From Scarlett Johansen’s ChatGPT feud to Drake’s resurrection of Tupac for the sake of his Kendrick Lamar beef, 2024 has seen AI cement itself as the next big thing in tech. It’s coming to your iPhone, it’s made Nvidia a $3 trillion company and it’s time you learned how to use it properly. As with the early days of search engines, you’ve got a couple of choices as to which model to pledge your allegiance to and one of the best is Google's Gemini.
Having launched in the UK just a few weeks ago, it’s as good a time as any to get to grips with all this innovation is capable of. Especially since a lot of what Gemini is good at coincides with summertime chores, such as figuring out an itinerary for your week-long trip to Alacante or finding which nearby pubs have a beer garden you can book for the next England game. That’s why we hopped on a call with Serge LaChapelle, a product director at Google who’s a 17-year veteran of the search giant and has taken up the role of Gemini ‘evangelist’ for the company. Although his advice applies directly to Gemini, it also carries over to ChatGPT, Meta AI and whichever large language model you want an accurate answer from. So without further ado, here are Serge’s five AI commandments…
1. Turn complex tasks into a conversation
While you can ask Gemini how many goals Phil Foden has scored at Euro 2024 that would be a waste of its talents akin to playing the Man City player on the left wing. Besides answering basic questions is something Google (or even Siri) can do already. Where AI does come in handy is in carrying out tasks that previously would have required you to pull together information from a couple of different sources. Since Gemini, ChatGPT and the like have been designed to remember the context of your back and forth and use it to further refine their answers, you should also be asking follow-up questions as you go along to get even better results.
“Google search has always been about trying to get you specific answers like, ‘How is the weather outside?’” says LaChapelle. “With Gemini, you get to develop the conversation as you go and get to narrow it to exactly what you want.”
2. Be creative with your questions
AI assistants such as Gemini are particularly task-oriented right now. Sometimes that means you can use them to find solutions to household problems, such as making a recipe out of the ingredients you have left in your fridge. Elsewhere, you can use them to help them with work, such as drafting meeting notes from a call or even when prepping for interactions with your colleagues. “I'm a pretty informal guy, but there's a lot of people that work in very hierarchical organizations and they're very nervous about talking to their boss,” says LaChapelle. “I was really surprised at how many people are using Gemini to prepare what they'll tell their boss for their year-end review.”
The one thing you’ll want to avoid when using AI in the office? Passing off its work as your own. Just like nabbing someone else’s lunch from the fridge, you’ll get found out eventually.
3. Specificity is key
‘Garbage in, garbage out’ is the unofficial mantra of many AI assistants since the quality of your question (and the information being scraped to answer it) has a major bearing on how useful and reliable the answer is. Case in point, that brief moment when Google’s AI search summaries recommended users eat rocks and put glue on their pizza. Although building a holiday itinerary poses less risk to your overall gut health, LaChapelle recommends covering off four bases with any AI prompt…
- Persona: Who is asking the question?
- Task: What do you want the AI to do for you?
- Context: Why are you asking the question? What else should the AI know?
- Format: Do you want the answer in a bulleted list, a one-page document, to be written as a letter or something else?
So if you want to see some galleries, tell Gemini you’re a fan of Monet. If you have a vegetarian on the trip, let it know so you’re not recommended surf and turf. If you want to take a day trip somewhere then say so. The more specific you are the less likely you are to run into any AI’s limitations and get turned off using it in the process.
4. Don’t just type out your questions
Recently, several models such as Gemini have become multimodal, which means they can understand questions by text, photo and even video – or you can mix the two together for even more context. So you can take a photo of your holiday packing list, which accounts for all the kit a two-year-old might need when travelling abroad, ask if there is anything missing and whether that revised list will comply with British Airways’ baggage limits all in one fell swoop.
Better still, Gemini connects to Google’s existing array of products meaning an itinerary can be exported to Google Maps in an instant, while biblical PDFs can be summarised into a Google Doc. So the next time you get sent a tome of a report by an overly verbose colleague, you know what to do…
5. Don’t expect a perfect answer every time
Although AI has come a long way in the last few months, no large language model has quite achieved the super intelligence that Joaquin Phoenix fell in love with in Her. Since they mostly work by crawling the Internet for data and then recontextualising it in an answer, there are a fair few subjects where AI just isn’t that useful. Summarising breaking news is one since there’s a paucity of accurate information to draw upon, and another LaChapelle highlights is math. So if you’re going to use ChatGPT to do your homework (or check your child’s), you might want to double-check any particularly complex answers. At least, until these models improve further.
“One of the challenges with AI is that it's this amazing new technology, but you can use it for something it’s not particularly good at and then you're like, ‘Oh maybe it's just a learning curve,’” says LaChapelle.
Google Gemini is available to download from Apple's App Store or the Google Play Store, and can also be accessed at gemini.google.com