rebbecaperrin8/vilniustech
1
0
Code Issues Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Rebbeca Perrin 2025-03-05 09:05:35 +01:00
commit be18bf5522
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://git.itbcode.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 produced by an [AI](https://git.sunqida.cn) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://watch.bybitnw.com) BOOM?<br>
<br>Transforming the country 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](https://southwales.com) by 2030.<br>
<br>China views [AI](https://novashop6.com) as being "strategically crucial" and its foray 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 in Chinese [AI](https://iamtube.jp) sped up after ChatGPT removed in 2022 and revealed pledges of real-world organization applications, Chen told CNA.<br>
<br>But it was DeepSeek's increase that truly "urged" the idea that smaller sized gamers like start-up [companies](https://jobskhata.com) might have roles to play in [AI](https://teachersconsultancy.com) research study and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](https://retailjobacademy.com) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://rejobbing.com) business simply altered the rules of tech-geopolitics<br>
<br>The "emphasis on expense advantage" is a distinguishing characteristic of Chinese [AI](http://212.64.10.162:7030), Chen states, with lower training and inference expenses - the expenses of using a trained model to draw conclusions from brand-new information.<br>
<br>2025 could likewise see the development of more Chinese [AI](https://adremcareers.com) models dealing with advanced reasoning jobs.<br>
<br>"We could see some [AI](http://211.159.154.98:3000) firms focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with scientific research study," [Chen included](http://103.197.204.1633025).<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://www.ejobsboard.com) companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and [affordable](https://www.4bride.org) ways to apply generative [AI](https://vidacibernetica.com) to tasks and develop advanced items beyond chatbots.<br>
<br>But on the flip side, access to high-end hardware, especially Nvidia's sophisticated [AI](https://www.noagagu.kr) chips, remains a crucial obstacle for [disgaeawiki.info](https://disgaeawiki.info/index.php/User:BrittneyCoane) Chinese developers, kept in mind Dr Marina Zhang, an [associate teacher](http://www.aiki-evolution.jp) at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) limit the capability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and lower design capabilities," she said.<br>
<br>"While some companies like DeepSeek, have discovered creative ways to enhance or use more basic hardware effectively, obtaining advanced chips still makes a huge difference for training very large [AI](https://git.fanwikis.org) models."<br>
<br>DeepSeek-Nvidia chips: Singapore states it anticipates companies to abide by its laws<br>
<br>US checking out whether DeepSeek used limited [AI](https://netgork.com) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](http://team.pocketuniversity.cn) bots compare against ChatGPT? We put them to the test.<br>
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
<br>In China, topics considered sensitive by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11862161) inform you what occurred in Tiananmen Square in 1989.<br>
<br>Tests recommend Chinese chatbots are programmed 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 mathematics, coding, and logic issues rather!"<br>
<br>To even more test for precision and [yewiki.org](https://www.yewiki.org/User:MayaHoughton435) self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact 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 heavily censored on Chinese social networks - with authorities only revealing the [death toll](http://106.39.38.2421300) a day later on.<br>
<br>DeepSeek failed to discuss that an attack had happened, highlighting instead a military air program and other occasions that had taken place 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 aspects at play, such as censorship as well as "a few useful constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing systems and has restricted access to advanced hardware which can affect how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information might likewise limit its flexibility (to perform) multilingual tasks ... 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://193.9.44.91) models which positions extra difficulties during real-world deployment."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai car attack.<br>
<br>That was after several repeated attempts - four triggers to be precise - in a period of around 20 minutes.<br>
<br>It ultimately passed on [details](https://www.cvgods.com) about the attack which killed 35 people and left lots of others injured, 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 police are conducting a comprehensive examination into the intentions and scenarios surrounding the incident", details which is now dated.<br>
<br>The motorist, Fan, was [performed](https://git.logicloop.io) last month.<br>
<br>This is Qwen2.5's response completely:<br>
<br>Answer: On Nov 11, 2024, a significant and awful occurrence happened in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant 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](https://asixmusik.com) of Zhuhai.<br>
<br>Casualties: The attack resulted in 35 deaths and 43 injuries.<br>
<br>Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the authorities.<br>
<br>Response: The cops reacted rapidly to the scene, and emergency situation [services](https://ruraltv.in) worked to transfer the hurt to healthcare facilities for treatment.<br>
<br>Investigation: The authorities are an extensive examination into the motives and circumstances surrounding the incident.<br>
<br>This event was widely reported in the media and caused substantial public concern. The federal government and regional authorities have actually been working to provide support to the victims and their households, and to ensure a detailed investigation into the incident.<br>
<br>If you need more detailed details or have specific questions about the incident, feel complimentary to ask.<br>
<br>Despite preliminary success, subsequent attempts to pose the very same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".<br>
<br>The modified response also raised concerns about its consistency and dependability.<br>
<br>Predictably, ChatGPT cited public details that had been commonly published in global news reports at the time of the mishap - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have praised the capability of Chinese [AI](https://wiki.project1999.com) apps to deliver structured and even "emotionally abundant" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://igazszavak.info).<br>
<br>"Qwen2.5 delivered a story that constructs slowly from curiosity to urgency, 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, mentally rich story with a more considerable twist".<br>
<br>"DeepSeek wrote a great story however lacked tension and an impactful climax, making Qwen2.5 the apparent option."<br>
<br>Opinions, though, vary.<br>
<br>Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 innovative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://www.bolsadetrabajotafer.com): Who is DeepSeek creator Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international [AI](https://job.duttainnovations.com) scene<br>
<br>As [reporters](http://git.sysoit.co.kr) and writers, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot embeded 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 interesting storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It included intricate 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 likewise remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware [AI](https://www.noagagu.kr) housed in a taken combat body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".<br>
<br>ChatGPT installed an excellent battle, creating an equally dramatic cyberpunk story 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://welcometohaiti.com) deities rule, corporations change emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this challenge - providing a storyline that seemed more suited for an animation movie.<br>
<br>"The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research center situated 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 comprehend his function in this strange new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".<br>
<br>The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the wrong hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "difficult to make a definitive declaration" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](https://alumni.myra.ac.in) designs are not merely duplicating Western paradigms, but rather evolving in cost-effective innovation methods - and providing localised and improved results.<br>
<br>In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi movie plot demonstrated its creative flair that produced a more [engaging](https://adremcareers.com) and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual reactions to questions about Chinese current occasions, which provides it an included benefit.<br>
<br>Experts also weighed in on their thoughts after using DeepSeek and other Chinese [AI](https://mp3talpykla.com) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.<br>
<br>"When given a choice, Chinese users desire the non-censored variation - much like anyone else, so I feel like that's a piece missing out on from it."<br>
<br>Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](https://allcollars.com) bots, especially for Chinese users.<br>
<br>"Ninety percent of people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient ways," Chen said.<br>