htvclara57725/job-4thai
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

Clara St Leon 2025-02-06 21:32:34 +00:00
commit fb3f4de89b
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.arachno.de) 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](http://83.151.205.893000). (Photos: Reuters/Dado Ruvic, AFP/[Sebastien](https://dainiknews.com) Bozon)<br>
<br>This audio is created by an [AI](https://lr-mediconsult.de) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://becalm.life) BOOM?<br>
<br>Transforming the nation into a tech superpower has long been President Xi Jinping's objective and [pipewiki.org](https://pipewiki.org/wiki/index.php/User:ShellieGenders) China has its sights on ending up being the world leader in [AI](http://stream.appliedanalytics.tech) by 2030.<br>
<br>China views [AI](https://gitea.freshbrewed.science) as being "tactically essential" 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 financial investments in Chinese [AI](https://music.lcn.asia) accelerated after ChatGPT took off in 2022 and showed promises of real-world organization applications, Chen informed CNA.<br>
<br>But it was DeepSeek's rise that really "urged" the idea that smaller gamers like [start-up companies](https://bnsgh.com) might have roles to play in [AI](https://gitlog.ru) research and developments, he includes.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](https://gogs.es-lab.de) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](http://114.132.245.203:8001) company simply changed the rules of tech-geopolitics<br>
<br>The "emphasis on cost advantage" is a distinguishing characteristic of Chinese [AI](http://git.e365-cloud.com), Chen says, with lower training and [35.237.164.2](https://35.237.164.2/wiki/User:BessieFitzRoy) reasoning costs - the costs of using a trained model to reason from new data.<br>
<br>2025 might also see the emergence of more Chinese [AI](https://groupeudson.com) designs tackling sophisticated reasoning jobs.<br>
<br>"We might see some [AI](https://www.vfrnds.com) companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with scientific research," Chen included.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://git.ipmake.me) companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to apply generative [AI](http://122.51.17.90:2000) to jobs and develop advanced items beyond [chatbots](https://pittsburghpenguinsclub.com).<br>
<br>But on the other hand, access to high-end hardware, particularly Nvidia's innovative [AI](https://www.scikey.ai) chips, remains a crucial difficulty for Chinese developers, noted 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 business ... requiring lots of to depend on older or lower-performance alternatives which can slow training and lower model abilities," she said.<br>
<br>"While some companies like DeepSeek, have actually discovered innovative ways to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a big distinction for training large [AI](http://60.205.210.36) models."<br>
<br>DeepSeek-Nvidia chips: Singapore states it [expects companies](https://timviecvtnjob.com) to adhere to its laws<br>
<br>US checking out whether DeepSeek used restricted [AI](http://121.40.234.130:8899) chips obtained through other countries, source says<br>
<br>So how do Chinese [AI](https://rightlane.beparian.com) bots match up against ? 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](http://111.2.21.14133001) so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place in Tiananmen Square in 1989.<br>
<br>Tests suggest 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 type of concern yet. Let's chat about math, coding, and logic problems instead!"<br>
<br>To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The car attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later on.<br>
<br>DeepSeek failed to mention that an attack had occurred, highlighting instead a military air program and other occasions that had actually 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 factors at play, such as censorship as well as "a couple of useful constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing units and has actually limited access to innovative hardware which can impact 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 may likewise limit its versatility (to bring out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established [AI](http://e-kou.jp) designs which postures additional difficulties during real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai automobile attack.<br>
<br>That was after numerous repeated efforts - four triggers to be precise - in a span of around 20 minutes.<br>
<br>It ultimately passed on details about the attack which killed 35 people and left lots of others hurt, 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, [bio.rogstecnologia.com.br](https://bio.rogstecnologia.com.br/bagjanine969) it wrote that "the police are conducting a thorough examination into the intentions and situations surrounding the occurrence", [details](https://kittelartscollege.com) which is now [outdated](https://candays.com).<br>
<br>The chauffeur, Fan, was carried out last month.<br>
<br>This is Qwen2.5's reaction in full:<br>
<br>Answer: On Nov 11, 2024, a major and tragic incident happened in Zhuhai, [gratisafhalen.be](https://gratisafhalen.be/author/rebbeca9609/) China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the crucial details:<br>
<br>Date and Time: The event happened on November 11, 2024, [wiki.dulovic.tech](https://wiki.dulovic.tech/index.php/User:EdithJoseph92) 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 chauffeur, determined as Fan Weiqiu (male, 62 years old), was nabbed by the police.<br>
<br>Response: The police reacted rapidly to the scene, and emergency situation services worked to transport the injured to healthcare facilities for treatment.<br>
<br>Investigation: The cops are carrying out an extensive examination into the motives and situations surrounding the incident.<br>
<br>This event was extensively reported in the media and [caused substantial](https://gitlab.healthcare-inc.com) public issue. The federal government and regional authorities have been working to provide support to the victims and their families, [it-viking.ch](http://it-viking.ch/index.php/User:AngelicaSnowball) and to guarantee a detailed examination into the occurrence.<br>
<br>If you need more detailed details or have specific concerns about the occurrence, do not hesitate to ask.<br>
<br>Despite preliminary success, [subsequent efforts](http://116.62.115.843000) to posture the very same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".<br>
<br>The altered action also raised questions about its [consistency](http://git.e365-cloud.com) and reliability.<br>
<br>Predictably, ChatGPT cited public details that had actually been commonly released in global [news reports](http://51.222.156.2503000) at the time of the accident - so no surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have actually praised the ability of Chinese [AI](https://energypowerworld.co.uk) apps to deliver structured and even "mentally abundant" writing.<br>
<br>"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in [AI](https://gofleeks.com).<br>
<br>"Qwen2.5 delivered a story that develops gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 [ultimately](http://mao2000.com3000) "crafted a more cinematic, mentally abundant story with a more significant twist".<br>
<br>"DeepSeek composed a good story but did not have tension and an impactful climax, making Qwen2.5 the apparent option."<br>
<br>Opinions, though, differ.<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 jobs, however 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 brand-new face of [AI](https://napvibe.com): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international [AI](https://arlogjobs.org) scene<br>
<br>As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.<br>
<br>True to form, DeepSeek developed an interesting storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
<br>It consisted of sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms". <br>
<br>It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware [AI](http://park8.wakwak.com) housed in a taken battle body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".<br>
<br>ChatGPT put up a good battle, creating a similarly remarkable cyberpunk story which likewise 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://gitea.blubeacon.com) deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that seemed more fit for an animation movie.<br>
<br>"The movie begins with the awakening of Sun Wukong within a modern 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 "looking for to understand his function in this strange new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each dealing 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 into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang noted that it was "tough 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 highlights how Chinese [AI](https://tribetok.com) models are not just duplicating Western paradigms, but rather developing in economical development methods - and delivering localised and enhanced 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 motion [picture plot](https://eelam.tv) showed its creative flair that made for a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, [supplies](https://999vv.xyz) precise and accurate reactions to concerns about Chinese current occasions, which offers it an added advantage.<br>
<br>Experts also weighed in on their ideas after using DeepSeek and other Chinese [AI](http://wiki.pokemonspeedruns.com) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.<br>
<br>"When provided an option, Chinese users desire the non-censored version - similar to anyone else, so I seem like that's a piece missing from it."<br>
<br>[Independent Beijing-based](https://fassen.net) specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](http://101.34.87.71) bots, specifically for Chinese users.<br>
<br>"Ninety percent of people utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive means," Chen said.<br>