In short: Carles Reina, ElevenLabs’ head of go-to-market and one of the company’s earliest employees, has issued a candid warning to candidates considering sales roles at the $11 billion voice AI company: expect long hours, constant travel, and an annual quota worth 20 times your base salary, with termination as the direct consequence of missing it. The comments, made on the 20VC podcast hosted by Harry Stebbings, have drawn attention for their directness at a moment when ElevenLabs is one of the fastest-growing AI companies in Europe. The company raised $500 million in a Series D led by Sequoia Capital in February 2026, having scaled to $330 million in annual recurring revenue in three years without relaxing the performance bar Reina describes.

Twenty times your salary, or you’re out

The structure Reina describes is simple. “If I pay you $100,000 a year, your quota is $2 million,” he said on the 20VC podcast. “That’s it. If you don’t achieve your quota, then you’re going to be out, right?” The ratio, 20 times base salary, is considerably higher than the industry standard for enterprise software sales roles, where quotas of five to eight times base salary are more common. Reina does not frame this as a threat to candidates: he presents it as the operating logic of a company that has grown to $330 million in annual recurring revenue in three years, and argues that the quota filters in the right kind of person rather than simply filtering out people who cannot perform.

The caveat Reina offers is that the bar is achievable. He said more than 80% of ElevenLabs’ sales representatives hit their quota in recent periods, a figure that, if accurate, suggests the 20x structure functions less as an attrition mechanism than as a self-selection device during hiring. The intent, he argues, is to warn candidates before they join rather than to discover the mismatch after. The long hours and travel requirements he flagged on his second 20VC appearance are the complement to the quota: ElevenLabs’ sales culture is remote-first but built around in-person customer relationships, with account executives expected to travel frequently and operate with a high degree of autonomy. Reina has said that “outbound is dead unless you do it with humans,” a position that commits the sales team to a relationship-intensive model that cannot be compressed into a nine-to-five schedule.

The compensation structure includes one notable pro-sales element: both the account executive and the customer success manager are paid if an upsell is completed within the first 12 months. This model, which treats customer success as a revenue-generating function rather than a post-sale support role, is one of the more unconventional positions Reina has taken publicly. In his second 20VC appearance, which led to the Business Insider coverage, he framed the traditional separation of customer success from revenue as “total BS,” arguing that the function’s value is indistinguishable from the value of closing new business if it is structured correctly.

Built from inside the machine

Reina’s authority on these questions comes from an unusually close vantage point. He describes himself as ElevenLabs’ first investor and fourth employee, which means he was involved in constructing the sales culture from scratch rather than inheriting one. He has scaled the revenue organisation from its earliest days to the $330 million ARR milestone, a trajectory that spans three years and multiple product pivots as ElevenLabs moved from a text-to-speech research project to an enterprise voice platform. The culture he describes is, in that sense, not a policy imposed on an existing team but the output of building a sales function inside a product-led company that had strong pull before it had a dedicated sales motion.

ElevenLabs was founded in April 2022 by Mati Staniszewski, who serves as CEO, and Piotr Dabkowski, who serves as CTO. The two met as teenagers at Copernicus High School in Warsaw, Poland; Staniszewski later studied mathematics at Imperial College London and worked as a deployment strategist at Palantir Technologies, while Dabkowski completed degrees at Oxford and Cambridge and worked as a machine learning engineer at Google. Their starting frustration was the quality of dubbed American films they watched growing up in Poland, an observation about the gap between what voice synthesis could do and what it needed to do to be useful that turned out to have significant commercial application. The company’s total funding across five rounds since 2022 stands at $781 million.

The Series D, closed on 4 February 2026 and led by Sequoia Capital, added $500 million to the company at an $11 billion valuation, more than three times its previous round valuation from January 2025. Andreessen Horowitz quadrupled its stake in the round, ICONIQ Growth tripled its position, and new investors Lightspeed Venture Partners, Evantic Capital, and BOND also participated. Andrew Reed, Partner at Sequoia, joined the company’s board. ElevenLabs closed 2025 at $330 million in annual recurring revenue, with the company targeting a doubling of that figure by the end of 2026, driven primarily by enterprise expansion.

Voice AI grows up

The product Reina’s team is selling has changed substantially since the company launched. ElevenLabs began as a text-to-speech research platform and became publicly associated with the voice cloning capabilities that made it one of the faster-growing AI consumer products of 2023. Its current enterprise offering centres on ElevenAgents, a platform for deploying voice and conversational AI agents that the company positions against customer support, sales automation, internal enablement, and workflow use cases. The platform supports more than 10,000 voices across 70 languages, with enterprise customers including Deutsche Telekom, Square, the Ukrainian Government, and Revolut among those that have deployed it for production workloads.

The infrastructure supporting those deployments has been reinforced by a series of major partnerships. In February 2026, ElevenLabs and Google Cloud expanded their strategic partnership to run on NVIDIA Blackwell GPUs, giving ElevenLabs access to the compute architecture it needs to serve high-volume enterprise inference at the latency standards voice applications require. In March 2026, ElevenLabs and IBM announced an integration between ElevenLabs’ text-to-speech and speech-to-text capabilities and IBM watsonx Orchestrate, IBM’s enterprise agentic AI platform, targeting banks, insurance companies, healthcare providers, and utilities that need voice agents capable of operating across languages and regulatory environments simultaneously.

The revenue split at the end of 2025 was approximately 50% enterprise and 50% consumer. The company expects that ratio to shift to 60% enterprise and 40% consumer by the end of 2026, and to continue moving in the same direction in 2027. This trajectory explains the specific shape of the sales culture Reina describes: enterprise software with a rapidly expanding product surface, in a market where competitors are also investing heavily, requires a sales organisation that can build and sustain relationships at speed and volume. The quota that results is high by conventional standards. By ElevenLabs’ own account, it is calibrated to what the market and the product make achievable.

What the model reveals

The directness of Reina’s candidate warnings sits within a broader pattern of AI-era companies reconfiguring what they expect from people, and where they invest the headcount they do hire. Meta cut hundreds of jobs across Reality Labs, recruiting, and sales in March 2026, redirecting the capital toward a $135 billion AI investment programme that Zuckerberg described as the defining bet of the company’s current phase. The pattern, which has played out at Klarna, Microsoft, and others, is consistent: AI spending rises, headcount in traditional functions falls, and the roles that survive carry higher expectations and, in some cases, higher compensation.

TNW reported in August 2025 that the next generation of AI unicorns might not hire anyone at all, analysing a structural shift in which the average seed-stage startup was being built with fewer than four people compared to more than six in 2022. ElevenLabs is not a zero-workforce company, and Reina’s comments are not a defence of that model: the whole point of his sales culture is that outbound is a human discipline that requires more relationship investment, not less. But the underlying dynamic is the same. Fewer roles, each carrying more responsibility, selected more precisely, paid more directly for measurable outcomes.

The voice AI category Reina is selling has also attracted its own wave of smaller investment activity. In March 2026, Ringtime raised €1.8 million to deploy AI voice agents in blue-collar recruitment, automating candidate outreach, screening, and matching across 22 languages for logistics, retail, food processing, and construction employers. The use case is different from ElevenLabs’ enterprise positioning, but the underlying technology and the commercial logic of replacing manual communication workflows with AI agents are the same. The market Reina is working is expanding from both ends: from the enterprise side, through large platform integrations, and from the startup side, through an increasing number of vertical applications built on voice AI infrastructure.

Glassdoor reviews from ElevenLabs employees describe “abnormally high” quotas and long hours, consistent with Reina’s public characterisation. Some reviewers note that leadership views membership of the ElevenLabs team as a reward in itself, a perspective that has generated frustration among employees who feel their performance above quota is not separately recognised. Reina’s approach to candidate transparency is, in that sense, a response to a known tension: the culture is demanding, it produces results, and it is better for both parties if candidates know that before they start rather than after.

Whether that level of directness becomes more common in AI-era hiring is partly a function of whether the results it produces continue to justify the model. ElevenLabs reached its current position as part of a broader acceleration in European AI ambition. TNW observed that five European startups joined the unicorn club in the opening weeks of 2026, a moment it described as evidence of a maturing European tech identity. ElevenLabs, with Polish founders and a global product, fits that pattern. At $330 million in ARR and $11 billion in valuation, the performance standards it demands of its sales team are the internal expression of the same ambition visible in the funding numbers.

After launching the pretty-decent vivo V70, which we reviewed and loved, the Chinese smartphone maker is back at it again. The company has just announced the sale of its latest V-series smartphone, the vivo V70 FE, in India. The new device focuses on high-resolution imaging, premium design, and long battery life, targeting users who want a feature-packed mid-range phone. Here’s everything you need to know about it.

200MP For the Win

The headline feature of the vivo V70 FE is its 200MP OIS main camera, designed to capture highly detailed images with improved stability. The phone also supports AI-powered features like 30x SuperZoom, multifocal portraits, and 4K video recording with stabilization. On the front, users get a 50MP selfie camera with eye autofocus, making it suitable for group shots and video calls.

vivo is also bundling a full AI photography suite, including tools like object removal, scene enhancement, and automatic color correction. These features aim to simplify editing and help users achieve polished images with minimal effort.

New Design & Processor

One of the more interesting additions is vivo’s Darkness Glow Technology, available on the Northern Lights Purple variant. As the name suggests, the back panel can glow in the dark after exposure to UV light, adding a bit of flair to the design.

On the front, there’s a 120Hz OLED display, while performance is handled by the MediaTek Dimensity 7360 Turbo chipset, combined with LPDDR5 RAM and UFS 3.1 storage. The smartphone runs on OriginOS 6, offering AI tools, productivity enhancements, and customization options. vivo is also promising 4 years of OS updates and 6 years of security updates, which is notable for this segment.

The vivo V70 FE is available in three variants:

• 8GB + 128GB: ₹37,999
• 8GB + 256GB: ₹40,999
• 12GB + 256GB: ₹44,999

Google News has begun showing Polymarket bets and odds alongside actual stories, . These look to appear as large blocks that include links to numerous ways for people to lose their money.

Bets tend to appear in the “For you” section of Google News, which is supposed to be tailored to a person’s particular interests. Futurism notes that the platform actually placed a Polymarket bet as the top news result when inquiring about the price of Bitcoin.

The publication saw links to the prediction market all over Google News, including in searches. It popped up in queries regarding the Strait of Hormuz, which presents a link that lets people bet on the number of ships that the critical passageway. The report even indicates that users were able to set the gambling platform as a source, which directs readers to an aggregate page of other Polymarket links.

There’s a caveat here. I wasn’t personally able to confirm most of these results. This could indicate that Google has quietly made some changes behind the scenes following Futurism’s initial report.

Complaints on indicate that Google started doing this at the tail-end of March. However, one user noted all the way back in January that Polymarket results had started showing up in the news section of a traditional Google search. I was able to replicate that one.

Engadget has reached out to Google to see just what’s going on here and if it plans to continue displaying Polymarket bets alongside actual news stories. The company did with both Polymarket and Kalshi back in November. This deal indicated the two gambling platforms would feed prediction data into Google’s finance platform, but didn’t say anything about News.

It’s pretty easy to see why Polymarket would be attractive to Google’s algorithms. The platform generates huge numbers on pages that are constantly updated. This could make these algorithms think the links are leading to valuable news stories and not, you know, a place to .

Prediction markets like Polymarket give users the ability to place bets on real world outcomes, which includes wars and other gruesome things. This has led to , which include an incident in which an unknown Polymarket user made more than $400,000 after “predicting” the capture of Venezuela’s president Nicolás Maduro invaded the country and abducted him.

Polymarket has hosted bets on the in current global conflicts, which is pretty dang chilling when you consider the possibility of government employees tipping the scales in their favor. President Trump did, after all, recently threaten to end an entire civilization.

The robot uses Bluetooth to communicate with your phone and uses 2.4-GHz Wi-Fi to connect directly to your home network for over-the-air updates (but not real-time management). Onboarding requires connecting to a temporary network on the device and bridging it to your home network, a quick process that gave me no trouble during setup. Firmware updates will likely be available, but note you’ll need to check the Device Information menu for them. Mammotion didn’t proactively push or suggest any updates during my testing, and these over-the-air updates often required multiple attempts to install successfully.

The app is decidedly limited, allowing you to select from the standard four operating modes and make a few small additional adjustments, including configuring the maximum speed of the robot and opting into a couple of beta features. These include a “Turbo Cleaning” mode that increases the power of the suction at the expense of battery life, and an option to improve the way the unit cleans steps and platforms. (Why this feature isn’t always on is a mystery.)

Leaves Left Behind

Photograph: Chris Null

Throughout my test runs, I saw fairly consistent performance results. The Spino E1 offers acceptable cleaning capabilities, though it’s far from perfect. With synthetic leaves, the unit averaged a cleanup rate of only about 80 percent, leaving behind a significant amount of material uncollected. This material wasn’t just isolated to corners and steps; it was scattered all around the pool. I also noticed the unit cleaned steps and platforms well, but it struggled heavily with obstacles, particularly at the waterline.

I saw similar results with organic debris, and the E1 struggled particularly with smaller particulate matter like dirt. On one run, I could best describe the pool as looking a bit like some of the debris had been smeared around on the pool floor instead of sucked up into the debris basket. All of this is unusual and suggests not that the unit has coverage issues, but rather that the device simply may be underpowered.

ScreenshotSpino app via Chris Null

Good news: The Turbo Cleaning mode available through the app was visibly more effective and bizarrely did not impact battery life at all. The bad news is that this option, still in beta, has to be manually activated in the app before each run of the robot. Hopefully, Mammotion will simply make Turbo Mode the default soon.

When finished, the Spino E1 climbs the pool wall and waits by the waterline for collection—at least momentarily. The problem is that the robot doesn’t push a notification via the Mammotion app to alert you when a cleaning cycle is done, and since the robot has to run its propulsion jets to float, you only have a limited time (about 10 minutes) before the battery dies and the robot sinks. A hook is included in the box to aid with pole-based retrieval in this event.

Morgan Dreiss, a copy editor in Orlando, has severe ADHD that they say requires them to always be “doing at least three things at once.” The result? A daily average screen time of 18 hours and 55 minutes.

“I’m reading a book or playing a game pretty much from waking to sleeping,” Dreiss tells WIRED. What they read comes from the library app Libby, so the books count toward overall screen engagement. Dreiss currently keeps their phone’s autolock feature disabled so they can continuously run a mobile game that pays out $35 for every 110 hours logged. (They’ve earned about $16 so far.)

For years, studies have brought forth worrying data about the potential negative effects of excessive screen time on both physical and cognitive health. Concerns over the neural development and mental health of young people glued to their phones have led to major legislative and courtroom battles; recently a jury found Meta and YouTube liable for designing their platforms with addictive features.

While the question of whether one can be clinically “addicted” to something like social media remains a subject of fierce contention, there seems to be a broad consensus in this decade that people would be better off scrolling less. On the more extreme end, there are virtual communities that share strategies for ditching smartphones and digital detox retreats where no notifications can find you.

Yet there are those, like Dreiss, who resist the emerging common wisdom about reducing screen time. You might call them “screenmaxxers.” It’s not that they necessarily have some totalizing concept of their habits; journalist Taylor Lorenz is likely in the minority of screenmaxxers eager to put the screen directly inside her brain, as she recently confessed to WIRED. It’s just that, for various reasons, they’re on their devices pretty much all the time, and they don’t see that as a problem whatsoever.

Part of the equation, of course, is work. Corina Diaz, 45, who lives in a remote forested region of Ontario, Canada, works in video game marketing and does influencer management for a game publisher. “So, a lot of screen time,” she says.

Diaz met her husband online in 2005 and had a child three years ago—her screen time increased when she was awake at strange hours because of her newborn, she says.

But Diaz has sought friendships online since the 1990s, when that meant availing herself of tools like Internet Relay Chat and bulletin board systems. “I’ve always felt screens, phone or otherwise, connected me to things I care about,” she says. “In particular, niche social groups that don’t have great mainstream visibility.” Now that she lives two and a half hours outside Toronto, the closest major city, her screen is “a bit of a connection lifeline,” she says.

Daniel Rios is in a similar position. A computer programmer, he lives in the South American country where he grew up after having lived abroad for years. Most of his friends moved away and didn’t return.

As a result, Rios keeps in touch with people over Discord, his primary social outlet. Not living in a city, he doesn’t go out all that much, and screens fill his days—though he says it’s “hard to quantify” exactly how many hours it all adds up to. “When I’m not working at the [desktop] computer, I’m playing at the computer or watching TV,” he says. “If I’m not at the computer, I’m looking at my phone. If I’m not doing any of the above, and I’m out of the house, I’m still probably listening to something on my phone.”

For decades, the ERP “playbook” was a familiar exercise in endurance: organizations would mobilize an army of consultants, brace for years of disruption, and spend millions on a monolithic system designed to last a decade.

Success was binary, the system either switched on, or it didn’t, while adoption and agility remained secondary concerns. But as we enter the AI era, this traditional model has reached a breaking point.