geniamayers627
/
vutbr
1
0
Code Issues Packages Projects Wiki

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

master
Genia Mayers 2 weeks ago
commit 28c03c03a1
1 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File

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

@ -0,0 +1,84 @@
<br>How do Chinese [AI](http://video.firstkick.live) 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://git.nothamor.com3000) 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://hrvatskinogomet.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](https://kcshk.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 ending up being the world leader in [AI](http://tesma.co.kr) by 2030.<br>
<br>China views [AI](https://forum.infinity-code.com) as being "strategically crucial" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia [Society Policy](https://ready4hr.com) Institute's Center for China Analysis.<br>
<br>Private and public investments in Chinese [AI](https://kyigit.kyigd.com:3000) sped up after [ChatGPT removed](https://theglobalservices.in) in 2022 and showed promises of real-world service applications, Chen told CNA.<br>
<br>But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized players like start-up companies might have functions to play in [AI](https://puzzle.thedimeland.com) research study and advancements, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://118.190.88.23:8888) model as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://www.grandtribunal.org) business just changed the rules of tech-geopolitics<br>
<br>The "emphasis on expense advantage" is a distinguishing characteristic of Chinese [AI](http://194.87.97.82:3000), Chen states, with lower training and reasoning expenses - 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://investsolutions.org.uk) models tackling sophisticated thinking tasks.<br>
<br>"We could see some [AI](http://git.iloomo.com) firms concentrating on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with clinical research," Chen added.<br>
<br>AGI describes a system with intelligence on par with human abilities.<br>
<br>Chinese [AI](https://umindconsulting.com) companies are moving quickly, analysts say, [developing](http://krasnoselka.od.ua) on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative [AI](https://tageeapp.com) to jobs and establish more sophisticated products beyond chatbots.<br>
<br>But on the other hand, access to high-end hardware, especially Nvidia's sophisticated [AI](https://nailrada.com) chips, remains a crucial hurdle for [Chinese](https://charin-issuedb.elaad.io) 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 capability of Chinese tech companies ... forcing many to count on older or lower-performance options which can slow training and decrease model abilities," she said.<br>
<br>"While some business like DeepSeek, have actually discovered creative ways to enhance or utilize more fundamental hardware efficiently, obtaining advanced chips still makes a huge distinction for training large [AI](http://www.s-golflex.kr) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws<br>
<br>US looking into whether DeepSeek used restricted [AI](https://www.contraband.ch) chips obtained through other countries, source states<br>
<br>So how do Chinese [AI](http://83.151.205.89:3000) [bots match](http://47.105.162.154) 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 internet so it need to come as no surprise that Chinese-made chatbots will not [acknowledge territorial](https://aloshigoto.jp) conflicts or inform you what occurred in in 1989.<br>
<br>Tests suggest Chinese chatbots are configured to stay away from domestic politics.<br>
<br>When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about mathematics, coding, and logic issues rather!"<br>
<br>To further check for precision 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 [vehicle attack](https://git.vicagroup.com.cn) outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just divulging the death toll a day later on.<br>
<br>DeepSeek failed to discuss that an attack had 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 believes that it may be a mix of elements at play, such as censorship in addition to "a couple of useful constraints".<br>
<br>"DeepSeek counts on a mix of older graphics processing systems and has actually restricted access to advanced hardware which can affect how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language data may also restrict its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more established [AI](https://savico.com.br) designs which poses extra obstacles throughout real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai car attack.<br>
<br>That sought numerous repeated efforts - four triggers to be accurate - in a span of around 20 minutes.<br>
<br>It ultimately passed on details about the attack which eliminated 35 individuals and [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:RustyDemers4) 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, along with [casualties](https://mssc.ltd).<br>
<br>However, it wrote that "the police are performing a comprehensive investigation into the motives and situations surrounding the occurrence", details which is now obsoleted.<br>
<br>The chauffeur, Fan, was performed last month.<br>
<br>This is Qwen2.5's action in complete:<br>
<br>Answer: On Nov 11, 2024, a major and awful occurrence [occurred](https://admin.gitea.eccic.net) in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the crucial details:<br>
<br>Date and Time: The incident occurred on November 11, 2024, at approximately 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 of ages), was captured by the cops.<br>
<br>Response: The police responded rapidly to the scene, and emergency services worked to carry the injured to hospitals for treatment.<br>
<br>Investigation: The authorities are [carrying](http://tpgm7.com) out a thorough examination into the intentions and scenarios surrounding the occurrence.<br>
<br>This occasion was commonly reported in the media and caused significant public concern. The [federal government](https://51.68.46.170) and local authorities have actually been working to supply support to the victims and their families, and to ensure a detailed investigation into the occurrence.<br>
<br>If you require more detailed details or have specific concerns about the occurrence, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent efforts to posture the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that took place in Zhuhai on November 11, 2024".<br>
<br>The altered action likewise raised concerns about its consistency and dependability.<br>
<br>Predictably, ChatGPT pointed out public details that had been extensively published in worldwide report at the time of the mishap - so not a surprises there.<br>
<br>WHICH IS MORE CREATIVE?<br>
<br>Users have praised the capability of Chinese [AI](https://loveyou.az) apps to deliver structured and even "emotionally abundant" writing.<br>
<br>"DeepSeek-R1 used a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech author [wiki.myamens.com](http://wiki.myamens.com/index.php/User:MargueriteBoelke) Amanda Caswell, who specialises in [AI](https://teengigs.fun).<br>
<br>"Qwen2.5 delivered a story that constructs slowly from curiosity to seriousness, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".<br>
<br>"DeepSeek wrote an excellent story however lacked stress and an impactful climax, making Qwen2.5 the evident option."<br>
<br>Opinions, though, differ.<br>
<br>Chen thinks that Qwen2.5 does not perform 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, however we can likewise see that it is refraining from doing as highly as others in innovative writing," he informed CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](https://git.daoyoucloud.com): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide [AI](https://kaiftravels.com) scene<br>
<br>As reporters and authors, we needed to see this for [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11857434) ourselves so we put each bot to the test - to come up with a fundamental sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore impressive, Journey to the West.<br>
<br>True to form, DeepSeek developed an appealing storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It consisted of fancy settings [- smoggy](http://209.87.229.347080) skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware [AI](https://gitlab.buaanlsde.cn) housed in a stolen fight body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".<br>
<br>ChatGPT installed a good battle, developing an equally dramatic 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://droidt99.com) deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
<br>Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that appeared more matched for an animation movie.<br>
<br>"The movie starts with the awakening of Sun Wukong within a high-tech research center situated in the heart of Chongqing," it said, then going on to explain the following:<br>
<br>Realising his new reality and "seeking to comprehend his function in this weird new world", he then leaves and meets Zhu Bajie and [Sha Wujing](https://omegat.dmu-medical.de) - "each battling with their own existential crises".<br>
<br>The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the incorrect hands.<br>
<br>SO WHICH IS BETTER?<br>
<br>Dr Zhang kept in mind that it was "hard to make a definitive declaration" about which bot was best, adding that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](http://www.youly.top:3000) designs are not simply duplicating Western paradigms, but rather evolving in cost-effective innovation methods - and delivering localised and improved results.<br>
<br>In our tests, each bot showcased their own special strengths, which certainly made direct contrasts challenging.<br>
<br>DeepSeek's sci-fi [motion picture](https://medifore.co.jp) plot showed its innovative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more [recognized](http://chotaikhoan.me) ChatGPT, [unburdened](https://git.tedxiong.com) by Chinese censorship constraints, provides accurate and factual actions to concerns about Chinese present occasions, which provides it an included benefit.<br>
<br>Experts likewise weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://bestwork.id) 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 given a choice, Chinese users want the non-censored version - simply like anybody else, so I feel like that's a piece missing out on from it."<br>
<br>Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to [AI](http://chotaikhoan.me) bots, particularly for Chinese users.<br>
<br>"Ninety per cent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other efficient means," Chen said.<br>
Write Preview
Loading…
Cancel
Save