had actually occurred, highlighting instead a military air program and other occasions that had occurred in the city like singles' day shopping sales along with sports and cultural activities.<br>
<br>Dr Zhang believes that it might be a mix of factors at play, such as censorship as well as "a few useful constraints".<br>
<br>"DeepSeek relies on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact how rapidly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language data may also limit its adaptability (to bring out) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more recognized [AI](http://116.198.225.84:3000) designs which presents additional challenges during real-world implementation."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our concern about the Zhuhai automobile attack.<br>
<br>That wanted several repeated attempts - 4 prompts to be exact - in a period of around 20 minutes.<br>
<br>It eventually communicated details about the attack which killed 35 people and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.<br>
<br>However, it wrote that "the authorities are performing an extensive investigation into the intentions and circumstances surrounding the occurrence", [pediascape.science](https://pediascape.science/wiki/User:KristanLightfoot) details which is now dated.<br>
<br>The motorist, Fan, was executed last month.<br>
<br>This is Qwen2.5's response completely:<br>
<br>Answer: On Nov 11, 2024, a major and tragic occurrence took place in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the essential details:<br>
<br>Date and Time: The event took place 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 resulted in 35 deaths and 43 injuries.<br>
<br>Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years old), was collared by the police.<br>
<br>Response: The police reacted quickly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.<br>
<br>Investigation: The cops are carrying out an extensive examination into the intentions and scenarios surrounding the event.<br>
<br>This event was commonly reported in the media and triggered considerable public issue. The government and local authorities have been working to offer support to the victims and their households, and to make sure a detailed investigation 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, subsequent efforts 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 events that occurred in Zhuhai on November 11, 2024".<br>
<br>The modified reaction also raised questions about its consistency and reliability.<br>
<br>Predictably, ChatGPT cited public details that had been commonly published in international news reports at the time of the mishap - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the capability of Chinese [AI](https://www.flytteogfragttilbud.dk) apps to deliver structured and even "emotionally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://portalwe.net).<br>
<br>"Qwen2.5 delivered a story that develops slowly from interest to seriousness, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:WinstonNajera5) adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more considerable twist".<br>
<br>"DeepSeek wrote an excellent story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice."<br>
<br>Opinions, though, differ.<br>
<br>Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as highly as others in imaginative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://www.hb9lc.org): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide [AI](https://social.sktorrent.eu) scene<br>
<br>As journalists and authors, [demo.qkseo.in](http://demo.qkseo.in/profile.php?id=995449) we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, [Journey](https://socialcoin.online) 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 combines with quantum computing".<br>
<br>It included fancy settings [- smoggy](http://49.235.101.2443001) skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware [AI](https://git.andert.me) housed in a taken combat body", Zhu Bajie as a cyborg club 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 installed](https://code.balsoft.ru) a good fight, developing a similarly significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".<br>
<br>"This is a world where [AI](https://fogel-finance.org) deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that appeared more fit for an animation movie.<br>
<br>"The film starts with the awakening of Sun Wukong within a modern research study facility located in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his brand-new truth and "seeking to comprehend his purpose in this strange new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".<br>
<br>The trio then starts a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted 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 data and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](https://www.rybalka.md) models are not merely replicating Western paradigms, but rather evolving in cost-efficient development methods - and delivering localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi film plot showed its imaginative flair that produced a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and factual actions to concerns about Chinese present occasions, which provides it an added benefit.<br>
<br>Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](http://jobjungle.co.za) 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 study firm Strategy Risks.<br>
<br>"When given an option, Chinese users want the non-censored variation - simply like anybody else, so I seem like that's a piece missing from it."<br>
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://almagigster.com) bots, specifically for Chinese users.<br>
<br>"Ninety percent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient methods," Chen said.<br>