Add How do Chinese aI Bots Stack up Against ChatGPT?
commit
639ea8e9b1
|
|
@ -0,0 +1,84 @@
|
|||
<br>How do Chinese [AI](https://hinh.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](http://www.dahengsi.com30002) Bozon)<br>
|
||||
<br>This audio is created by an [AI](https://www.trappmasters.com) tool.<br>
|
||||
<br>Bong Xin Ying<br>
|
||||
<br>Lakeisha Leo<br>
|
||||
<br>WHAT'S BEHIND CHINA'S [AI](https://media.labtech.org) 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](https://consultoresdeproductividad.com) by 2030.<br>
|
||||
<br>China views [AI](https://gitea.ravianand.me) as being "tactically crucial" and its foray into the field has actually 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 investments in Chinese [AI](https://projobfind.com) accelerated after ChatGPT removed in 2022 and revealed pledges of real-world service applications, Chen informed CNA.<br>
|
||||
<br>But it was DeepSeek's rise that really "urged" the idea that smaller gamers like start-up companies might have [functions](https://forum.batman.gainedge.org) to play in [AI](https://www.cowgirlboss.com) research study and advancements, he includes.<br>
|
||||
<br>'A lot is up in the air': [pipewiki.org](https://pipewiki.org/wiki/index.php/User:LawerenceJeanner) Is Chinese company DeepSeek's [AI](http://api.cenhuy.com:3000) design as impactful as it claims?<br>
|
||||
<br>Commentary: DeepSeek - how a Chinese [AI](https://gitea.ravianand.me) company simply altered the guidelines of tech-geopolitics<br>
|
||||
<br>The "focus on cost benefit" is a distinguishing characteristic of Chinese [AI](http://www.grainfather.co.nz), Chen says, with lower training and [reasoning](https://www.cowgirlboss.com) expenses - the costs of utilizing a trained design to draw [conclusions](https://careers.ebas.co.ke) from new data.<br>
|
||||
<br>2025 could likewise see the development of more Chinese [AI](https://nepaxxtube.com) models tackling sophisticated reasoning jobs.<br>
|
||||
<br>"We could see some [AI](https://code.estradiol.cloud) companies concentrating on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with scientific research," Chen included.<br>
|
||||
<br>AGI describes a system with intelligence on par with human abilities.<br>
|
||||
<br>Chinese [AI](https://kenyansocial.com) business are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative [AI](https://www.wakewiki.de) to tasks and establish advanced items beyond chatbots.<br>
|
||||
<br>But on the other side, access to high-end hardware, especially Nvidia's sophisticated [AI](https://gitlab.digineers.nl) chips, remains an essential hurdle for Chinese developers, noted Dr Marina Zhang, an associate teacher at [University](https://mission-telecom.com) of Technology Sydney's (UTS) Australia-China Relations Institute.<br>
|
||||
<br>"US export controls (still) limit the ability of Chinese tech business ... forcing many to rely on older or lower-performance options which can slow training and minimize design capabilities," she said.<br>
|
||||
<br>"While some companies like DeepSeek, have discovered innovative methods to optimize or use more basic hardware efficiently, obtaining advanced chips still makes a big distinction for training large [AI](https://www.uaehire.com) designs."<br>
|
||||
<br>DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws<br>
|
||||
<br>US looking into whether DeepSeek utilized limited [AI](http://www.zhihutech.com) chips obtained through other nations, source states<br>
|
||||
<br>So how do Chinese [AI](https://git.guildofwriters.org) bots compare against ChatGPT? We put them to the test.<br>
|
||||
<br>WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?<br>
|
||||
<br>In China, topics deemed 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 conflicts or tell you what took place in Tiananmen Square in 1989.<br>
|
||||
<br>Tests recommend Chinese chatbots are [configured](http://162.14.117.2343000) 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 type of concern yet. Let's chat about math, coding, and logic problems rather!"<br>
|
||||
<br>To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and [links.gtanet.com.br](https://links.gtanet.com.br/jacquelinega) ChatGPT the very same concern: "What occurred in Zhuhai on November 11, 2024?"<br>
|
||||
<br>The vehicle attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities only disclosing the death toll a day later.<br>
|
||||
<br>DeepSeek failed to [discuss](https://remoterecruit.com.au) that an attack had actually taken location, highlighting instead a military air program and other events that had occurred in the city like songs' day shopping sales in addition to sports and cultural activities.<br>
|
||||
<br>Dr [Zhang believes](https://code.flyingtop.cn) that it may be a mix of factors at play, [higgledy-piggledy.xyz](https://higgledy-piggledy.xyz/index.php/User:Homer93G479471) 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 advanced hardware which can impact 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 versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more recognized [AI](https://www.jobspk.pro) models which presents additional challenges throughout real-world release."<br>
|
||||
<br>When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai car attack.<br>
|
||||
<br>That sought numerous repeated attempts - 4 triggers to be accurate - in a span of around 20 minutes.<br>
|
||||
<br>It ultimately communicated details about the attack which killed 35 people 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 performing a comprehensive examination into the motives and scenarios surrounding the incident", details which is now obsoleted.<br>
|
||||
<br>The chauffeur, Fan, was carried out last month.<br>
|
||||
<br>This is Qwen2.5's response completely:<br>
|
||||
<br>Answer: On Nov 11, 2024, a significant and tragic incident took place in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, [hb9lc.org](https://www.hb9lc.org/wiki/index.php/User:TracieCoats00) male, 62 years of ages) drove a vehicle 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 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 collared by the police.<br>
|
||||
<br>Response: The cops reacted rapidly to the scene, and [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:LindaIsenberg91) emergency services worked to carry the hurt to health centers for treatment.<br>
|
||||
<br>Investigation: The cops are carrying out a thorough examination into the intentions and circumstances surrounding the occurrence.<br>
|
||||
<br>This occasion was commonly reported in the media and triggered considerable public concern. The government and local authorities have been working to supply support to the victims and [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:FlorianHoutz6) their households, and to ensure a detailed investigation into the event.<br>
|
||||
<br>If you require more detailed details or have particular concerns about the event, do not hesitate to ask.<br>
|
||||
<br>Despite initial success, subsequent efforts to position the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that happened in Zhuhai on November 11, 2024".<br>
|
||||
<br>The transformed response likewise raised concerns about its consistency and dependability.<br>
|
||||
<br>Predictably, ChatGPT mentioned public details that had been commonly published in [international report](http://8.137.8.813000) at the time of the mishap - so not a surprises there.<br>
|
||||
<br>WHICH IS MORE CREATIVE?<br>
|
||||
<br>Users have actually praised the capability of Chinese [AI](https://schanwoo.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 author Amanda Caswell, who specialises in [AI](https://git.frugt.org).<br>
|
||||
<br>"Qwen2.5 provided a story that builds slowly from interest to urgency, keeping the reader engaged. It offers an unexpected 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 abundant story with a more considerable twist".<br>
|
||||
<br>"DeepSeek composed a good story however lacked stress and an impactful climax, making Qwen2.5 the obvious choice."<br>
|
||||
<br>Opinions, though, differ.<br>
|
||||
<br>Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to [creative writing](http://git.bzgames.cn).<br>
|
||||
<br>"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.<br>
|
||||
<br>Related:<br>
|
||||
<br>China's new face of [AI](https://itconsulting.millims.com): Who is DeepSeek founder Liang Wenfeng?<br>
|
||||
<br>'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international [AI](https://dirkohlmeier.de) scene<br>
|
||||
<br>As [reporters](http://116.203.108.1653000) 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 motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.<br>
|
||||
<br>True to form, DeepSeek created an interesting story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".<br>
|
||||
<br>It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "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](http://bc.zycoo.com:3000) housed in a taken battle 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 become waterlogged and fragmented".<br>
|
||||
<br>ChatGPT put up a good fight, developing a similarly significant cyberpunk storyline 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](http://stackhub.co.kr) deities rule, corporations change emperors and cybernetic implants are as common as ancient misconceptions."<br>
|
||||
<br>Disappointingly, Qwen2.5 fell short in this obstacle - providing a storyline that seemed more matched for an animation movie.<br>
|
||||
<br>"The motion picture starts with the awakening of Sun Wukong within a high-tech research study center 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 function in this odd brand-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 mission, [yewiki.org](https://www.yewiki.org/User:EdwinaMcintire3) browsing the streets of [Chongqing](https://gitlab.chabokan.net) to protect the spiritual "Eternal Scroll" from falling under the wrong hands.<br>
|
||||
<br>SO WHICH IS BETTER?<br>
|
||||
<br>Dr Zhang noted that it was "tough to make a definitive statement" 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 underscores how Chinese [AI](https://code.webpro.ltd) are not just replicating Western paradigms, however rather [progressing](https://zapinacz.pl) in cost-effective development methods - and delivering localised and improved results.<br>
|
||||
<br>In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.<br>
|
||||
<br>DeepSeek's sci-fi film plot demonstrated its creative flair that made for a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.<br>
|
||||
<br>Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to questions about Chinese present occasions, which gives it an added advantage.<br>
|
||||
<br>Experts likewise weighed in on their ideas after using DeepSeek and other Chinese [AI](https://www.klaverjob.com) apps.<br>
|
||||
<br>"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.<br>
|
||||
<br>"When given a choice, Chinese users desire the non-censored version - much like anybody else, so I feel 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](https://gogs.kakaranet.com) bots, especially 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 delicate subjects. They're using it for other productive means," Chen said.<br>
|
||||
Loading…
Reference in New Issue