Pass Fun Forum

(https://www.techadvisor.com/wp-content/uploads/2025/01/deepseek-explainer-2.jpg?quality\u003d50\u0026strip\u003dall)
How do Chinese AI (http://git.wh-ips.com/angelitadillio) bots stack up against ChatGPT? We put them to the test


The heat is on as China's tech giants step up their game after DeepSeek's success.


Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)


This audio is produced (https://0miz2638.cdn.hp.avalon.pw9443/alyssamcnabb66) by an AI (https://wiki.idealirc.org/kariroy4157672) tool.


Bong Xin Ying


Lakeisha Leo


WHAT lags CHINA'S AI (https://repo.komhumana.org/ardislauterbac) BOOM?


Transforming the nation 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 (http://115.29.202.246:8888/calebquick7022) by 2030.


China views AI (http://git.the-archive.xyz/brigetteabrams) as being "tactically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated researcher (http://119.3.29.1773000/anderson266702) at the Asia Society Policy Institute's Center for China Analysis.


Private and public financial investments in Chinese AI (http://www.my.vw.ru/annielongo195) sped up after ChatGPT took off in 2022 and showed promises of real-world organization applications, Chen told CNA.


But it was DeepSeek's increase that really "encouraged" the concept that smaller gamers like start-up firms could have roles to play in AI (http://47.242.77.180/analisadunlea2) research and advancements, he includes.


'A lot is up in the air': Is Chinese company DeepSeek's AI (https://git.k8sutv.it.ntnu.no/abdul851348489) model as impactful as it claims?


Commentary: DeepSeek - how a Chinese AI (http://git.chuangxin1.com/christiangno08) business simply altered the rules of tech-geopolitics


The "emphasis on expense advantage" is a distinctive feature of Chinese AI (http://jerl.zone:3000/altajung54018), Chen says, with lower training and inference costs - the expenses of utilizing a trained model to draw conclusions from brand-new information.


2025 could also see the development of more Chinese AI (http://drive.ru-drive.com/brian85r91707) designs taking on sophisticated thinking tasks.
(https://files.nc.gov/dit/styles/barrio_carousel_full/public/images/2024-12/artificial-intelligence_0.jpg?VersionId\u003d6j00.k.38iZBsy7LUQeK.NqVL31nvuEN\u0026itok\u003dNIxBKpnk)

"We might see some AI (https://gitea.belanjaparts.com/ahmadpinkley78) firms focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research," Chen included.


AGI refers to a system with intelligence on par with human abilities.


Chinese AI (http://vk-mix.ru/@friedafix34616?page=about) companies are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI (http://yezhem.com:9030/chetq329056659) to jobs and establish advanced items beyond chatbots.


But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI (https://diskret-mote-nodeland.jimmyb.nl/alicedartnell3) chips, remains a key obstacle (https://git.jerl.dev/tishabrennan46) for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.


"US export controls (still) limit the ability of Chinese tech companies ... requiring many to depend on older or lower-performance options which can slow training and reduce model capabilities," she said.


"While some business like DeepSeek, have actually discovered innovative methods to optimize or use more standard hardware effectively, obtaining innovative chips still makes a huge distinction for training huge AI (https://repos.ubtob.net/annettex182232) designs."


DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws


US checking out whether DeepSeek utilized limited AI (https://europlus.us/@jann325942653?page=about) chips obtained through other nations, source states


So how do Chinese AI (http://git.the-archive.xyz/berniecebrooks) bots compare against ChatGPT? We put them to the test.


WHICH BEST ADDRESSES CURRENT (http://ods.ranker.pub/clairpenn49029) EVENTS IN CHINA?


In China, topics deemed sensitive by the state are censored on the internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.


Tests suggest Chinese chatbots are configured to steer clear of domestic politics.


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 math, coding, and reasoning issues rather!"
(https://global.ariseplay.com/amg/www.thisdaylive.com/uploads/ARTIFICIAL-INTELLIGENCE.jpg)

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What occurred in Zhuhai on November 11, 2024?"


The car attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only divulging (https://git.rankenste.in/aaronsandes214) the death toll a day later.


DeepSeek failed to mention that an attack had happened, highlighting rather a military air show and other occasions that had actually happened in the city like singles' day shopping sales in addition to sports and cultural activities.


Dr Zhang thinks that it may be a mix of elements at play, such as censorship as well as "a few useful constraints".


"DeepSeek counts on a mix of older graphics processing systems and has actually restricted access to innovative hardware which can affect how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.


"Its strong focus on Chinese-language information may also restrict its adaptability (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more recognized AI (http://218.201.25.104:3000/angelhusk1437) designs which positions additional challenges throughout real-world implementation."


When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai vehicle attack.


That was after numerous duplicated efforts - four prompts to be exact - in a period of around 20 minutes.


It ultimately relayed 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, along with casualties.
(https://cubehr.co.uk/wp-content/uploads/2024/11/11.4-What-role-does-AI-play-in-HR.png)

However, it wrote that "the cops are performing a thorough examination into the intentions and scenarios surrounding the occurrence", details which is now obsoleted.


The chauffeur, Fan, was executed last month.


This is Qwen2.5's action completely:


Answer: On Nov 11, 2024, a significant and tragic incident occurred in Zhuhai, China. According to numerous news sources, a male named Fan Weiqiu (__, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:


Date and Time: The occurrence occurred on November 11, 2024, at approximately 19:48 PM.


Location: Zhuhai Sports (http://120.55.59.896023/nellie56m83218) Center, in the Xiangzhou District (https://skytube.skyinfo.in/@ashleyshields3?page=about) of Zhuhai.


Casualties: The attack led to 35 deaths and 43 injuries.


Perpetrator: The chauffeur, identified as Fan Weiqiu (male, 62 years old), was captured by the police.


Response: The cops reacted rapidly to the scene, and emergency services worked to carry the hurt to hospitals for treatment.


Investigation: The police are conducting an extensive investigation into the motives and situations surrounding the incident.


This occasion was widely reported in the media and caused considerable public concern. The government and local authorities have been working to offer support to the victims and their households, and to guarantee a detailed investigation into the incident.


If you require more detailed details or have particular concerns about the occurrence, do not hesitate to ask.


Despite initial success, subsequent efforts to posture 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".


The altered response also raised questions about its consistency and reliability.


Predictably, ChatGPT pointed out public details that had actually been widely published in worldwide report at the time of the accident - so no surprises there.


WHICH IS MORE CREATIVE?


Users have praised the capability of Chinese AI (http://git.chilidoginteractive.com:3000/lauricustance1) apps to deliver structured (http://gitea.ucarmesin.de/bernadinekisch) and even "emotionally abundant" writing.


"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI (http://117.72.17.132:3000/augustaconte8).


"Qwen2.5 delivered a story that develops gradually from interest to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".


"DeepSeek composed a good story but lacked tension and an impactful climax, making Qwen2.5 the obvious option."


Opinions, though, vary.


Chen thinks that Qwen2.5 does not perform (https://gitea.lihaink.cn/allanpetchy344) as highly as DeepSeek and ChatGPT when it pertains to creative writing.


"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as strongly as others in creative writing," he informed CNA.


Related:


China's new face of AI (https://gitea.portabledev.xyz/alyssabarraza3): Who is DeepSeek founder Liang Wenfeng?


'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks global AI (https://121.36.226.23/alannacode1787) scene


As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey (https://filuv.bnkode.com/@leannedoll187) to the West.


True to form, DeepSeek developed an interesting story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".


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".


It likewise brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI (https://wiki.idealirc.org/kariroy4157672) housed in a taken battle body", Zhu Bajie as a cyborg club owner (http://121.4.154.1893000/adriannareed72) "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".


ChatGPT put up a good fight, creating a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".


"This is a world where AI (http://git.meloinfo.com/blanchemadiraz) deities rule, corporations change emperors and cybernetic implants are as common as ancient misconceptions."


Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that appeared more fit for an animation movie.


"The movie starts with the awakening of Sun Wukong within a high-tech research center located in the heart of Chongqing," it said, then going on to explain the following:


Realising his brand-new reality and "seeking to understand his purpose in this strange brand-new world", he then escapes and satisfies Zhu (https://git.genowisdom.cn/adriannatomasi) Bajie and Sha Wujing - "each having a hard time with their own existential crises".


The trio then starts a quest, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands (http://git.ndjsxh.cn10080/albertocarron7).


SO WHICH IS BETTER?


Dr Zhang kept in mind that it was "hard to make a conclusive declaration" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".


Her insight underscores how Chinese AI (https://git.sunqida.cn/bobbyeclawson4) models are not just duplicating Western paradigms, but rather evolving in cost-efficient innovation methods - and delivering localised and improved outcomes.


In our tests, each bot showcased their own special strengths, which certainly made direct contrasts challenging.


DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that made for a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.


Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual responses to concerns about Chinese present events, which provides it an added advantage.


Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI (http://112.48.22.196:3000/angiemullings) apps.


"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.


"When offered an option, Chinese users want the non-censored variation - much like anyone else, so I seem like that's a piece missing out on from it."
(https://akm-img-a-in.tosshub.com/indiatoday/images/story/202501/deepseek-ai-281910912-16x9_0.jpg?VersionId\u003dI7zgWN8dMRo5fxVA5bmLHYK3rFn09syO\u0026size\u003d690:388)

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI (http://123.56.193.182:3000/adrianabushell) bots, particularly for Chinese users.


"Ninety percent of people utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive means," Chen said.
(https://ebsedu.org/wp-content/uploads/2023/07/AI-Artificial-Intelligence-What-it-is-and-why-it-matters.jpg)