allisonstahl22
/
celest-interim
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Allison Stahl 2025-02-23 12:31:19 +00:00
parent 34f1660a3d
commit 2080d24095
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](http://carpetube.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](https://www.h0sting.org) Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is created by an [AI](https://git.lodis.se) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://sharingopportunities.com) BOOM?<br>
<br>Transforming the nation 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](http://40th.jiuzhai.com) by 2030.<br>
<br>China views [AI](http://042.ne.jp) as being "strategically essential" and its foray 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 financial investments in Chinese [AI](https://gitlab.chabokan.net) accelerated after ChatGPT removed in 2022 and revealed pledges of real-world company applications, Chen informed CNA.<br>
<br>But it was DeepSeek's rise that actually "urged" the concept that smaller sized gamers like start-up companies could have functions to play in [AI](https://c-hireepersonnel.com) research study and advancements, he includes.<br>
<br>'A lot is up in the air': Is Chinese company DeepSeek's [AI](https://git.micg.net) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://gitlab.cranecloud.io) company just changed the rules of tech-geopolitics<br>
<br>The "focus on expense advantage" is a distinct feature of Chinese [AI](http://revoltsoft.ru:3000), Chen states, with lower training and inference expenses - the costs of using a trained design to draw conclusions from brand-new data.<br>
<br>2025 might likewise see the introduction of more Chinese [AI](https://git.genowisdom.cn) models taking on innovative reasoning tasks.<br>
<br>"We might see some [AI](http://git.youkehulian.cn) firms focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research study," Chen added.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://gitlab.tncet.com) companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative [AI](http://82.157.11.224:3000) to jobs and develop more sophisticated items beyond chatbots.<br>
<br>But on the other side, access to high-end hardware, particularly [Nvidia's innovative](https://afrocinema.org) [AI](https://optimiserenergy.com) chips, remains a crucial hurdle for [Chinese](https://code.dev.beejee.org) 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) limit the ability of Chinese tech companies ... requiring many to depend on older or lower-performance alternatives which can slow training and lower design capabilities," she said.<br>
<br>"While some business like DeepSeek, have found innovative ways to enhance or use more basic hardware effectively, obtaining innovative chips still makes a huge distinction for training large [AI](http://git.itlym.cn) models."<br>
<br>DeepSeek-Nvidia chips: [Singapore](https://findspkjob.com) says it anticipates business to adhere to its laws<br>
<br>US looking into whether DeepSeek used restricted [AI](https://choosy.cc) chips obtained through other nations, source says<br>
<br>So how do Chinese [AI](https://git.rongxin.tech) 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 web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are configured to guide clear of domestic politics.<br>
<br>When asked "Who is Xi Jinping", [DeepSeek's](https://git.mitsea.com) reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and reasoning issues instead!"<br>
<br>To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What happened in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just disclosing the death toll a day later.<br>
<br>DeepSeek failed to point out that an attack had actually occurred, highlighting instead a military air show and other occasions that had actually taken place in the city like songs' day shopping sales as well as sports and cultural activities.<br>
<br>Dr Zhang thinks that it might be a mix of elements at play, such as censorship in addition to "a few useful constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to cutting-edge hardware which can affect how rapidly and extensively the model 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 limit its versatility (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 established [AI](http://hammer.x0.to) models which poses extra challenges during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai vehicle attack.<br>
<br>That was after multiple duplicated efforts - four prompts to be accurate - in a span of around 20 minutes.<br>
<br>It ultimately communicated details about the attack which killed 35 individuals and left lots of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.<br>
<br>However, it composed that "the authorities are conducting an extensive investigation into the intentions and scenarios surrounding the event", details which is now obsoleted.<br>
<br>The motorist, Fan, was executed last month.<br>
<br>This is Qwen2.5's reaction completely:<br>
<br>Answer: On Nov 11, 2024, a significant and terrible event occurred in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a number of casualties. Here are the key details:<br>
<br>Date and Time: The incident happened on November 11, 2024, [archmageriseswiki.com](http://archmageriseswiki.com/index.php/User:CodyWayne60360) at approximately 19:48 PM.<br>
<br>Location: [Zhuhai Sports](http://git.sysoit.co.kr) Center, in the Xiangzhou District of Zhuhai.<br>
<br>Casualties: The attack led to 35 deaths and 43 injuries.<br>
<br>Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the police.<br>
<br>Response: The authorities reacted rapidly to the scene, and emergency situation services worked to transport the hurt to hospitals for treatment.<br>
<br>Investigation: The cops are conducting an extensive examination into the intentions and scenarios surrounding the event.<br>
<br>This event was extensively reported in the media and caused considerable public issue. The federal government and local authorities have actually been working to provide support to the victims and their households, and to make sure a detailed examination into the event.<br>
<br>If you require more detailed details or have particular questions about the event, feel free to ask.<br>
<br>Despite initial success, subsequent attempts to pose the exact same concern to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on occasions that happened in Zhuhai on November 11, 2024".<br>
<br>The altered response also raised questions about its consistency and reliability.<br>
<br>Predictably, ChatGPT mentioned public details that had been commonly released in international news reports at the time of the accident - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have praised the capability of Chinese [AI](http://47.104.65.214:19206) apps to deliver structured and even "mentally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://realestate.kctech.com.np).<br>
<br>"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "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 option."<br>
<br>Opinions, however, differ.<br>
<br>Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek 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 new face of [AI](https://my.buzztv.co.za): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global [AI](https://www.mpowerplacement.com) scene<br>
<br>As reporters and authors, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the [futuristic megacity](https://gitea.namsoo-dev.com) of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.<br>
<br>True to form, DeepSeek developed 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 fancy settings [- smoggy](https://src.enesda.com) skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It likewise remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://surgiteams.com) housed in a stolen fight body", [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:AshtonBungaree) 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 a good fight, coming up with an equally remarkable cyberpunk storyline which similarly 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://impactosocial.unicef.es) deities guideline, corporations change emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that appeared more matched for an animation movie.<br>
<br>"The motion picture 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 new reality and "seeking to understand his purpose in this strange new world", he then leaves and satisfies Zhu 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 into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "challenging to make a conclusive statement" about which bot was best, including that each displayed its own strengths in various areas, "such as language focus, training data and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](http://git.yang800.cn) designs are not merely duplicating Western paradigms, [gratisafhalen.be](https://gratisafhalen.be/author/olivershoem/) but rather progressing in affordable innovation approaches - and providing localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons [challenging](http://101.34.87.71).<br>
<br>DeepSeek's sci-fi motion picture plot showed its imaginative flair that produced a more [appealing](https://casajienilor.ro) and creative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual actions to concerns about Chinese current occasions, which gives it an included benefit.<br>
<br>Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](http://47.107.132.138:3000) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research company Strategy Risks.<br>
<br>"When provided a choice, Chinese users desire the non-censored variation - simply like anyone else, so I seem like that's a piece missing from it."<br>
<br>Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](http://www.vpsguards.co) bots, especially for Chinese users.<br>
<br>"Ninety percent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive ways," Chen said.<br>