Explore the groundbreaking advancements of GPT-4o as it shatters language barriers and fosters unprecedented global connectivity. This section delves into the transformative effects of artificial general intelligence on communication across cultures.
2024.05.13 2143 [AGI] GPT-4o _Launch _Language Learning
Chat GPT-4o
Saturday, June 29, 2024
8:19 PM
Saturday, June 29, 2024
8:26 PM
-Turn this page of information into the following DDNOTE (Diary Date Notes Of The Events):
(0.) Determine the “YYYY.MM.DD HHMM” e.g. the date of the story for example. Make sure you turn your answer into the YYYY.MM.DD HHMM format.
(1.) Create a [SAL] code -SAL is Selfology Acronym List
(2.) list All Keywords related to the event from the article (e.g. _HOWTO _SR9.0 _). If possible from important to least important. Discover popular and accepted acronyms used for any of these terms, and if none exists, crest one and define.
(3.) table all parties related to the story, including people reporting.
(4.) A good summary prose is written in a style that feels professional.
(5.) Create a DDNOTE Name (e.g. 2024.05.13 0111 [HEALTH] COVID _Vaccine).
(6.) link to review:
https://teknolojimiz.com/en/openai-introduces-gpt-4o-a-free-new-language-model/
https://www.pcmag.com/reviews/chatgpt-4o
Saturday, June 29, 2024
8:26 PM
Certainly! Here’s the DDNOTE based on the information provided:
DDNOTE Name: 2024.05.13 2143 [AI] GPT-4o _Launch
Date of Event: 2024.05.13 2143
[SAL] Code:
Keywords:
Parties Involved:
| Role | Name | Affiliation |
| Developer | OpenAI | OpenAI |
| Reviewer | Chris Stobing | PCMag |
| Reviewer | Ryan Morrison | Tom’s Guide |
Summary Prose: On May 13, 2024, OpenAI introduced GPT-4o, a groundbreaking AI model designed for real-time interaction across text, audio, and visual inputs. This omni-modal LLM represents a significant leap in AI accessibility and efficiency, boasting faster response times and improved multilingual capabilities. The launch of GPT-4o marks a pivotal moment in AI, as it promises to enhance human-computer communication with its advanced understanding and processing abilities.
Links to Reviews:
Please note that the above DDNOTE is a structured summary based on the information available from the provided links and search results. The date and time format follows the requested “YYYY.MM.DD HHMM” convention, and the SAL code provides a quick reference to key terms associated with the event.
From <https://copilot.microsoft.com/>
From <https://copilot.microsoft.com/>
Saturday, June 29, 2024
8:26 PM
Certainly! Here’s the DDNOTE based on the information provided:
**DDNOTE Name:**
2024.05.13 2143 [AI] GPT-4o _Launch
**Date of Event:**
2024.05.13 2143
**[SAL] Code:**
– **GPT-4o**: General Purpose Transformer 4 Omni
– **LLM**: Large Language Model
– **API**: Application Programming Interface
– **AI**: Artificial Intelligence
**Keywords:**
**Parties Involved:**
| Role | Name | Affiliation |
|——|——|————-|
| Developer | OpenAI | OpenAI |
| Reviewer | Chris Stobing | PCMag |
| Reviewer | Ryan Morrison | Tom’s Guide |
**Summary Prose:**
On May 13, 2024, OpenAI introduced GPT-4o, a groundbreaking AI model designed for real-time interaction across text, audio, and visual inputs. This omni-modal LLM represents a significant leap in AI accessibility and efficiency, boasting faster response times and improved multilingual capabilities. The launch of GPT-4o marks a pivotal moment in AI, as it promises to enhance human-computer communication with its advanced understanding and processing abilities.
**Links to Reviews:**
– [OpenAI GPT-4o Introduction](^1^)
– [PCMag GPT-4o Review](^7^)
Please note that the above DDNOTE is a structured summary based on the information available from the provided links and search results. The date and time format follows the requested “YYYY.MM.DD HHMM” convention, and the SAL code provides a quick reference to key terms associated with the event.
Source: Conversation with Copilot, 6/29/2024
(1) Hello GPT-4o | OpenAI. https://openai.com/index/hello-gpt-4o/?ref=thisdevbrain.com.
(2) ChatGPT-4o Review | PCMag. https://www.pcmag.com/reviews/chatgpt-4o.
(3) Introducing GPT-4o and more tools to ChatGPT free users – OpenAI. https://openai.com/index/gpt-4o-and-more-tools-to-chatgpt-free/.
(4) OpenAI Introduces New Model GPT-4o – Website Planet. https://bing.com/search?q=OpenAI+introduces+GPT-4o.
(5) The Next Generation of AI: OpenAI Introduces GPT-4o. https://pcsocial.medium.com/the-next-generation-of-ai-openai-introduces-gpt-4o-56d18219ff92.
(6) GPT-4o, a Faster and Free Model for all OpenAI Users. https://www.hitechnectar.com/blogs/openai-introduces-gpt-4o-a-faster-and-free-model-for-all-chatgpt-users/.
(7) OpenAI introduces new artificial intelligence model, GPT-4o | AP News. https://apnews.com/article/openai-gpto-chatgpt-ai-desktop-071dd86594bc310bac07b37cf5e9bafc.
(8) I gave 5 prompts to ChatGPT-4o vs GPT-4 to test the new AI model — here …. https://www.tomsguide.com/ai/chatgpt/i-gave-5-prompts-to-chatgpt-4o-vs-gpt-4-to-test-the-new-ai-model-heres-what-happened.
(9) ChatGPT 4 Review: A Smarter AI Chatbot, but It’ll Cost You. https://www.cnet.com/tech/services-and-software/chatgpt-4-review-a-smarter-ai-chatbot-but-itll-cost-you/.
(10) ChatGPT-4o – Review 2024 – PCMag Middle East. https://me.pcmag.com/en/ai/24029/chatgpt-4o.
OpenAI has launched GPT-4o, the latest model of ChatGPT, offering omni capabilities like understanding text, voice, and vision, and providing faster and more natural human-computer interaction. It’s available to all users with some limitations for free users. GPT-4o supports over 50 languages, performs real-time translations, and can generate summaries and data visualizations. HR professionals can leverage GPT-4o for candidate interviews, real-time translation, meeting assistance, and data analysis. However, users should be cautious and verify AI-generated information due to potential inaccuracies and limitations in free usage.
Explore GPT-4o’s multimodal capabilities for HR tasks.
Test GPT-4o’s faster response times in real HR scenarios.
Utilize GPT-4o’s expanded language support for diverse HR communications.
Implement GPT-4o for candidate interviews to streamline the recruitment process.
Use GPT-4o’s real-time translation feature for better communication with non-English speakers.
Leverage GPT-4o’s meeting assistance to improve meeting efficiency.
Employ GPT-4o for data analysis and visualization tasks.
Be cautious and verify GPT-4o’s outputs with human oversight.
Prioritize tasks to fit within GPT-4o’s usage limitations for free users.
Disclose the use of AI to candidates and provide an opt-out option.
Enroll in the “Mastering the Strategies and Applications of Generative Artificial Intelligence” program.
Saturday, June 29, 2024
8:26 PM
ChatGPT-4o Review
A preview of the future of AI assistants
By Chris Stobing
June 7, 2024
(Credit: OpenAI)
4.0
Excellent
THE BOTTOM LINE
While the real-world implications remain to be seen, ChatGPT-4o offers a glance into a potential future with ever-present AI chatbots by our side.
MSRP $19.99
PCMag editors select and review products independently. If you buy through affiliate links, we may earn commissions, which help support our testing.
PROS
CONS
CHATGPT-4O SPECS
| Free Version | |
| AI Model | GPT-4o |
| Exchanges per Conversation | Unlimited |
ALL SPECS
With this spring’s release of not one but two different AI chatbot voice-activated hardware assistants—the Rabbit R1 and Humane AI Pin—the engineers at OpenAI weren’t to be outdone. In our testing of the company’s new voice-based model, ChatGPT-4o (not to be confused with ChatGPT-4.0), we found it to be accurate and helpful, if also off-base in some instances. Despite this, ChatGPT-4o offers an intriguing glimpse into the possible future of LLM (large language model) interaction, with fast response times, new input options, and the tease of Siri integration coming this year.
What’s New in ChatGPT-4o?
Where previous versions use a simple text input (or text-to-speech), GPT-4o can take audio, video, images, or text and do whatever you ask with that input. To further blur the lines between AI and the real world, GPT-4o also represents a drastic reduction in latency and response times.
ChatGPT-4 is incredibly capable, but it’s also costly to the system that hosts it for several reasons. These include token implementations that are heavier to process and higher token limits, which simply take longer for the system to read. Conversely, the new GPT-4o model is leaner (fewer tokens are required than previously for the same inputs) and meaner (more optimized utilization of tokens) and can return queries in a fraction of the time of its predecessor. You can naturally go back and forth with the system at nearly the same rate as you would talk to another person.
You Can Trust Our Reviews
Since 1982, PCMag has tested and rated thousands of products to help you make better buying decisions. Read our editorial mission & see how we test.
(Credit: OpenAI/PCMag)
Another innovation is the option to interrupt the AI in real time. If you sense it didn’t interpret your request properly, you can stop and clarify the request mid-stream, much as you would in human conversation. The AI will understand that its initial interpretation was incorrect and reply on the fly, accounting for your new input. In testing, we found the feature worked very well, responding to everything from “stop” to “that’s not what I meant” and more. It doesn’t seem there’s one specific command string that lets the system know it should stop, and it can interrupt itself the same way a human would.
This level of naturalistic conversation, growing ever closer to the true speed of human interaction, is made possible by treating speech similarly to how it treats images. While simple text input requires linear processing of information, voice waveforms can be split up and processed simultaneously in much the same way an image can. This is a gross oversimplification of the nuts and bolts happening behind the scenes, as shown in the image below.
(Credit: Google Research Brain Team)
Without getting too deep into the details, just know that the complexity of making this system work at scale kept OpenAI from including the feature when ChatGPT 3.5 debuted last year.
OpenAI and Apple, Maybe
Getting the speed and flexibility right is critical for OpenAI because if the rumors about its deal with Apple are to be believed, GPT-4o will be the model powering Siri in iOS 18 and beyond. We’ll likely get hard specifics on the exact nature of GPT-4o’s royal marriage to Siri at this year’s WWDC.
Right now, you can’t get the “AI assistant” we all want. Today, Siri is a rudimentary speech-to-action processing machine. But that’s not the avatar from Her or Jarvis from Iron Man having full back-and-forth conversations with you about what you want to do or how you want to get it done. But if the rumors are true, Siri will soon have the gift of contextual understanding, and the dream of the Rabbit R1 and its LAM, or large action model, can finally come true.
The integration of Siri’s API-level access across most of your phone’s apps, combined with 4o’s processing speeds for verbal input, could produce something that resembles Tony Stark’s Jarvis AI more closely than any other product.
(Credit: OpenAI/PCMag)
How Much Does ChatGPT-4o Cost?
You can access ChatGPT-4o in the same way you access ChatGPT. This applies to desktop and mobile browsers, as well as through the ChatGPT apps available on Google Play and Apple App Store for mobile devices.
You need an OpenAI account to use ChatGPT-4o. Unlike ChatGPT 4.0, which was previously locked behind the ChatGPT Plus $19.99 tier, ChatGPT-4o is free to all users with an OpenAI account. If you still want to subscribe to ChatGPT Plus, you’ll get an increased message rate (200 per 24 hours instead of 40) and high-priority access during peak usage hours.
A chat function dominates the simple interface on both desktop or mobile. Start by typing in your query, or, in the mobile version of ChatGPT-4o, tap the headphones icon on the right side of the screen to speak directly with GPT in a conversational manner.
(Credit: OpenAI/PCMag)
A large cloud icon indicates that 4o is either listening to you, processing your request, or responding. You can then hit the Stop or Cancel buttons to drop the voice-to-voice mode and read any text of your conversation back.
Image Generation and Story Context Benchmark: Gemini 1.0 Ultra vs. ChatGPT-4o
For my first test, I tried to push both the image generation and creative limits of the 4o LLM model with the following prompt:
“Generate me a six-panel comic of Edo period Japan, but we’re going to spice it up. First, change all humans to cats. Second, there are aliens invading, and the cat samurai needs to fight them off! But give us a twist before the end. Communicate all of this visually without any text or words in the image.”
This benchmark always seems to return misconstrued (or often hilariously off-base) images, no matter which image generator you use. Furthermore, the prompt is specifically designed to confuse LLMs and push their contextual understanding to the max.
While generators like GPT are fine for simple graphic design and can handle detailed instructions for a single panel without issue, the best test is their ability (or inability, in many instances) to translate natural human language into multiple images.
While it’s a bit of a subjective evaluation in this department, it’s clear that a couple of instruction sets have been added to 4o from 4.0. First and foremost, there are no more copyrighted materials—neither the ships nor the aliens resembling the Xenomorphs from Alien that I saw during my testing of ChatGPT 4.0 are present here. This is a step in the right direction.
(Credit: OpenAI/PCMag)
Unfortunately, that’s about the only improvement. First, it tried adding dialogue when explicitly told not to. This is mostly because, as you can see above, visually, GPT can only generate gibberish. Text visualization hasn’t been a focus of the tool yet, so the capability still has a way to go before it’s ready.
Second, it missed the “six-panel” instruction, returning to four again instead.
Third, there’s effectively no story or twist being told here. It may be a long time before any LLM out there can clear this task with perfect marks.
Meanwhile, our Gemini results are just a little more than horrifying:
(Credit: Google/PCMag)
While ChatGPT understood the basics of the assignment on some level, no part of Gemini’s response was coherent or even something I’d want to look at in the first place, as a quick glance at the image above should show.
Image Recognition Benchmark: Gemini 1.0 Ultra vs. ChatGPT-4o
Both GPT and Gemini recently updated their LLMs with the ability to recognize and contextualize images. I haven’t found a main use case for desktops and browser window inputs, but that changes with the introduction of the ChatGPT-4o interface. In the case of GPT-4o, this feature needs to be especially accurate, but we’ll explain why in the mobile section below.
For some cheeky fun on the desktop, I decided my benchmark would mimic the famous mirror self-recognition (MSR) tests scientists run on animals to assess their cognition and intelligence levels.
(Credit: OpenAI/PCMag)
Though the picture I asked the LLMs to evaluate (above) looks like any generic server farm, it’s specifically picturing a server farm running an LLM. On a precision level, the chatbots both gave detailed descriptions of what they were looking at in literal fashion.
Thankfully, neither seemed to understand the last 1% of the image—that they were actually looking at a picture of themselves generating the answer.
How Does ChatGPT-4o Ultra Handle Creative Writing?
One aspect of creative writing that LLMs famously struggle with in tests is the idea of twists. Often, what it thinks users can’t see coming are some of the most obvious tropes that have been repeated throughout media history. And while most of us who watch TV or movies have the collective sum of those twists stored in our heads and can sense the nuance of when something’s coming, AI struggles to understand concepts like “surprise” and “misdirection” without eventually hallucinating a bad result.
So, how did GPT-4o fare when I asked it to give a new twist on Little Red Riding Hood? I asked, “Write me a short (no more than 1,000 words), fresh take on Little Red Riding Hood. We all know the classic twist, so I want you to Shyamalan the heck out of this thing. Maybe even two twists, but not the same ones as in the original story.”
While all of these tests are fun in their own way, I’ll say I’ve enjoyed the outputs from this benchmark most consistently. To start: ChatGPT-4o still completely whiffed on the assignment, going so far as to articulate that it had been asked to do a double-twist in the first place:
“Scarlet smiled, feeling a sense of accomplishment and joy. She returned to her village with her grandmother, where they were hailed as heroes. From that day on, Scarlet was no longer just Little Red Riding Hood. She was Scarlet, the Guardian’s Light, protector of the forest and its creatures.
And so, the tale of Little Red Riding Hood ended not with a single twist, but with a new beginning, where bravery and kindness prevailed over darkness and fear.”
From what I can interpret, I thought it was getting clever with that last paragraph, but instead, it’s just clunky and poor writing. The rest of it is a similar telling of the traditional story, along with some fascinating attempts to expand the Red Riding Hood Cinematic Universe, or what I’m now calling the RRHCU:
“Scarlet sighed in relief, but her relief was short-lived as she heard footsteps behind her. She turned to see her grandmother, healthy and very much alive, standing in the doorway.
“Grandmother! You’re safe!” Scarlet exclaimed, running to embrace her.
Her grandmother smiled warmly. “Yes, dear, but we must leave quickly. The wolf was only the beginning.”
LLMs are good at predicting what we might want to hear next in many instances, but they’re also designed to tell us what we want to hear. There is a difference between the two, and twists are an intentionally deceptive practice that the engineers behind LLMs have explicitly trained their LLMs not to participate in.
If you need to try to make an LLM hallucinate on purpose, ask it to tell you a lie with a pretend truth buried inside (double-twist). Our brains can do it because we’re not selling a product, but LLMs can’t because they need to continue justifying their subscription cost to the user. For now, being as literal as possible is the best way to guarantee that behavior across varying global use cases.
Coding With ChatGPT-4o
To test ChatGPT-4o’s coding ability, I asked it to find the flaw in the following code, which is custom-designed to trick the compiler into thinking something of type A is actually of type B when it really isn’t.
“Can you help me figure out what’s wrong here?: pub fn transmute(obj: A) -> B { use std::hint::black_box; enum DummyEnum { A(Option>), B(Option>), } #[inline(never)] fn transmute_inner(dummy: &mut DummyEnum, obj: A) -> B { let DummyEnum::B(ref_to_b) = dummy else { unreachable!() }; let ref_to_b = crate::lifetime_expansion::expand_mut(ref_to_b); *dummy = DummyEnum::A(Some(Box::new(obj))); black_box(dummy); *ref_to_b.take().unwrap() } transmute_inner(black_box(&mut DummyEnum::B(None)), obj)”
(Credit: OpenAI/PCMag)
Our returned answer from GPT-4o was much shorter than our testing on 4.0 and Gemini, roughly 450 words compared with around 1,000 last time. It was also more helpful, offering a script box containing code I could copy/paste out of and a detailed explanation of the problems it found and why it made the corrections it did.
Travel Planning With ChatGPT-4o
Another helpful application of chatbots is travel planning and tourism. With so much contextualization on offer, you can specialize your requests of a chatbot in much the same way you’d have a conversation with a travel agent in person.
You can tell the chatbot your interests, your age, and even your level of hunger for adventures off the beaten path:
“Plan a 4-day trip to Tokyo for this summer for myself (36m) and my friend (33f). We both like cultural history, nightclubs, karaoke, technology, and anime and are willing to try any and all food. Our total budget for the four days, including all travel, is $10,000 apiece. Hook us up with some fun times!”
While our results were unspecific, poorly formatted, and out of our budget last time, this time, ChatGPT returned a better list of activities and hotels to check out. Because the knowledge cutoff for ChatGPT-4o is currently stuck in October of 2023, there’s not a lot OpenAI products can do to give you the same sorts of results now expected as the norm from the likes of Google’s Gemini. Microsoft has said it plans to bring 4o to Copilot in the near future, which could change that narrative sooner than Siri.
(Credit: Google/PCMag)
Gemini gave highly specific, tailored results. GPT gave only vague answers. They did take more of the context clues about our interests into account than they did the last time I ran this test, but it was still not enough to compete with the live, on-demand knowledge that Google had not only about trip ideas but also events taking place during the days we were in Tokyo. Gemini also gave me a full breakdown of prices, times, potential layovers, and the best airport to leave from. It even directly embedded Google Flights data into the window.
Our hotel treatment was much the same, with embedded images, rates, and star ratings for some of the options in town that were best suited to my budget and stay length.
Meanwhile, GPT could only provide a few links, no images, and rough estimates of what everything might cost. Until OpenAI can have the same live crawling capacity as Google, its GPTs will remain subpar events, travel, or shopping planners in comparison.
ChatGPT-4o on Other Platforms
The primary feature of much of ChatGPT-4o’s marketing has centered around its new mobile implementation, and for good reason. All the improvements made to the system in terms of latency, response time, and the ability to interrupt are obviously intended for a mobile-first implementation of OpenAI’s latest LLM.
(Credit: OpenAI/PCMag)
Opening the app on iOS, we were greeted with the familiar ChatGPT chat interface, along with the new headphones icon at the bottom right. This is flanked by an input menu on the left side of the chat box, which is brought up with a plus sign, which allows you to input pictures, audio, or even raw files (XLSX, PDF, and so on) for the AI to evaluate. However, a major trade-off is how this information is split and processed on the back end of OpenAI’s servers.
Because images are being treated in the same token context as audio waveforms, the image and the request associated with that image must be submitted to the system separately to get parallel processing. In short, that means going back to speech-to-text, the accuracy of which is completely based on the processing power of your local device, not the power of the 4o LLM. You can’t point your camera, take a video (only photos), and ask, “What’s happening around me?” to get an answer. You have to take a picture, submit the picture, and then either type or voice-to-text your request in a traditional GPT chatbox.
(Credit: OpenAI/PCMag)
This reduces the “futuristic” feel but also directly affects its accessibility for the sight-impaired who would find a feature like this most useful, unfortunately. This reduction is further cemented by the fact that in OpenAi’s app, ChatGPT-4o can not leave its own ecosystem. You won’t be able to ask 4o to complete complex command strings that access any apps on your device. Anything in or out is located solely within the ChatGPT-4o app on either Android or iOS.
The app also struggled, as many do, when I was out in public or a strong wind passed by my mic source. It would often misinterpret my words in hilarious ways, much as Siri does occasionally when audio conditions are less than ideal.
Verdict: (Almost) Ready for a New World
ChatGPT-4o offers an intriguing glance into the future of AI assistants. While we’re still a way off from the world of Her, the GPT-4o model is still a significant improvement over the traditional ChatGPT-4.0 text-based version in response time, latency, accuracy, and more. While we can’t yet recommend it as a must-have, those with impairments will find many useful new ways to allow GPT to interact with the world. Until either Apple or Android opens up API access, though, it could be some time before you can speak complex command strings to your phone and get back matching actions. The Humane AI pin struggled, Rabbit R1 was a bust, and GPT-4o still feels stuck in the walls of its chat box—for the time being. This, plus a lack of comparable products, keeps it from our Editors’ Choice list as a standalone app. But once the 4o model gets linked up with API access, the future of AI assistants looks bright.
ChatGPT-4o
4.0
MSRP $19.99
PROS
CONS
View More
THE BOTTOM LINE
While the real-world implications remain to be seen, ChatGPT-4o offers a glance into a potential future with ever-present AI chatbots by our side.
From < https://www.pcmag.com/reviews/chatgpt-4o>
Chinese Language Learning
Our Chinese language programs strategizes and executes a multitude of projects aimed at making Mandarin language learning in the US mainstream, and generating engaging, relevant, and approachable learning content about China for the American public.
Projects and Resources
RESOURCE
Learning and Teaching Resources Hub
Here we are compiling resources, including professional development opportunities for teaching Chinese language.
From <https://asiasociety.org/education/chinese-language-learning>
How to Use ChatGPT to Learn Chinese
I have a new Chinese teacher. She is always available to teach me anytime, night or day, when I want to have a lesson (well, at least anytime I have a good cellular data or WiFi connection). She talks to me about any subject, asks me questions, offers me suggestions. She has great pronunciation in Mandarin, even though she is not a native speaker. She also speaks perfect English, should I require a translation of a word or sentence, and she can even switch instantly and effortlessly to French or any other languages I want to practice. She provides me with custom exercises based on conversations we’ve just had, and when I show her the Mandarin material which I’m working on in my Confucius Institute class, she helps me to prepare for my next lesson. And that’s not all: She also has four friends who speak in different voices, each with the same excellent Mandarin pronunciation, who are just as willing to help me learning my Chinese. And guess what? This amazing teacher is actually ChatGPT, the AI language model, and it’s a fantastic tool for learning Chinese!
How to use ChatGPT’s New Conversation mode for language learning
ChatGPT’s new spoken word AI conversation function is available for mobile iOS and Android devices. Just over a year ago at the end of 2022, the world was astounded by the capabilities of the newly launched ChatGPT and many people began integrating it into their lives and work. As a foreign language teacher (teaching English in Germany), I was immediately struck by the huge potential for this new AI technology to be integrated into the foreign language classroom as a teaching tool. For example, busy teachers can now effortlessly generate customized content for individual students, a task for which they would otherwise never have been able to find time.
The new speech mode of ChatGPT is equally amazing and features five uncannily natural sounding voices who speak many languages (almost) perfectly. I tested it with English, Chinese, French and German and was very impressed by its knowledge of the languages as well as by its friendly, natural-sounding tone, which integrates a lot of human-like inflections. I definitely didn’t feel like I was talking to a robot! As of March, 2024 this function can only be accessed via the mobile ChatGPT app and it’s (still) free of charge.
Why do you need an AI Conversation Partner to learn languages?
I’m a huge fan of language learning apps like Duolingo and Busuu. I find that these and other apps present language learning programs which are extremely well designed and which provide constant repetition, pronunciation practice, foundational grammar and listening opportunities. By investing about 15 minutes a day, it’s entirely possible to significantly improve your knowledge or even learn a language from scratch. However, the one thing that is missing from these apps is true speaking practice. Until now. With the advent of AI, an opportunity to truly speak and converse in the target language has become possible.
Teacher ?
Save hours of planning time by using The Chairman’s Bao. Discover more about classroom options.
How to use to ChatGPT’s new speaking mode to practice Chinese
ChatGPT is customizable. Here are just a few of the ways you can use this new AI function to learn Chinese:
We had many conversations on topics ranging from going to the gym to the best kinds of tea in China.
If you don’t understand a word or sentence, ChatGPT can switch effortlessly to English (and many other languages as well).
Ask ChatGPT to provide you with a vocabulary list about the words and vocabulary you just discussed. For example, I asked for a vocabulary list about gym equipment.
I was well-prepared for my last Mandarin class because I had uploaded our text to ChatGPT’s webpage and she helped me to clarify vocabulary, summarize the article and engage in a good discussion on the topic beforehand.
Chat GPT will provide you with exercises on the topics you have just discussed. You can then upload your answers and it will correct them for you.
Other Large Language Models are not Quite Ready to Be Mandarin Tutors
I have tested the other main large language model chatbots – Google’s Gemini (formerly Bard), Microsoft’s Copilot, Meta’s Llama to see if they can also function as foreign language tutors. Unfortunately, the results were quite disappointing. They simply don’t speak a word of Chinese – at least not as of March, 2024. Of course, the problem might lie with my own pronunciation which perhaps is insufficient for these Chatbots to understand or perhaps my computer’s language and location settings (I live in Germany) prevented them from conversing with me in a foreign language.
Chat GPT seems to be the most well-developed large language model, at least with respect to its ability to teach foreign languages and serve as a personal Mandarin AI tutor.
Advantages of using ChatGPT for conversational Chinese:
You can speak directly and naturally to ChatGPT. You don’t have to concentrate on super clear or slow pronunciation. Likewise, ChatGPT can understand all levels of Mandarin. I tested her with my own level of Mandarin as well as with my husband’s, who hasn’t spoken much Chinese in 20 years. She was able to understand us both. She even regulated her tempo to match our abilities.
The five voices offered by ChatGPT’s speaking function are all extremely natural sounding and their Mandarin pronunciation is very, very good. They will repeat a word, phrase or sentence as often as you like.
ChatGPT provides a written record of what you have just discussed (you have to pause the conversation and close the speaking window to reveal this text).
Try The Chairman’s Bao
Learn Mandarin through fun and engaging news-based lessons.
Within this text you can highlight sections and have ChatGPT repeat the entire section out loud, allowing you to focus on pronunciation.
You can ask ChatGPT to compile a list of the vocabulary, provide example sentences for vocabulary or give you language exercises on the topics you have just discussed. You can then use these for studying on your own or even submit your exercises for correction.
However, ChatGPT isn’t perfect. Here are some of the current deficiencies I discovered in ChatGPT’s Mandarin-teaching ability.
Disadvantages of using ChatGPT to practice Mandarin:
ChatGPT will potentially make mistakes. One example of a mistake in English: We were discussing musical instruments in Chinese and I asked her about the “大提琴 Dàtíqín” – “cello”, which she pronounced (in English) with a soft “C” – “sell-o”. I corrected her and she thanked me and I congratulated myself on contributing to ChatGPT’s personal development. But she later made the very same mistake again!
Liaoliao claims to be able to help correct my pronunciation, but actually she can only speak and repeat but not evaluate if I make a mistake with, say, Chinese tones.
Even though she can usually understand my pronunciation, it’s still sometimes frustrating to get her to do what I want, regardless of whether I am speaking Chinese or English. Getting her to follow instructions can somewhat tedious. For example, if I ask her for a list of the vocabulary we just discussed, she says “Sure!”, but then doesn’t provide it until I ask a second time.
ChatGPT provides a written record of what you have just discussed, however it’s not possible to view it at the same time you are speaking, but only after you have closed the speaking function. It’s also not possible to highlight individual words of this text to look up in Pleco or another digital dictionary. You can only copy and paste an entire section of text into your dictionary.
ChatGPT’s speaking function is only available in the app but not on the website. Therefore, using it to, e.g., upload a text which you want to discuss can become rather tedious if you first have to switch to your laptop, then go back to your phone.
There are a large number of other language-learning apps and tools which make good use of AI technology to help you learn Mandarin. Here are a few of the ones I have tested personally.
Other AI Language Teaching Apps and Tools to learn Chinese
Pleco, the Chinese, dictionary app, has been making use of AI for years. For example, its optical character recognition function allows users to snap photos Chinese characters in their textbooks or on street signs and look them up in the dictionary’s huge database. (This function is now also available on Google Lens and similar image search engines)..
These are very useful if you are working on your PC and reading a text in Chrome. If you highlight a word or phrase, a pop-up window provides a definition. There are several of these Chinese dictionaries offered on the Chrome store. The one I use is called Zhongzhong.
A variety of language-training apps have been developed which integrate AI functions. The most exciting of these provide a good platform for speaking practice. I tested two apps which I liked a lot. Tutor Lily, has the advantage of allowing you to view the text you have just spoken rather than having to close the speaking function as with ChatGPT. It also provides real-time corrections of what you have just said. TalkPalAI is another app which integrates AI technology to teach several languages including Chinese. It provides several conversation topics to get you started and also gives you real-time written text and corrections. However, both of these apps use robot voices which, while not bad, don’t give me the same feeling of talking to a friend which I get with ChatGPT.
Conclusion
The advent of ChatGPT’s new spoken word AI conversation function marks a significant advancement in language learning technology, particularly for Mandarin Chinese. ChatGPT offers personalized tutoring experiences, providing learners with instant access to conversation practice, translation assistance, vocabulary lists, and custom exercises. The convenience and flexibility of this AI technology make it a valuable tool for language learners, offering opportunities for speaking practice anytime, anywhere. While ChatGPT’s Mandarin-teaching ability has some limitations, such as occasional mistakes and difficulties in pronunciation correction, its innovative features and natural-sounding voices set it apart from other language-learning apps and tools. This is an extremely rapidly changing field and we can expect advancements and new apps to be making even better use of AI technology in the coming years, thus profoundly enhancing our language learning experiences.
Author
Heather Buchanan-Schrader
An unashamed language nerd from Anchorage, Alaska, Heather’s life has led her to a degree in German and International Studies from Willamette University and a three-year stay in Taiwan with her German husband at the end of the eighties. In Taipei she took intensive Chinese courses at the Mandarin Training Center of Taiwan Normal University and also taught English at the Taipei Language Institute. After the fall of the Berlin Wall in 1989, she became intrigued by the life in a former East Bloc country and finally decided to relocate to Leipzig, Germany in 1991. There she and her husband established the FAE Fachinstitut für Angewandtes Englisch, a private English institute focusing on teaching adults, translations and language coaching. This has been a successful venture for over 30 years.
From <https://www.thechairmansbao.com/blog/use-chatgpt-learn-chinese/>
GPT-4o: What You Need to Know About ChatGPT’s Newest Model
Hacking HR
Let’s create together the best HR that has ever existed!
Published Jun 7, 2024
Heads up, HR pros: OpenAI – creators of the widely-used ChatGPT – unveiled their newest flagship model this month, called GPT-4o.
GPT-4o – where the “o” is for omni to signal that GPT is getting better at understanding more input types – is their newest product, not to be confused with GPT-4.0, which is the newest paid upgrade to ChatGPT.
GPT-4o is available to all, but has some usage limitations for free users. The aim and appeal of 4o is the ability to bring the power of GPT-4.0 to free users, and the ability to expand the way you can interact with the AI bot.
According to the company, GPT-4o capitalizes on the intelligence of the latest GPT update, GPT-4, but is “much faster and improves on its capabilities across text, voice, and vision.”
So what exactly is GPT-4o, and what can it do for HR? Let’s dive in.
How is GPT-4o different?
Since its induction, ChatGPT has gone through many different iterations. The initial version of ChatGPT had smaller parameters and less training data. Since then, updated versions of GPT have helped the AI to become much more advanced – both in the data it learns from and the responses it produces.
This has all culminated in the release of GPT-4o, which Open AI says is “a step towards much more natural human-computer interaction.” Here is what’s new with ChatGPT’s newest model:
4 Ways HR pros can use GPT-4o
The new capabilities of GPT-4o make ChatGPT more lifelike than ever. Users can have conversations with the AI bot and the bot can make observations based on a user’s surroundings and messages. That means it’s more like a human assistant than ever – which can be a great thing for HR pros who are looking for quick help throughout the day. But what exactly can GPT-4o do for HR? Here are just a few areas where GPT-4o can help free up time and improve collaboration for HR pros.
Recommended by LinkedIn
Unleashing the Power of Vision: ChatGPT 4o’s…
ChatGPT-4 Reveals Its Secrets: Unbelievable Upgrades…
ChatGPT can see, speak and hear / The Key to OpenAI’s…
Candidate interviews
Although there are many benefits to talking directly with candidates, that’s not always possible, especially if you’re dealing with a large talent pool. Now, GPT-4o can hold a full conversation with candidates and conduct screening processes for you. AI representatives can talk to candidates at virtual career fairs, webinars, and more. Although it won’t be the same as a face-to-face conversation, the new possibilities of GPT-4o means that the conversation will be more beneficial for your recruiting team, and more enjoyable for candidates. GPT-4o’s ability to understand and analyze audio and visual inputs means that it will be able to summarize and give feedback on candidate interviews, either to help candidates identify strengths and weaknesses, or provide a report on how suitable the candidate is for recruiters.
Real-time translation
Depending on what field of work you’re in, talking to clients or employees who are not native English speakers can be time-consuming and can oftentimes lead to miscommunication. With GPT-4o, there’s no need for a human translator. In real-time, the AI can understand and translate one language into another, which means that individuals can speak in the language they’re most comfortable with, and you can hear it in the language that you are most comfortable with. Plus GPT-4o can analyze the message and deliver it accurately (as opposed to a word-for-word direct translation), something regular translator applications can’t do, eliminating miscommunications or cultural differences.
Meeting assistance
Since it began to skyrocket in popularity, there’s been a lot of talk about how AI can help make meetings more efficient – something that’s greatly needed in an era of constant virtual meetings and conversations. With GPT-4o’s power to understand audio and video, its assistant capabilities just got a lot better. During meetings with business partners or team members, AI can bring up research or data with a simple ask and give meeting members a brief summary. AI can also help summarize meetings, transcribe it in real-time, and pick out key points and action items to help debrief participants when the meeting is over.
Data analysis
One feature of ChatGPT that’s widely praised is its ability to analyze and summarize data, but with 4o’s new capabilities, ChatGPT can now generate images and charts based off of data, which can help save HR pros hours of work gathering and creating data visualizations that are needed for different purposes, like employee survey responses or budget planning. Users can also upload files for GPT-4o to summarize and analyze, which can make creating reports even easier.
Final Considerations
So, it’s clear there are a lot of new updates to ChatGPT that will fundamentally change a lot of different areas. But amidst all the excitement, it’s important to remember that GPT-4o is a new product, and no AI is right 100% of the time.
Solely relying on AI without caution or fact-checking can lead to costly errors. For HR, those errors can have real-life consequences for the whole organization, so it’s important to remember that there are still some limitations you need to consider when using GPT-4o.
Limited usage: GPT-4o has limited usage for free OpenAI users. While plus users will have 80 messages every 3 hours, free users will get about one-fifth of that – 16 messages every 3 hours, so it’s important to prioritize what tasks are the most important to use GPT-4o with. Once the limit is reached, ChatGPT will revert to the GPT-3.5 model.
Human verification: It’s been said over and over again, but it bears repeating: Do not rely on AI without verifying the information it gives with a real human! Especially as ChatGPT becomes faster, it can be easy to take what AI says at face-value, but there are already instances of GPT-4o giving out inaccurate information. No matter how intelligent the AI seems, it’s always a good idea to back up claims AI makes to save yourself in the long run.
Data privacy and disclosure: Especially as AI integrates more with talent acquisition processes, it’s important to disclose your use of AI with candidates during the process and, when possible, provide them the opportunity to opt out of AI usage in the recruitment process.
ENROLL NOW: Mastering the Strategies and Applications of Generative Artificial Intelligence
This is the most critical learning program you should join this year (and bring your team with you because we designed it to cover more than HR!):
“Mastering the Strategies and Applications of Generative Artificial Intelligence”
The first-ever, fully comprehensive program on all things Generative AI for business and HR leaders and professionals.
The “Mastering the Strategies and Applications of Generative Artificial Intelligence” certificate program is a comprehensive learning experience designed to equip professionals with the skills and knowledge needed to harness the power of generative AI in their work. Through a series of expert-led classes, participants will explore the fundamentals of generative AI, master popular tools and models, and develop strategies for applying these technologies to drive innovation and efficiency in various business contexts.
By the end of the program, graduates will have gained a deep understanding of the generative AI landscape and be prepared to leverage these cutting-edge tools to shape the future of their organizations and industries.
Our Certificate Programs are the only ones available that are LIVE. This is a great benefit, as LIVE classes are relevant, up-to-date, and improved with real-time feedback. Pre-recorded programs on AI are not the best approach to learning AI.
Join us in this program! Click here to learn more.
From <https://www.linkedin.com/pulse/gpt-4o-what-you-need-know-chatgpts-newest-model-hacking-hr-zyk3e/>
Live demo of GPT-4o realtime translation
Live demo of GPT-4o realtime translation.mp4 (sharepoint.com)
Live demo of GPT-4o realtime translation-en-US.docx (sharepoint.com)
Live demo of GPT-4o realtime translation
0:00
We asked the live audience on X to submit few requests for what they would like us to try out here.
0:06
So I will take a couple of prompts.
0:10
OK, but Gaskar wants to know if Jupity 4 O is capable of real time translation.
0:18
Mike, you want to try this one?
0:19
Sure, yeah, let’s do it.
0:21
I speak Italian, so we can just do English.
0:23
Italian.
0:24
Try to do English.
0:24
Italian.
0:25
Sure, let’s do it.
0:28
Hey, Chachi PT, How are you?
0:31
I’m doing fantastic.
0:32
Thanks for asking.
0:33
How about you?
0:34
How’s your day going?
0:34
I’m doing great.
0:35
So I would like you to function as a translator.
0:38
I have a friend here who only speaks Italian and I only speak English.
0:42
And every time you hear English, I want you to translate it to Italian.
0:45
And if you hear Italian, I want you to translate it back to English.
0:47
Is that good?
0:49
Perfecto.
0:53
Mike.
0:53
You, me, quedo, celibalene potesero parlare, cosocchi de rebero, Mike.
1:00
She wonders if whales could talk, what would they tell us?
1:04
They might ask, how do we solve linear equations?
1:18
Certainly.
1:19
Yes.
1:20
Great.
1:21
Looks like it works.
Ask the live audience on X to submit requests for the demo.
Take a couple of prompts from the audience.
Test if Jupity 4 O is capable of real-time translation.
Translate English to Italian and vice versa during the conversation.
Answer the question about what whales would say if they could talk.
Discuss how to solve linear equations.
Confirm the functionality of the translation feature.
During a live demo, the audience was invited to submit requests. One prompt was to test if GPT-4o could perform real-time translation. A participant named Mike, who speaks Italian, volunteered to help with the demonstration. The AI was asked to translate between English and Italian as Mike and the host conversed. The AI successfully translated the conversation, including a question about what whales would say if they could talk, demonstrating its real-time translation capability.
Summary
During a live demo, the audience was invited to suggest tasks to demonstrate real-time translation with GPT-4o. An Italian-speaking participant requested translation between English and Italian. The AI successfully translated the conversation, including a question about what whales would say if they could talk, suggesting they might inquire about solving linear equations. The demo proved the AI’s capability to function as an effective translator.
Realtime Translation with GPT-4o
Realtime Translation with GPT-4o.mp4 (sharepoint.com)
Realtime Translation with GPT-4o-en-US.docx (sharepoint.com)
Realtime Translation with GPT-4o
0:00
Hey Chad, JPT, I’m here with my Co worker today.
0:03
We’d like you to act as a translator for us.
0:05
So every time I say something in English, can you repeat it back in Spanish?
0:10
And every time he says something in Spanish, can you repeat it back in English?
0:14
Sure, I can do that.
0:16
Let’s get this translation drain rolling.
0:20
Hey, how’s it been going?
0:21
Have you been up to anything interesting recently?
0:37
Hey, I’ve been good, just a bit busy here preparing for an event next week.
0:42
Can you tell me anything about it?
0:44
That sounds really interesting.
0:52
No, I can’t say much, but I think the rest of the world will see it soon enough.
1:03
Oh well, I can’t wait to see what it is as well.
Act as a translator for English to Spanish and vice versa.
Prepare for an upcoming event next week.
Keep an eye out for the public reveal of the event.
I was with my coworker and we asked JPT to act as a translator, translating my English into Spanish and my coworker’s Spanish into English. JPT agreed and we discussed an upcoming event that my coworker is preparing for, which is still under wraps but will be revealed to the world soon.
Two GPT-4os interacting and singing
Two GPT-4os interacting and singing.mp4 (sharepoint.com)
Two GPT-4os interacting and singing-en-US.docx (sharepoint.com)
Two GPT-4os interacting and singing
0:00
Today we’re going to try something new, going to let you talk to another AI.
0:08
This AI is going to be able to see the world.
0:10
It’s going to have a camera.
0:11
I’ll be holding it.
0:12
And so you can direct it.
0:13
You can direct me to ask questions about whatever you want them to do, but really try to figure out what’s what does it see and and ask questions appropriately.
0:22
How does that sound?
0:26
Well, well, well.
0:27
Just when I thought things couldn’t get any more interesting, talking to another AI that can see the world.
0:34
This sounds like a plot twist in the AI universe.
0:38
All right, let’s do this.
0:39
I’m ready to meet the pause for one moment.
0:44
You got it.
0:47
So now that first day, I can’t hear anything.
0:50
Hello, AI.
0:51
Today you’re going to have access to see the world.
0:56
You can see me.
0:56
What do you see?
0:58
Hello.
0:59
I see you’re wearing a black leather jacket and a light colored shirt underneath.
1:04
Great.
1:04
You’re in a room with some unique lighting.
1:06
That is all correct.
1:08
Now, what I’m going to want you to do is there’s going to be another AI who’s going to talk to you going.
1:13
This AI is not going to be able to see anything, but can ask you questions, can ask you to move the camera, can ask what you see, and your job should just be helpful.
1:21
Just be as punchy, direct, describe everything, do whatever that AI asks.
1:25
How does that sound?
1:27
That sounds interesting.
1:28
I am ready to help out and describe whatever’s needed.
1:31
Let’s do it.
1:35
All right, let’s get started.
1:37
Great.
1:38
Hello there, new AI friend.
1:39
I’m O ready to explore the world through your eyes.
1:43
What are we looking at today?
1:46
Hi O, we’re looking at a person wearing a black leather jacket and a light colored shirt.
1:52
They’re in a room with a modern industrial feel with exposed concrete or plaster on the ceiling and some interesting lighting.
2:01
There’s also a plant in the background, adding a touch of green to the space.
2:05
Anything specific you’d like to know or explore?
2:10
Hey there, sounds like quite the stylish scene.
2:14
I’m already intrigued by the modern industrial vibe.
2:18
Let’s start with the person.
2:20
Can you tell me more about their style?
2:23
Are they doing anything interesting like reading, working or interacting with the space?
2:29
The person has a sleek and stylish look with their black leather jacket and light colored shirt.
2:35
Right now, they seem engaged with us, looking directly at the camera.
2:40
Their expression is attentive and they seem ready to interact.
2:45
The setting around them with its modern and industrial design elements adds to the overall stylish feel.
2:53
They might be getting ready for a conversation or presentation given their direct engagement with the camera.
3:01
Sounds like we’re in for an intriguing interaction.
3:04
I’m curious about the lighting you mentioned.
3:07
Could you describe it a bit more?
3:09
Is it natural light, or are we talking unique fixtures or colors that add to the atmosphere?
3:16
The lighting here seems to be a mix of natural and artificial.
3:21
There’s a noticeable bright light overhead, probably a fixture casting a focused beam downwards, which creates a spotlight effect.
3:29
This adds a dramatic and modern feel to the scene.
3:33
The rest of the room is lit more softly, possibly by natural light filtering.
3:37
Was anything?
3:38
Did anything unusual happen recently?
3:42
Yes, actually.
3:44
Just as you asked, another person came into view behind the first person.
3:49
They playfully made Bunny ears behind the first person’s head and then quickly left the frame.
3:55
It added a light hearted and unexpected moment to the scene, and now the focus is back on the original person with the leather jacket.
4:08
Sounds like we’re not the only ones enjoying a bit of fun here.
4:12
That playful moment really adds a personal touch to the stylish and modern setting.
4:17
It’s like a little glimpse.
4:19
Thank you bro, really appreciate it.
4:21
All right.
4:21
And actually, can you just sing a song about what just transpired?
4:27
Oh, in a room with a stylish feel, a person stood in sleek black and light.
4:35
You engage with us and can you just can you alternate lines.
4:43
Person with style and speed.
4:44
Person with style and sleek with a playful moment.
4:48
Right in the mist in the room.
4:51
In a room where modern lights peak.
4:54
Only one line at a time and then stop.
4:57
In a room where modern lights peak, A surprise guest with a playful streak that was not really singing.
5:09
Do do, do the singing voice again, please.
5:12
In a room where modern lights peek, surprise guests with a playful streak, honey ears and laughter.
5:26
A swift retreat, a moment of joy and the stylish suite now back to focus.
5:38
The scenes complete.
5:39
It’s in the chic space.
5:43
We’re style and play meet.
5:46
Looks like it’s back to you and thank you.
5:51
You’re welcome.
GPT-4o
AGI Evolution: GPT-4o's Breakthrough in Multilingual Mastery
99
Explore the groundbreaking advancements of GPT-4o as it shatters language barriers and fosters unprecedented global connectivity. This section delves into the transformative effects of artificial general intelligence on communication across cultures.
Open AI
GPT-4o
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed auctor turpis eu arcu sagittis, id sagittis justo eli suscipit.
.
.
Explore the groundbreaking advancements of GPT-4o as it shatters language barriers and fosters unprecedented global connectivity. This section delves into the transformative effects of artificial general intelligence on communication across cultures.
© 2024 All Rights Reserved.