More

    I just tested Google Gemini Advanced — and it offers a real alternative to ChatGPT Plus

    $19.99/month for Gemini Advanced !!

    Google has officially unveiled its Gemini Ultra 1.0 artificial intelligence model “Google Gemini Advanced”, which the firm says can compete with OpenAI’s most powerful AI model, GPT-4-Turbo, on the majority of workloads. If accurate, it would be the first serious challenge to OpenAI’s ChatGPT since the beginning of the GenAI boom.

    To make things unclear. Google has rebranded its chatbot from Bard to Gemini, so both the underlying model and the service you use to access it now have the same name.

    I’ve been wanting to put Gemini Ultra to the test since it was initially introduced in December, promising genuine multi-modal support for photos, video, text, speech, and coding. It is only available with a $19.99/month subscription to the new Google One AI Premium plan, which I subscribed to.

    This isn’t an exhaustive review or comparison to ChatGPT — they will follow in time — but more a snapshot of my experience playing with it in the first 24 hours since its launch.

    First thing I tried — coding

    The first thing I test on each new chatbot is its coding ability. This is something that should come easily to AI and one of the earliest commercial use cases for generative AI even before ChatGPT.

    Google made a big fuss of Gemini Ultra’s coding ability, so I asked it to develop a website to evaluate how well that translates into useful coding assistance inside the Gemini Advanced chatbot.

    I created an image of an anime-style pixel-art cat sitting on a fence. I showed Gemini this photo and the idea of the cat becoming the hero of a new program about a cat spy called Cat-astrophe. I then requested it to produce a CSS style sheet using the image’s colors.

    It didn’t perform an excellent job, only picking a tiny number of colors, but it was able to generate a usable CSS. I then requested it to develop a website for my hypothetical cat show using that CSS, and it performed an excellent job. All I had to do was provide the right link to the photograph.

    Making images inside Gemini

    (Image credit: Google)
    Google Gemini Advanced
    (Image credit: Google)

    Image creation is not something that Gemini Advanced performs automatically. Google DeepMind has constructed a distinct Imagen 2 model to handle this. However, its enhanced reasoning and comprehension should enable greater collaboration between me and the chatbot, as well as a better image.

    I began by asking it to make an image of my favorite test topic, “Cat on the Moon,” with the words “Cat on the Moon” at the bottom. It provided me with two photos that did precisely as I requested.

    However, I could accomplish it with Bard already, so I attempted to confuse Gemini. I instructed it to put the cat in a spacesuit and place it on the Moon’s surface with the Earth in the backdrop. But keep the same visual style as the one you’ve already generated.”

    I did what I asked, as I asked, but didn’t add the text back on. When I asked it to add the text to the bottom left corner it created a new image and put it in the top right — not a win but other AI platforms also struggle with consistency over image generation and at least the text was legible.

    An infinite number of bots writing Shakespeare

    Google Gemini Advanced

    One area where AI is beginning to shine is poetry, notably adopting or replicating the style of previous creators. So I asked Gemini Advanced to create a Shakespearean sonnet on the console wars. It worked well on the first run, however there was no mention of any console.

    I then asked it to be more precise, which resulted in an excellent work of poetry. The difficulty is that this isn’t very difficult for an AI, so I asked it to extract the most frequently used words in the sonnet and use them to create an intriguing statement with only those words.

    With this test, I was hoping it would recognize the most common terms like “of,” “is,” and “or” and then produce something interesting. It didn’t, and I had to keep trying till it gave me the common terms but not the message. In comparison, ChatGPT received my request on the first attempt.

    The poem written by Gemini Advanced:

    Three banners fly where digital wars rage,
    A battleground where loyal players stand,
    Xbox and PlayStation, legends on the stage,
    With Nintendo’s charm, a magic in its hand.

    From bygone days when rivals clashed and burned,
    Where hedgehog swift and plumber bravely fought,
    The embers of those battles have returned,
    Though names have changed, the passion is untaught.

    Green, blue, and red, their colors mark the lines,
    Each champion boasts of power yet unseen,
    With worlds immersive, narratives that shine,
    The choice divides where gamers may convene.

    Yet ‘neath the fray, a shared love does abide,
    For in the realm of play, all hearts collide.

    Conclusion — good but needs some work

    Google Gemini Advanced

    I was generally satisfied with the responsiveness of Bard… err… Gemini Advanced in comparison to prior generations. It provided reasoned and organized responses to even hard questions, but it did not answer as much as I had expected.

    It feels like it’s waiting for some fine-tuning and extra capabilities to be enabled, but when it happens, it’s easily comparable to using ChatGPT Plus.

    What remains to be seen is how much better it becomes as Google updates the bot based on user feedback, real-world use cases, and fine-tuning.

    Recent Articles

    Related Stories

    Leave A Reply

    Please enter your comment!
    Please enter your name here

    Verified by MonsterInsights