I used an AI stylist for five days and hated it
For five days, generative AI became my personal stylist. It told me what to wear and how to wear it. It chose my hairstyle and lip colour. It even suggested to the manicurist that yellow was my colour.
Generative AI—which can do everything from write code, conduct makeshift therapy sessions and create designs for fashion designers—could add close to $300 billion in the next five years to the operating profits of apparel, fashion and luxury sectors, says a 2023 report by consulting firm McKinsey. It can do so, the report adds, by helping streamline design and supply chain issues, but more importantly, it can allow shoppers to try on clothes via their devices, and add chatbots as shopping assistants to help people sift through their wardrobe and make better style decisions.
So, I decided to dive into the world of AI with three apps to see if algorithms could change the way I dress.
Also read: Gen Z can't stop buying fast fashion and won't repeat outfits—here's why
One was ChatGPT, the popular US-born general-purpose tool, and the other two were newly launched homegrown platforms, Glance AI and Slayrobe. These three AI advisers, or stylists, saved me time and lessened the burden of making a decision each time I opened my wardrobe. But they seemed to have one agenda: turn me into a blind follower of trends.
Sample this conversation with ChatGPT.
Me: Hey ChatGPT, What should I wear to office today? I work in a newsroom and I want to wear something corporate-ish but a little casual and it should look all very effortless.
ChatGPT: That's a great idea. I'd suggest going for something like this:
A simple, well-fitted blazer in a neutral colour (like navy, black or grey), but leave it unbuttoned to keep it relaxed. Pair it with a plain shirt. Chinos in a neutral shade, or dark jeans if you want to keep it even more casual. Casual loafers or stylish sneakers. Keep accessories minimal.
Me: This is too boring. And it's 40 degrees Celsius here, so blazer is out. I'm a fashion writer and I want something different and stylish. Suggest more options?
ChatGPT: Wow! A fashion writer, I'm jealous of you, girl! Of course, here's something for that 'unbothered but unmistakably stylish" look. Lightweight cotton shirt with 3/4th sleeves or rolled long sleeves. Tuck it in slightly at the front (French tuck) for that casual-editor vibe. Straight or wide-leg trousers in breathable fabrics like linen. Chunky flats or sleek platform slides. Bold earrings or a structured minimalist necklace. Go for a low sleek bun. Add gold hoops—bam, you're Anna Wintour's cooler cousin.
It's not bad advice, but recommending rolling up the sleeves or adding an ankle-length skirt for a Parisian touch isn't exactly going to up my style game.
Then, I turned to Slayrobe. After logging into the app, you have to enter your height, identify your body shape (round, triangle, rectangle, inverted triangle, hourglass), features you want to flaunt/downplay, and your 'style agenda" (Effortless Chic, Dreamy Diva, Bold Boss, Timeless Queen). Then comes a barrage of looks, from clothes to jewellery, all based on algorithms trained on over 70,000 styling decision points.
You can also buy the suggested options—the app leads the user to the respective product's brand website. There's colour analysis in case you wish to know which shades are meant for your skin tone. And a wardrobe organiser allows you to upload a photo of your garments and create looks, like Cher Horowitz's outfit-picking computer in Clueless (1995).
'Women are being overfed with trends, and despite this, the universal feeling remains: We have nothing to wear," says Slayrobe's founder-CEO Pooja Lalwani, who's earlier worked on fashion tech initiatives at Google and Tommy Hilfiger. 'I wanted to create one platform where you can get help organising your wardrobe, style yourself better, know your colours and then post about it." The women-only app is designed to let you post your photos on the feed and as Stories, and follow other people—much like Instagram.
After choosing the option of Dreamy Diva as my 'vibe", I asked the stylist bot to help me find some timeless office wear style ideas. The responses were: 'Embrace soft, flowing fabrics", 'accessorise with delicate details", don't 'overdo with embellishments" .... again, all useful tips but nothing new.
But for a school student like Aashna Gulati such information is useful. 'I am still figuring out what my style is," says Mumbai-based Gulati, 16, who constantly experiments with AI apps to find fashion inspiration. 'I shop after seeing (on AI stylist apps) what will look good on me. I want to dress like Kendall (Jenner), Kareena (Kapoor Khan) but I don't have their stylists, so this is the best option for me."
Also read: The salwar returns to the runway with a new look
That's the promise of an AI stylist. It might not give you exactly what you're looking for but it can direct you towards what you might like.
'AI gets the basics right. It can tell you how a sage green blouse, a pair of canary blue trousers and a burgundy bag will look together but it can't tell whether that combo will suit you," says celebrity stylist Isha Bhansali, who's styled the likes of actor Ayushmann Khurrana. 'It's also about how much you care about personal style. Many people are just happy with following trends and shopping accordingly, and AI helps with exactly that."
Glance AI works on this theme: it creates fully styled, shoppable looks based on your body type, personal taste, lifestyle and mood, all on the phone.
After entering my details, Glance AI offered a variety of looks in a somewhat Pinterest moodboard way. Under Ready For Safari, for instance, I could see a myself—the app asks you to upload a selfie—wearing a moss green casual shirt from two brands, one ₹664 and other, ₹1,799, depending on your budget. The options were followed by text explaining how the collection 'merged utility and sophistication, featuring earthy tones, linen and structured silhouettes for an elevated, adventure-ready and stylish look". Choice of a green shirt for safari? Definitely not out of the box.
'We're built for Gen Z and millennial consumers," says Mansi Jain, senior vice-president and general manager, Glance AI. 'These are users who want AI to curate for them—not just show options. It marks a shift from marketplace models to inspiration-first commerce, where the AI stylist becomes the first touchpoint of fashion discovery."
Can an AI stylist replace a human stylist? It depends on who you ask. Bhansali compares AI to a calculator, saying 'it works on calculations, trends and not emotions, and fashion is so much about emotions."
Jain's take: 'Unlike human stylists, AI stylists scale to millions, adapt in real-time, and learn from every interaction. Our models don't just react to trends—they understand your style graph, predict what will resonate, and visualise you in it with near-photorealistic accuracy."
The thing is AI can offer answers when you're searching for your sense of style but it cannot serve you that personal touch that makes you you. Whether it was the taupe blouse ChatGPT suggested I wear for an interview, or the smokey party make-up I did after going through different looks on Glance AI, or the red salwar-kameez I zeroed in on for a family puja, they were all 'uniform"-like answers. And so very boring and predictable.
As Bhansali says, 'If I told ChatGPT I am on my period, it won't suggest anything white because that information has been fed into it. But what if my mood is to wear white? Style can be dictated by algos, not personal style."
When I asked ChatGPT if it believes AI stylists can supersede human counterparts, it said: 'AI is the calculator. The human stylist is the architect. Both can do math. Only one can build the Taj Mahal."
Also read: Why labubu dolls, Disney cartoons have entered the adult wardrobe
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Indian Express
29 minutes ago
- Indian Express
Delhi must underline for Washington the grave dangers of Asim Munir's vision of Pakistan
In 2018, in his first term, US President Donald Trump had spelt out, in his typically blunt style, the sense that Rawalpindi and Islamabad had taken advantage of Washington: 'The United States has foolishly given Pakistan more than 33 billion dollars in aid over the last 15 years, and they have given us nothing but lies & deceit, thinking of our leaders as fools… they give safe haven to terrorists'. This week, he said: 'I love Pakistan'. It would be simplistic to view the unprecedented lunch meeting at the White House between Trump and General Asim Munir — the first time a military leader who is not head of state in Pakistan has been accorded the honour — as a major u-turn. Indeed, India-US ties have been steadily deepening over the last three decades, based on a convergence of economic and strategic interests and shared values, even as the US-Pakistan relationship has grown more volatile. That said, the current moment in international relations is one of flux and Delhi must tread carefully. The Pahalgam attack underscored the grave national security threat that Pakistan-sponsored terrorism continues to present for India. With Operation Sindoor, Delhi has made it clear to both Rawalpindi and the world that it will pierce the shield of 'proxies' and not give in to Pakistan's nuclear blackmail. India has raised the costs of terror in order to ensure that such attacks on its soil are not carried out with impunity. Communicating the new normal it has etched with Pakistan after Pahalgam to its friends abroad is Delhi's challenge. To be sure, Delhi cannot control who Trump chooses to engage, and for what reasons. Pakistan's geography — it shares a 900-km border with Iran — may make it an attractive tactical partner for the US in the current Israel-Iran war. There is speculation that Pakistan's rolling out the red carpet for the privately-owned US cryptocurrency firm, World Liberty Financial (WLF), may have helped ingratiate Munir to the White House — Donald Trump Jr has close ties with WLF. A White House spokesperson has claimed that Munir has proposed Trump for the Nobel Peace Prize for his self-proclaimed role — firmly denied by India — in the post Op Sindoor cessation of hostilities. For India, though, the question is less why the Munir-Trump meeting, and more about how to ensure that the red lines it has laid down are respected, including by the US. Just a fortnight before terrorists killed 26 people in Pahalgam after confirming their religion, Munir had reiterated some of the nastiest tropes of the two-nation theory. He called Kashmir Pakistan's 'jugular vein', and reduced the complex and layered identities of the Subcontinent's people to their religion. It is now for Delhi — diplomatically, through the appropriate channels — to remind Washington that Pakistan's Field Marshal is a fundamentalist with an army at his disposal. Delhi has done well so far in standing its ground and making it clear that it will not compromise on its national interest: Even if belatedly, it issued a clear denial of President Trump's claims about mediating the ceasefire. Now, it must underline for Washington the danger that Munir's vision of Pakistan poses for stability in the region and for global order — and why Delhi has drawn some hard red lines.
Mint
an hour ago
- Mint
The advertising industry parties in Cannes, with AI as its new plus-one
Tech companies like Spotify annually host parties for clients and business partners at the Cannes Lions advertising festival, where attendees are known for letting loose after dark. After several years of small experiments with AI and big anxieties over its impact, advertising executives got with the program at this week's Cannes Lions International Festival of Creativity, the ad industry's annual five-day gathering on the French Riviera. Almost every company that took over a swanky beach club, hosted guests in a villa or bought its staff $5,000 festival passes told an enthusiastic story about artificial intelligence. Raging against the machine was firmly out. Any remaining rank-and-file worries about job losses were mostly voiced far from official events. 'We've moved beyond the promise and the fear to the practical application," said Don McGuire, chief marketing officer at chip maker Qualcomm, adding that the company is saving 2,400 hours a month by using an AI agent-building tool called Writer. 'People are talking about using it in different contexts. It's no longer, 'Well, it could do this, or could do that.' " Two years ago, at the first Cannes Lions since the debut of ChatGPT announced AI's new potential, ad agency Monks co-founder Wesley ter Haar set up in a small apartment. Cassandra-like, he told visitors that AI was about to upend ad creation and employment. Executives at other companies in Cannes that year described their trials with the technology but emphasized that only humans can develop the emotional insights that steer ad campaigns. This time the idea of AI-driven industry transformation was mainstream, even if leaders still expressed confidence about humans' continued role. 'Obviously the world of business, and the world at large, is being profoundly disrupted as we speak, and the impact on jobs is already being felt," said Marisa Thalberg, the chief customer and marketing officer at Catalyst Brands, the company formed by the merger of Brooks Brothers-owner SPARC Group and JCPenney. 'My optimism comes from knowing how much creativity is—and will remain—so fundamentally and uniquely human, even if the ways we harness and express it continue to change." Instagram and Facebook owner Meta Platforms used the festival to unveil a host of new AI-based products designed to help advertisers make ads as quickly and simply as possible, feasibly without the need for an agency. Executives at the company repeatedly said the tools weren't designed to replace agencies, however—just to speed up their work and help smaller businesses that can't afford agencies. Marketers in Cannes even put concerns such as President Trump's trade war and tightening consumer budgets on the back burner in favor of talking about AI. 'I didn't have one single conversation about tariffs," said Yannick Bolloré, the chairman and chief executive officer of French advertising holding company Havas. The guest list-only 'cafe" run by Havas on the grounds of the Mondrian Hotel used AI to turn guests into 3-D characters in a movie using only a photo. The company last year said it would invest 400 million euros, or more than $429 million at the time, in AI development over the course of four years, a commitment similar to those made by rival holding companies. Now Bolloré is asking that his staff refer to AI agents as 'teammates." 'Those agents will be fully part of the Havas family," Bolloré said. 'In terms of employees we will find a lot of efficiencies, but our bet is that we will manage more revenue with the same amount of people." But reality isn't always close at hand during Cannes, a 13,000-person conference where $1,355 magnums of Dom Pérignon are regularly ordered to business tables at lunch, and executives' public displays of affection for AI began to wear thin with some. Lower-ranking attendees darkly joked at post-programming parties that they'd be replaced by their artificial counterparts before the next festival. And research published Monday raised some red flags for agencies, most of which have been racing to build up their AI arsenal. Agency trade association the 4As and consulting firm Forrester found that although 75% of agencies are using the technology—up from 61% last year—75% of those using it are also funding it directly without passing on the costs to clients, up from 41% in 2024. 'That is deeply concerning," said Jay Pattisall, principal analyst at Forrester, who wrote in the report that 'agencies are backsliding into antiquated commercial models that led to the commoditization and lack of transparency associated with marketing services." The strongest pushback to the AI overload at Cannes came from the celebrities and social-media content creators who now flood Cannes along with traditional ad players and tech companies. Actors Josh Duhamel, Reese Witherspoon, JB Smoove and others touted their own creative companies but also made a case for the employment of Hollywood talent in the ad industry. Advertising benefits from emotional connections that actors, directors and scriptwriters know how to provide, Smoove said. 'We're talking about mastering the moment," Smoove said. 'You meet somebody that you haven't seen in years and they tell you a funny joke? AI can't do that."
Mint
an hour ago
- Mint
Meta wanted to buy a $30 billion AI startup: report. What it is trying instead.
Meta Platforms stock has climbed this year in response to the social media company's progress with artificial-intelligence. Now, it is reportedly stepping up its efforts, trying to acquire a major AI start-up and recruiting new AI executives. Meta looked to buy Safe Superintelligence earlier this year but was rebuffed by its founder Ilya Sutskever, CNBC reported late Thursday, citing people familiar with the matter. Safe Superintelligence was valued at $30 billion in a funding round in March. Meta and Safe Superintelligence didn't immediately respond to requests for comment. On the face of it, such an acquisition would have been an odd move. Safe Superintelligence hasn't released any products, as it concentrates on developing supersmart AI. Meta has also been getting along perfectly well on its own, with its stock up 19% so far this year. The real attraction of such a deal likely would have been to get Sutskever and his key employees on board. Sutskever was previously chief scientist at OpenAI, where he helped develop the technology behind ChatGPT. He left OpenAI last year following a break with its CEO Sam Altman, and subsequently launched Safe Superintelligence. Thwarted in his efforts to bring Sutskever on board, Meta CEO Mark Zuckerberg has instead negotiated to recruit Safe Superintelligence's CEO Daniel Gross, as well as former GitHub CEO Nat Friedman, according to CNBC. Gross and Friedman are partners in the investment fund NFDG, which has backed several AI start-ups. So far, Meta has relied on in-house AI models, as opposed to acquiring or funding an AI start-up as Microsoft has done with OpenAI and has with Anthropic. However, there have been signs that Zuckerberg feels Meta's AI team needs bolstering. Last week, Meta completed an investment in Scale AI. The Wall Street Journal reported that Meta would pump $14 billion into the data-labeling company in exchange for a 49% stake and that Scale AI founder Alexandr Wang would join Meta. The bigger picture here is that multiple AI companies have delayed the releases of their next flagship models amid concerns they don't show sufficient improvement. That suggests the industry's 'scaling law," the idea that larger and more complex models are automatically more intelligent, is breaking down. Meta is among those struggling to make a breakthrough. Its 'Behemoth" model, originally meant to be released in April, is being delayed until fall or later, according to the Journal. The response from AI companies has been the development of so-called reasoning models that break down problems step-by-step. However, a recent paper from researchers at Apple found 'fundamental limitations" in such models. At tasks beyond a certain level of complexity, these AIs suffered 'complete accuracy collapse," according to the researchers. That suggests the industry will need to adopt new techniques to push AI to the next level of intelligence. Meta will hope that its new recruits can get there first.
