aprilsteffen8/youarealways
1
0
Code Issues Actions Packages Projects Wiki

Add How do Chinese aI Bots Stack up Against ChatGPT?

April Steffen 2025-02-09 12:56:01 +00:00
commit cf51be309e
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](http://devhub.dost.gov.ph) [AI](http://47.108.182.66:7777) 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 game after DeepSeek's success.<br>
<br>[Alibaba's](http://106.55.3.10520080) Qwen2.5-Max chatbot, Chinese start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)<br>
<br>This audio is generated by an [AI](https://twwrando.com) tool.<br>
<br>Bong Xin Ying<br>
<br>Lakeisha Leo<br>
<br>WHAT'S BEHIND CHINA'S [AI](http://gogs.kexiaoshuang.com) BOOM?<br>
<br>Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in [AI](https://20.112.29.181) by 2030.<br>
<br>China views [AI](https://flixtube.info) as being "tactically essential" and its venture 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://eurosynapses.giannistriantafyllou.gr) sped up after ChatGPT took off in 2022 and revealed pledges of real-world service applications, Chen informed CNA.<br>
<br>But it was DeepSeek's increase that really "encouraged" the idea that smaller sized players like start-up companies might have functions to play in [AI](https://www.virsocial.com) research study and advancements, he adds.<br>
<br>'A lot is up in the air': Is Chinese firm DeepSeek's [AI](http://www.withsafety.net) design as impactful as it claims?<br>
<br>Commentary: DeepSeek - how a Chinese [AI](https://pierre-humblot.com) business just altered the guidelines of tech-geopolitics<br>
<br>The "focus on cost benefit" is a distinguishing characteristic of Chinese [AI](http://www.vmeste-so-vsemi.ru), Chen says, with lower training and reasoning expenses - the expenses of [utilizing](https://gogs.2dz.fi) a trained model to draw conclusions from brand-new information.<br>
<br>2025 could also see the development of more Chinese [AI](https://thenolugroup.co.za) designs dealing with sophisticated reasoning tasks.<br>
<br>"We might see some [AI](http://www.topverse.world:3000) firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways 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 abilities.<br>
<br>Chinese [AI](http://sbstaffing4all.com) business are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-efficient methods to apply generative [AI](http://120.78.74.94:3000) to jobs and develop more advanced products beyond chatbots.<br>
<br>But on the flip side, access to high-end hardware, especially Nvidia's sophisticated [AI](https://git.manu.moe) chips, remains a key difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
<br>"US export controls (still) restrict the capability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and decrease design abilities," she said.<br>
<br>"While some business like DeepSeek, have actually discovered creative methods to optimize or use more standard hardware effectively, obtaining innovative chips still makes a huge difference for training huge [AI](https://www.ynxbd.cn:8888) designs."<br>
<br>DeepSeek-Nvidia chips: Singapore says it anticipates companies to adhere to its laws<br>
<br>US looking into whether DeepSeek utilized limited [AI](https://www.empireofember.com) chips obtained through other nations, source states<br>
<br>So how do Chinese [AI](https://gitea.qianking.xyz:3443) bots compare against ChatGPT? We put them to the test.<br>
<br>WHICH BEST [ADDRESSES CURRENT](http://203.171.20.943000) EVENTS IN CHINA?<br>
<br>In China, subjects considered by the state are [censored](https://www.unotravel.co.kr) on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what [occurred](http://mirae.jdtsolution.kr) in Tiananmen Square in 1989.<br>
<br>Tests suggest Chinese chatbots are configured 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 question yet. Let's chat about mathematics, coding, and reasoning problems rather!"<br>
<br>To further test for precision and self-censorship, [oeclub.org](https://oeclub.org/index.php/User:VickeyN17973675) we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
<br>The cars and truck attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities only divulging the death toll a day later.<br>
<br>DeepSeek failed to mention that an attack had actually occurred, highlighting rather a military air show and other occasions that had actually [occurred](https://gitea.pi.cr4.live) in the city like singles' day shopping sales along with 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 practical constraints".<br>
<br>"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can affect how rapidly and extensively the model can be trained or upgraded," she said, pointing to existing US export curbs on China.<br>
<br>"Its strong focus on Chinese-language information may also limit its flexibility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more recognized [AI](https://asg-pluss.com) models which presents extra obstacles during real-world release."<br>
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai vehicle attack.<br>
<br>That sought multiple duplicated attempts - four prompts to be accurate - in a span of around 20 minutes.<br>
<br>It eventually relayed details about the attack which eliminated 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, in addition to [casualties](https://gitea.thuispc.dynu.net).<br>
<br>However, it wrote that "the authorities are conducting a thorough investigation into the intentions and scenarios surrounding the incident", details which is now obsoleted.<br>
<br>The motorist, Fan, was performed last month.<br>
<br>This is Qwen2.5's action in full:<br>
<br>Answer: On Nov 11, 2024, a major and terrible event occurred in Zhuhai, China. According to [numerous news](https://git.manu.moe) sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile 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 occurrence took place on November 11, 2024, 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: [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11861831) The motorist, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the authorities.<br>
<br>Response: The authorities responded rapidly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.<br>
<br>Investigation: The cops are performing an extensive investigation into the intentions and circumstances surrounding the incident.<br>
<br>This occasion was widely reported in the media and caused substantial public concern. The federal government and regional [authorities](https://www.sportpassionhub.com) have actually been working to provide support to the victims and their families, and to guarantee a detailed investigation into the occurrence.<br>
<br>If you require more detailed details or have particular concerns about the incident, do not hesitate to ask.<br>
<br>Despite preliminary success, subsequent attempts to pose the exact same question to Qwen2.5 resulted in 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 action likewise raised questions about its consistency and dependability.<br>
<br>Predictably, [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:MonserrateHuntin) ChatGPT mentioned public details that had actually been extensively released in global news reports 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://www.iratechsolutions.com) apps to provide structured and even "mentally rich" writing.<br>
<br>"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," [wrote tech](https://dyipniflix.com) author Amanda Caswell, who specialises in [AI](https://gitlab.healthcare-inc.com).<br>
<br>"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery 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 great story but did not have tension and an impactful climax, making Qwen2.5 the apparent option."<br>
<br>Opinions, [wiki.whenparked.com](https://wiki.whenparked.com/User:LatashaRutledge) though, vary.<br>
<br>Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.<br>
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as highly as others in creative writing," he told CNA.<br>
<br>Related:<br>
<br>China's new face of [AI](http://1.12.246.18:3000): Who is DeepSeek founder Liang Wenfeng?<br>
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide [AI](https://repo.serlink.es) scene<br>
<br>As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi film plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore impressive, [wiki.asexuality.org](https://wiki.asexuality.org/w/index.php?title=User_talk:WileyK1034) Journey to the West.<br>
<br>True to form, DeepSeek created an engaging storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".<br>
<br>It consisted of intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms". <br>
<br>It also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware [AI](https://sfren.social) housed in a stolen fight body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation 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 set up a good fight, coming up with an equally 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](http://194.67.86.160:3100) deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."<br>
<br>Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that seemed more suited for an animation film.<br>
<br>"The film starts with the awakening of Sun Wukong within a state-of-the-art research facility situated 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 unusual brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".<br>
<br>The trio then starts a quest, navigating the streets of Chongqing to secure 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 "hard to make a definitive declaration" about which bot was best, adding that each showed its own strengths in different locations, "such as language focus, training information and hardware optimization".<br>
<br>Her insight highlights how Chinese [AI](https://wiki.monnaie-libre.fr) models are not just duplicating Western paradigms, but rather evolving in cost-efficient development approaches - and providing localised and enhanced outcomes.<br>
<br>In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.<br>
<br>DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more interesting and [engel-und-waisen.de](http://www.engel-und-waisen.de/index.php/Benutzer:XFPZack3509) creative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual responses to concerns about Chinese current occasions, which provides it an [included advantage](https://www.boatcareer.com).<br>
<br>Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese [AI](https://git.didi.la) apps.<br>
<br>"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, [mediawiki.hcah.in](https://mediawiki.hcah.in/index.php?title=User:RandellKenney) creator and CEO of the research study firm Strategy Risks.<br>
<br>"When given an option, Chinese users desire the non-censored variation - just like anybody else, so I seem 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](https://www.wikiwrimo.org) bots, particularly for Chinese users.<br>
<br>"Ninety percent of individuals 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>