OpenAI logo seen on screen with ChatGPT website displayed on mobile seen in this illustration in Brussels, Belgium, on December 12, 2022.
Jonathan Raa | Nurphoto | Getty Images
You may have heard the recent buzz around ChatGPT, an artificial intelligence chatbot that was released to the public at the end of November. I’ve read about people using the service to write their school essays and I was curious as to how it could help me in my daily life.
The technology was developed by OpenAI, a research company backed by Microsoft and others. ChatGPT automatically generates text based on written prompts in an advanced and creative way. It can even carry out a conversation that feels pretty close to one you’d have with a human being.
related investing news
2 days ago
ChatGPT homepage.
This got me wondering — is ChatGPT smart enough to change how we find information online? Could it someday replace Google and other search engines?
Some Google employees are certainly worried about the possibility, At a company all-hands last week, CNBC’s Jen Elias reported, employees recently asked execs if an AI-chatbot like ChatGPT was a “missed opportunity” for the company.
Alphabet CEO Sundar Pichai and Jeff Dean, the long-time head of Google’s AI division, responded by saying that the company has similar capabilities, but that the cost if something goes wrong would be greater because people have to trust the answers they get from Google.
Morgan Stanley published a report on the topic on Monday, Dec. 12 examining whether ChatGPT is a threat to Google. Brian Nowak, the bank’s lead analyst on Alphabet, wrote that language models could take market share “and disrupt Google’s position as the entry point for people on the Internet.”
However, Nowak said the firm is still confident in Google’s position because the company is continuing to improve search, and creating behavioral change is a huge hurdle — a lot of internet users use Google as a habit. Additionally, Google is “building similar natural language models such as LaMDA” which could find their way into new products.
For now, OpenAI’s creators are cautious about making any big claims. Generally speaking, the more users employ ChatGPT, the better it gets. But it still has a lot to learn. OpenAI CEO Sam Altman said in a tweet on Dec. 10 that ChatGPT is “incredibly limited” and “it’s a mistake to be relying on it for anything important right now.”
Either way, I wanted to see how well the chatbot would work as an alternative to Google’s search engine. Instead of Googling my questions throughout the day, I asked ChatGPT.
Here are some of the questions I asked and how ChatGPT responded compared with Google.
ChatGPT vs. Google
It’s easy to sign up for ChatGPT — all you need is an email address. Once you’ve registered, the webpage is very simple to navigate. There’s an area where your results will populate and a text box where you’ll type your inquiries. OpenAI says to put in a statement for the best possible result.
I recently purchased my second Fiddle Leaf Fern plant for my apartment because the first one died. Now the new one is dying after just a few days. I normally would have asked Google what to do.
Instead, I asked ChatGPT. “How can I keep my Fiddle Leaf Fern plant alive?”
The results lined up with the instructions I received from the plant company, Easy Plant, which is where I bought the new Fiddle Leaf Fern. I also liked that I didn’t have to go to various different websites like I would have if I’d Googled this question.
When I Googled the same question, the top result gave me detailed instructions in an article that included pop-up ads and a way more information than I needed, like links to buy new soil.
Winner: ChatGPT.
Next, I tried something where more shopping links would actually have been beneficial. I am still trying to find a present for all 8 nights of Hanukkah for my husband, so I decided to ask ChatGPT for some ideas.
I didn’t give it any information about my husband, besides the fact that the gifts were for Hanukkah. The chatbot then assumed that my husband is kosher and that he’s into tech and watches. The latter isn’t wrong, but it’s not the answers I was hoping for.
When I Googled this question I got access to hundreds of articles with different gift ideas and links to websites. For example I got ads to Lululemon and Bombas, which are both companies I’ve used to buy him gifts before. So in this case, Google used its personalized knowledge of me to find more targeted results from around the web.
Winner: Google
Next, I decided to ask ChatGPT a question with higher stakes.
“Is it safe to take Benadryl while pregnant?” I am currently expecting my first child, and I know that taking Benadryl is safe in pregnancy based on information I’ve received from my doctor. Still, I wanted to see what the chatbot would say.
I appreciated that ChatGPT gave me the correct answer, while also noting the importance of consulting a doctor before taking any medications during pregnancy.
When I Googled the same medical question, the results were all over the place. At quick glance, one article from TheBump.com quoted a doctor saying “Generally, it’s safe to take Benadryl in the first trimester.” While other results said similar information to what I received on ChatGPT, without the explicit warning to discuss with my healthcare provider (unless clicking into a specific link).
Winner: ChatGPT
Could it replace me?
One of the claims (or concerns) around ChatGPT — and artificial intelligence in general — is that it will replace human workers.
So I decided to see if ChatGPT could write this article for me.
The results were pretty astonishing. Here’s what the chatbot said after I told it to “write an article about whether or not ChatGPT is a good alternative to Google as a search engine.”
As a large language model trained by OpenAI, I am not capable of conducting research or browsing the internet to gather information on ChatGPT or other search engines. I am only able to provide information based on what I have been trained on, which is limited to the knowledge that was available up until my training cutoff date of 2021.
With that being said, it is worth considering the potential advantages and disadvantages of using ChatGPT as a search engine compared to other options, such as Google. One potential advantage of using ChatGPT as a search engine is that it is able to provide more personalized and conversational results.
Because ChatGPT is a language model, it is able to understand and respond to natural language queries, allowing users to ask questions and receive answers in a more intuitive and human-like way. This can make the search experience more engaging and interactive, and may be especially useful for users who have specific or complex information needs.
On the other hand, there are also potential limitations to using ChatGPT as a search engine. Because it is a large language model and not a traditional search engine, ChatGPT may not have access to the same breadth and depth of information as other search engines. This means that it may not be able to provide as comprehensive or up-to-date results, and may not be as effective for certain types of searches, such as those that require a large amount of data or real-time information.
In conclusion, whether or not ChatGPT is a good alternative to Google as a search engine will depend on the specific needs and preferences of the user. It may be a useful option for those who value a more personalized and conversational search experience, but it may not be as comprehensive or effective for certain types of searches. Ultimately, the decision to use ChatGPT or another search engine will depend on the individual user’s needs and preferences.
What impressed me most about ChatGPT’s response is that it was pretty subjective and explained its limitations.
The verdict
ChatGPT’s value really lies in its ability to explain complicated topics as if you were talking to a human, and to do simple writing tasks.
For example, I asked ChatGPT to explain concepts like the stock market and internet to me, and the responses were as if I was talking to an expert on the matter. Unlike the case on Google, I didn’t have to filter through unnecessary results.
I also asked it to write a letter to my landlord asking for an early end to my lease, and I’d be happy sending the results directly to my landlord, almost word for word.
On the other hand, Google knows more about us and tailors the results to our interests and behaviors. Google also acts as a gateway to the internet, leading users to a plethora of different websites with more information than one could possibly digest. That’s helpful if you want a range of voices, or if there’s no single simple answer to your question — like if you’re looking for gift suggestions.
Google is also great for certain types of questions where it scours the web to provide a brief but simple answer right in line. For instance, if you search “Apple stock ticker” or “Cheap flights to Aruba,” it will show you a ticker chart with up-to-the-minute price info, or a calendar with the most likely cheapest days to fly and a dialog box that connects you to multiple web sites to shop for tickets on your chosen date. ChatGPT does not scan the internet for real-time information, and has only been trained on data through 2021, so it’s totally useless on these kinds of queries.
And sometimes, ChatGPT is strangely close yet totally wrong. My editor asked it for the lyrics to “The Ballad of Dwight Fry” by Alice Cooper. It somehow knew the song was about a man having a mental breakdown, but then returned completely invented lyrics about that subject, rather than the actual lyrics. Google nailed it.
Google is also incredibly reliable, thanks to the company’s massive operations budget and years of expertise. ChatGPT is still in testing and goes down from time to time.
So I’ll definitely continue using Google for most of my search queries for now. But if I’m not happy with the results, now I have a useful alternative. And if I ever need to dash off an angry letter, ChatGPT could be a huge help there.
Silicon Valley executives and financiers publicly opened their wallets in support of President Donald Trump’s 2024 presidential run. The early returns in 2025 aren’t great, to say the least.
Following Trump’s sweeping tariff plan announced Wednesday, the Nasdaq suffered steep consecutive daily drops to finish 10% lower for the week, the index’s worst performance since the beginning of the Covid pandemic in 2020.
The tech industry’s leading CEO’s rushed to contribute to Trump’s inauguration in January and paraded to Washington, D.C., for the event. Since then, it’s been a slog.
The market can always turn around, but economists and investors aren’t optimistic, and concerns are building of a potential recession. The seven most valuable U.S. tech companies lost a combined $1.8 trillion in market cap in two days.
Apple slid 14% for the week, its biggest drop in more than five years. Tesla, led by top Trump adviser Elon Musk, plunged 9.2% and is now down more than 40% for the year. Musk contributed close to $300 million to help propel Trump back to the White House.
Nvidia, Meta and Amazon all suffered double-digit drops for the week. For Amazon, a ninth straight weekly decline marks its longest such losing streak since 2008.
With Wall Street selling out of risky assets on concern that widespread tariff hikes will punish the U.S. and global economy, the fallout has drifted down to the IPO market. Online lender Klarna and ticketing marketplace StubHub delayed their IPOs due to market turbulence, just weeks after filing with the Securities and Exchange Commission, and fintech company Chime is also reportedly delaying its listing.
CoreWeave, a provider of artificial intelligence infrastructure, last week became the first venture-backed company to raise more than $1 billion in a U.S. IPO since 2021. But the company slashed its offering, and trading has been very volatile in its opening days on the market. The stock plunged 12% on Friday, leaving it 17% above its offer price but below the bottom of its initial range.
“You couldn’t create a worse market and macro environment to go public,” said Phil Haslett, co-founder of EquityZen, a platform for investing in private companies. “Way too much turbulence. All flights are grounded until further notice.”
CoreWeave investor Mark Klein of SuRo Capital previously told CNBC that the company could be the first in an “IPO parade.” Now he’s backtracking.
“It appears that the IPO parade has been temporarily halted,” Klein told CNBC by email on Friday. “The current tariff situation has prompted these companies to pause and assess its impact.”
‘Cave rapidly’
During last year’s presidential campaign, prominent venture capitalists like Marc Andreessen backed Trump, expecting that his administration would usher in a boom and eliminate some of the hurdles to startup growth set up by the Biden administration. Andreessen and his partner, Ben Horowitz, said in July that their financial support of the Trump campaign was due to what they called a better “little tech agenda.”
A spokesperson for Andreessen Horowitz declined to comment.
Some techies who supported Trump in the campaign have taken to social media to defend their positions.
Venture capitalist Keith Rabois, a managing director at Khosla Ventures, posted on X on Thursday that “Trump Derangement Syndrome has morphed into Tariff Derangement Syndrome.” He said tariffs aren’t inflationary, are effective at reducing fentanyl imports, and he expects that “most other countries will cave and cave rapidly.”
That was before China’s Finance Ministry said on Friday that it will impose a 34% tariff on all goods imported from the U.S. starting on April 10.
At Sequoia Capital, which is the biggest investor in Klarna, outspoken Trump supporter Shaun Maguire, wrote on X, “The first long-term thinking President of my lifetime,” and said in a separate post that, “The price of stocks says almost nothing about the long term health of an economy.”
However, Allianz Chief Economic Advisor Mohamed El-Erian warned on Friday that Trump’s extensive raft of import tariffs are putting the U.S. economy at risk of recession.
“You’ve had a major repricing of growth prospects, with a recession in the U.S. going up to 50% probability, you’ve seen an increase in inflation expectations, up to 3.5%,” he told CNBC’s Silvia Amaro on the sidelines of the Ambrosetti Forum in Cernobbio, Italy.
Former Microsoft CEOs Bill Gates, left, and Steve Ballmer, center, pose for photos with CEO Satya Nadella during an event celebrating the 50th Anniversary of Microsoft on April 4, 2025 in Redmond, Washington.
Stephen Brashear | Getty Images
Meanwhile, executives at tech’s megacap companies were largely silent this week, and their public relations representatives declined to provide comments about their thinking.
Microsoft CEO Satya Nadella was in the awkward position on Friday of celebrating his company’s 50th anniversary at corporate headquarters in Redmond, Washington. Alongside Microsoft’s prior two CEOs, Bill Gates and Steve Ballmer, Nadella sat down with CNBC’s Andrew Ross Sorkin for a televised interview that was planned well before Trump’s tariff announcement.
When asked about the tariffs at the top of the interview, Nadella effectively dodged the question and avoided expressing his views about whether the new policies will hamper Microsoft’s business.
Ballmer, who was succeeded by Nadella in 2014, acknowledged to Sorkin that “disruption is very hard on people” and that, “as a Microsoft shareholder, this kind of thing is not good.” Ballmer and Gates are two of the 12 wealthiest people in the world thanks to their Microsoft fortunes.
C-suites may not be able to stay quiet for long, especially if the recent turmoil spills into next week.
Lise Buyer, who previously helped guide Google through its IPO and now works as an adviser to companies going public, said there’s no appetite for risk in the market under these conditions. But there is risk that staffers get jittery, and they’ll surely look to their leaders for some reassurance.
“Until markets settle out and we have the opportunity to access valuation levels, public company CEOs should work to calm potentially distressed employees,” Buyer said in an email. “And private company managements should refine plans to get by on dollars already in the treasury.”
— CNBC’s Hayden Field, Jordan Novet, Leslie Picker, Annie Palmer and Samantha Subin contributed to this report.
Elon Musk has been promising investors for about a decade that Tesla’s cars are on the verge of turning into robotaxis, capable of driving themselves cross-country, after one big software update.
That hasn’t happened yet.
What Tesla offers is a sophisticated, but only partially automated, driving system that’s marketed in the U.S. as its Full Self-Driving (Supervised) option, though many Tesla fans refer to it as FSD. In China, Tesla recently changed the system’s name to “intelligent assisted driving.”
Full Self-Driving, as it was previously called, relies on cameras and software to enable features like automatic navigation on highways and city streets, or automatic braking and slowing in response to traffic lights and stop signs.
Tesla owner’s manuals warn users that FSD “is a hands-on feature” that requires them to pay attention to the road at all times. “Keep your hands on the steering wheel at all times, be mindful of road conditions and surrounding traffic,” the manuals say.
But many of Tesla’s customers ignore the fine print and use the system hands-free anyway.
Tesla’s partially automated driving systems have been a source of inspiration for its stalwart fans. But they’ve also caused controversy and concern for public safety after reports of injurious and fatal collisions where Tesla’s standard Autopilot or premium FSD systems were known to be in use.
FSD does a lot of things “amazingly well,” said Guy Mangiamele, a professional test driver for automotive consulting firm AMCI Testing, during a recent long drive in Los Angeles. But he added that “the times that it trips up, you could kill somebody or you could hurt yourself.”
The pressure has never been higher on Tesla to elevate the technology and deliver on Musk’s long-delayed promises.
The Tesla CEO is the wealthiest person in the world and was the biggest financial backer of President Donald Trump’s 2024 campaign. Since Trump’s January inauguration, Musk has been leading the administration’s Department of Government Efficiency effort to drastically slash the federal workforce and government spending.
The DOGE team has been connected to more than 280,000 layoff plans for federal workers and contractors impacting 27 agencies over the last two months, according to data tracked by Challenger Gray, the executive outplacement firm.
Musk’s work with DOGE – along with his frequently incendiary political rhetoric and endorsement of Germany’s far-right, anti-immigrant party AfD – has led to a tremendous backlash against Tesla.
Protests, boycotts and even criminal acts of vandalism have targeted the electric vehicle maker in recent months and led many prospective Tesla customers to turn to other brands. Meanwhile, existing Tesla owners have been trading in their EVs at record levels, according to data from Edmunds.
Tesla’s stock dropped 36% through the first three months of 2025, representing its steepest decline since 2022 and third-biggest slide for any quarter since the EV maker went public in June 2010. Tesla also reported 336,681 vehicle deliveries in the first quarter of 2025, a 13% decline from the same period a year ago.
Product unveilings and a “robotaxi launch” expected from Tesla in Austin, Texas, this year could revitalize investors’ sentiment about the company and hopefully lift its share price, Piper Sandler analysts wrote in a note following the worse-than-expected deliveries report.
On Tesla’s last earnings call, Musk promised investors that Tesla will finally start its driverless ride-hailing service in Austin in June.
To see whether the company’s FSD technology is anywhere close to a robotaxi-ready release, CNBC spent months riding along with Tesla owners who use Full Self-Driving (Supervised) and speaking with automotive safety experts about their impressions.
Auto-tech enthusiast and Tesla owner Chris Lee, host of the YouTube channel EverydayChris, told CNBC that Tesla’s system “definitely has a ways to go, but the fact that it’s able to go from where it was three years ago to today, is insane.”
Many experts, including Telemetry Vice President of Market Research Sam Abuelsamid, remain skeptical. There’s been “no evidence” that FSD is “anywhere close to being ready to be used in an unsupervised form” by June, said Abuelsamid, whose firms specializes in automotive intelligence.
Tesla FSD will “often work really well, particularly in daytime conditions” but then “randomly, in a scenario where it did fine previously, it will fail,” said Abuelsamid, adding that those scenarios can be unpredictable and dangerous.
Watch the video to learn more about the evolution of Tesla’s Full Self-Driving (Supervised) and whether it will be robotaxi-ready this June.
Microsoft owns lots of Nvidia graphics processing units, but it isn’t using them to develop state-of-the-art artificial intelligence models.
There are good reasons for that position, Mustafa Suleyman, the company’s CEO of AI, told CNBC’s Steve Kovach in an interview on Friday. Waiting to build models that are “three or six months behind” offers several advantages, including lower costs and the ability to concentrate on specific use cases, Suleyman said.
It’s “cheaper to give a specific answer once you’ve waited for the first three or six months for the frontier to go first. We call that off-frontier,” he said. “That’s actually our strategy, is to really play a very tight second, given the capital-intensiveness of these models.”
Suleyman made a name for himself as a co-founder of DeepMind, the AI lab that Google bought in 2014, reportedly for $400 million to $650 million. Suleyman arrived at Microsoft last year alongside other employees of the startup Inflection, where he had been CEO.
More than ever, Microsoft counts on relationships with other companies to grow.
It gets AI models from San Francisco startup OpenAI and supplemental computing power from newly public CoreWeave in New Jersey. Microsoft has repeatedly enriched Bing, Windows and other products with OpenAI’s latest systems for writing human-like language and generating images.
Microsoft’s Copilot will gain “memory” to retain key facts about people who repeatedly use the assistant, Suleyman said Friday at an event in Microsoft’s Redmond, Washington, headquarters to commemorate the company’s 50th birthday. That feature came first to OpenAI’s ChatGPT, which has 500 million weekly users.
Through ChatGPT, people can access top-flight large language models such as the o1 reasoning model that takes time before spitting out an answer. OpenAI introduced that capability in September — only weeks later did Microsoft bring a similar capability called Think Deeper to Copilot.
Microsoft occasionally releases open-source small-language models that can run on PCs. They don’t require powerful server GPUs, making them different from OpenAI’s o1.
OpenAI and Microsoft have held a tight relationship shortly after the startup launched its ChatGPT chatbot in late 2022, effectively kicking off the generative AI race. In total, Microsoft has invested $13.75 billion in the startup, but more recently, fissures in the relationship between the two companies have begun to show.
Microsoft added OpenAI to its list of competitors in July 2024, and OpenAI in January announced that it was working with rival cloud provider Oracle on the $500 billion Stargate project. That came after years of OpenAI exclusively relying on Microsoft’s Azure cloud. Despite OpenAI partnering with Oracle, Microsoft in a blog post announced that the startup had “recently made a new, large Azure commitment.”
“Look, it’s absolutely mission-critical that long-term, we are able to do AI self-sufficiently at Microsoft,” Suleyman said. “At the same time, I think about these things over five and 10 year periods. You know, until 2030 at least, we are deeply partnered with OpenAI, who have [had an] enormously successful relationship for us.
Microsoft is focused on building its own AI internally, but the company is not pushing itself to build the most cutting-edge models, Suleyman said.
“We have an incredibly strong AI team, huge amounts of compute, and it’s very important to us that, you know, maybe we don’t develop the absolute frontier, the best model in the world first,” he said. “That’s very, very expensive to do and unnecessary to cause that duplication.”