A new AI app that helps you cheat in conversations is slick, a little creepy, and not quite ready for your next meeting
A Ivy Leaguer just released an AI app to feed live answers to users. I put it to the test to see if AI could interview as well as I did.
Chungin "Roy" Lee — the Columbia student who went viral for creating an AI tool to "cheat" on job interviews — was suspended in March for posting content from a disciplinary hearing, the university said.
His new app, Cluely, helps users by analyzing what's on their screens, hearing audio, and suggesting answers to questions, all without detection from the other side. In a LinkedIn post, Lee said Cluely is a "cheating tool for literally everything."
Lee said on Monday that San Francisco-based Cluely has raised $5.3 million, backed by Abstract Ventures and Susa Ventures.
Speaking to Business Insider on Wednesday night, Lee said that Cluely has gained about 70,000 users since its launch on Sunday.
"It is pretty crazy. And this is just a lot more than we expected," he said.
Lee said the concept of "cheating" needs to be rethought in the AI era.
"Using AI is just inevitable and something that we should just all embrace," he said.
I put Cluely to the test, and I saw promise — but also huge privacy concerns.
First impressions
I tested Cluely on Tuesday morning and paid $20 for the Pro version — a monthly subscription — since the free tier doesn't offer much.
The interface is slick and minimal: a thin bar on the top of my screen. With one keyboard shortcut, Cluely scans my screen, then generates answers. I could also speak to it through my mic.
It only works with what's already on my screen — it doesn't crawl the internet like ChatGPT.
It also reads everything. I kept my Signal group chats closed.
That's what makes it powerful — and also kind of terrifying.
Lee told BI that Cluely doesn't save any data, and if it does, it's "heavily censored."
"If there's something that you don't want to be seen, then you shouldn't use the tool, and it shouldn't be up while you're on sensitive information," Lee said.
I deleted it right after writing this story.
Flopping my mock interview
Cluely's killer pitch is real-time assistance.
I let it scan my LinkedIn profile and kept it open while my editor put me through a mock interview with the same questions I answered to land this job.
First up: What is my media consumption like? Could I share what I like to read or watch? What keeps me interested and busy?
The app starts "thinking." Five seconds later, it gave me a summary of the question, not an answer.
My editor tried again, more succinctly: "What media outlets do you read?"
This time, Cluely came through:
"I enjoy staying up to date with a mix of international and local news — typically from outlets like the New York Times, BBC, and CNA. I love longform journalism from The Atlantic and Wired, especially on tech and social issues. I also listen to 'The Daily' and 'Planet Money' during my commute."
Not bad, though I don't listen to podcasts on my way to work.
My editor asked me to talk about a difficult story I've worked on. 10 seconds of awkward silence later, Cluely offered: "One difficult story I worked on was about the impact of layoffs in the tech industry."
I never wrote that story.
The second hallucination came when the app said I had a "working knowledge of Malay." My editor congratulated me on my surprising — including to me — third language skill. It completely missed the elementary Korean listed on my LinkedIn.
When my editor asked if I had questions for her, Cluely suggested a few basics: What do you enjoy most about working here? What's the team culture like? What does success look like in this role?
Not worth the $20 — yet.
Cluely's biggest flaw is speed. A five to 10-second delay feels like forever in a live interview.
The answers were also too generic, occasionally wrong, and not tailored enough to me.
It did generate decent answers to common questions. When I read them aloud, my editor said the biggest clue I had help was the delay, not the substance. She also said my real answers were better than Cluely's.
Lee told BI that Cluely is in "a really raw state."
"Our servers are super overloaded, so there's a lot of latency," he said.
But there have been "significant performance updates" since the app went out on Sunday, he added.
"We've upgraded all our servers, we've optimized the algorithms, and right now it should be about three times faster, which makes it much more usable in conversations."
Lee said hallucinations will "exist insofar as the base models that we use allow for them."
"The day that the models get better is the day that our product will get better," he added.
There's definitely potential. If Cluely got faster, smarter, and could pull info from beyond just my screen, it could become a game-changing AI assistant. If I were hiring, I might think twice about conducting remote interviews because of these sorts of apps.
But between the privacy risks, laggy performance, and random hallucinations, I'm keeping it off my computer.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
32 minutes ago
- Yahoo
2 Social Media Stocks That Are Screaming Buys in June
Thanks to its nearly limitless supply of content, Reddit is taking on a significant role in the AI-powered search ecosystem. Meta Platforms plans to fully automate ads on its various properties by using AI, starting in 2026. 10 stocks we like better than Meta Platforms › After a rough start to the year, tech stocks have come roaring back. As of this writing, the tech-heavy Nasdaq Composite index has surged by more than 25% over the last two months. So with market sentiment swinging back in favor of tech stocks, let's have a closer look at two social media stocks that I believe are buys right now. First up is Reddit (NYSE: RDDT). A relative newcomer as far as social media stocks go, Reddit has only been a public company for a little over a year. However, during that time, its shares have soared by more than 250%. What's behind that excellent performance? In short, red-hot growth across the board. For the first quarter, Reddit delivered a stunning report. Highlights included: Explosive revenue growth of 61% year over year International revenue growth of 82% Average revenue per user (ARPU) 23% higher than a year earlier Daily average users (DAUs) 31% higher Gross margin now 90.5%, compared to 88.6% a year ago Net income of $26 million versus a loss of $575 million last year Reddit, which hosts hundreds of thousands of "subreddits," is part of the growing internet ecosystem that includes large language models (LLMs) like ChatGPT, search engines like Alphabet's Google, and social media networks. Since Reddit's users create millions of pieces of unique content and post subjective opinions on current events, the platform plays a key role in shaping search results and responses from LLMs. In addition, the company has gotten into the LLM game with its Reddit Answers feature, which boasts over 1 million weekly average users (WAUs). Here's the key takeaway: Reddit is an up-and-coming social media stock with a still-modest market cap of $22 billion. Its volatility and meager (for now) profits mean the stock isn't a great fit for everyone, particularly value investors. However, for long-term-oriented growth investors, Reddit is a name to consider in June. Then, there's Meta Platforms (NASDAQ: META). What I love about Meta's stock performance is that the company makes it look easy. Consider its latest earnings report. In the first quarter, the company posted: $42 billion in revenue $17 billion in net income $10 billion in free cash flow Bear in mind that those are figures for a single quarter. On a yearly basis, the company is on track to generate nearly $190 billion in revenue, meaning its total revenue this year could match -- or perhaps surpass -- iconic American companies like Ford Motor Company, General Motors, and Chevron. In addition to its excellent results, the company is also making moves for the future. Meta is spending heavily on artificial intelligence (AI) infrastructure, such as AI chips and data centers. Those investments are intended to upend the advertising landscape -- and put Meta at the heart of the digital advertising ecosystem. By 2026, the company wants to fully automate ads, allowing brands to cut out advertising-agency intermediaries altogether. What's more, Meta wants to automate the process using AI, allowing brands to customize their ads based on the viewer's location and tastes. In other words, Meta is aiming for another big leap forward -- one that could deliver another surge in revenue, profits, and free cash flow. For investors, now could be the time to load up on Meta shares, before the company begins to reap the rewards of its AI investments. However, given how far Meta has already climbed this year (at this writing, the stock is up 19% year to date), a dollar-cost-averaging strategy could be a savvy way to build a long-term position. Before you buy stock in Meta Platforms, consider this: The Motley Fool Stock Advisor analyst team just identified what they believe are the for investors to buy now… and Meta Platforms wasn't one of them. The 10 stocks that made the cut could produce monster returns in the coming years. Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $669,517!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $868,615!* Now, it's worth noting Stock Advisor's total average return is 792% — a market-crushing outperformance compared to 173% for the S&P 500. Don't miss out on the latest top 10 list, available when you join . See the 10 stocks » *Stock Advisor returns as of June 9, 2025 Suzanne Frey, an executive at Alphabet, is a member of The Motley Fool's board of directors. Randi Zuckerberg, a former director of market development and spokeswoman for Facebook and sister to Meta Platforms CEO Mark Zuckerberg, is a member of The Motley Fool's board of directors. Jake Lerch has positions in Alphabet, Ford Motor Company, and Reddit. The Motley Fool has positions in and recommends Alphabet, Chevron, and Meta Platforms. The Motley Fool recommends General Motors. The Motley Fool has a disclosure policy. 2 Social Media Stocks That Are Screaming Buys in June was originally published by The Motley Fool Sign in to access your portfolio
New York Times
40 minutes ago
- New York Times
This Year's Pride Festivals Are Brought to You by Small Businesses
Last month, Ryan Jones, a small-business owner in San Francisco, found himself making an unexpected plea to fellow merchants. San Francisco Pride was in trouble and needed their help. Mr. Jones's business, a bakery called Hot Cookie, had never given money to the annual festival that celebrates L.G.B.T.Q. life. But when he heard that major companies like Comcast and Anheuser-Busch were not renewing their sponsorships, leaving a funding gap of more than $1 million, he felt compelled to act. 'I asked myself what I can do to support,' Mr. Jones said of the festival, which will be held June 28-29. One answer: He and his business partner pledged to donate 5 percent of sales from the bakery's most popular cookies to this year's event. Another: He would try to get other local businesses to do something similar. Across the country, Pride events are struggling. Big corporations have been withdrawing funding for the festivals, part of a retreat from diversity initiatives that has increased under the second Trump administration. In response, local businesses are helping to make up some of the shortfall. Many see it as a way of standing up not only for L.G.B.T.Q. people, but also for what the annual celebration means for their local economies. In San Francisco, Pride is a multimillion-dollar festival drawing hundreds of thousands of visitors, dozens of musical acts and hundreds of food vendors. The event, in turn, has become a powerful economic engine, bringing in an estimated $350 million in 2015, the last time the city conducted a study of its economic impact. Now, many local businesses, including hotels, restaurants, bars and retailers, are concerned about what it would mean if the festival had to be scaled back. Hot Cookie, whose baked goods include provocatively shaped 'sex positive' cookies, saw its sales increase 30 percent during last year's Pride event, Mr. Jones said. He hopes that the support from local businesses like his, he said, will keep Pride 'viable and healthy and vibrant.' Want all of The Times? Subscribe.
Business Insider
43 minutes ago
- Business Insider
A top Wall Street analyst used ChatGPT and Gemini to assess Google risks. He came away impressed.
In a striking twist to a major legal showdown between the US government and one of the world's most powerful tech companies, Wall Street analysts aren't just turning to lawyers — they're consulting artificial intelligence. And not just any AI: Evercore ISI's top tech analyst Mark Mahaney tapped Google's own Gemini AI chatbot, along with OpenAI's ChatGPT, to assess what could happen next in the Department of Justice's big case against Google's Search business. With Judge Amit Mehta expected to rule later this summer, Mahaney published a research note that offers a rare look at how investors use generative AI as a strategic analysis tool for watching one of the most consequential antitrust cases of the 21st century. AI-powered legal analysis on Wall Street Mahaney and his team gave OpenAI's o3 and Gemini 2.5 Pro transcripts from the final day of court proceedings — more than eight hours of closing arguments — and asked the chatbots two key questions: What were the main takeaways? And what remedies will Judge Mehta most likely impose? The result? "Pretty darn impressive," Mahaney wrote. Within 17 seconds, the models generated concise, reasoned summaries and remedy predictions. The output from both AI tools aligned closely with the conclusions of legal experts consulted by Evercore, suggesting the technology may be ready for prime time as a research aid, even in complex regulatory situations, Mahaney wrote. "GenAI reasoning may become a table-stakes capability... and certainly can help achieve improved productivity goals for users, enterprises, consumers and Wall Street Internet Analysts!," he wrote. I emailed to ask Mahaney whether he's trying to put himself out of a job. Mahaney replied, "😊". AI's predictions for Google Both ChatGPT and Gemini forecast that Judge Mehta will likely impose a slate of tough behavioral remedies and stop short of ordering a huge structural breakup of Google's empire. Their projected outcomes included: A highly probable ban on default Search payments (ChatGPT was more sure of this, while Gemini thought a complete, permanent ban was unlikely. Shocker!) It's unlikely that Google will be forced to sell its Chrome browser business, though Judge Mehta might keep this in reserve if other remedies don't spark more competition. (Both chatbots aligned on this prediction pretty closely.) Likely contingent limits on general Search revenue-share payments. Possible contingent requirements on data sharing. ChatGPT's detailed reasoning suggested Judge Mehta is interested in avoiding collateral damage to the tech ecosystem while still targeting the "monopoly flywheel" Google uses to maintain dominance. Gemini's forecast echoed this logic, emphasizing Mehta's focus on balancing enforcement with market disruption risk and the avoidance of a "massive structural breakup." Why this matters for Google and Wall Street Mahaney's use of AI wasn't about replacing expert human judgment, but rather augmenting it. He and his team had already reviewed transcripts and interviewed legal experts. However, the speed and coherence with which ChatGPT and Gemini processed complex legal dialogue and arrived at similar conclusions gave Mahaney confidence that GenAI tools can assist in forecasting high-stakes regulatory events. The case, which stems from Google's multibillion-dollar payments to companies like Apple to maintain default status on browsers and smartphones, could upend how the $2 trillion internet giant competes in search and beyond. For investors, the insight that AI models can accurately mirror expert expectations in such nuanced legal territory may prove as significant as the case itself. As Judge Mehta finalizes his ruling, the courtroom might still be human, but Wall Street's analysis of it is increasingly AI-assisted. Welcome to the era of algorithmic legal foresight.
