Google Chrome Fixes 1,072 Security Bugs in June Using AI—More Than Past Two Years Combined

Google says it fixed more Chrome bugs in June than over the past two years, thanks to AI

With help from its internal AI tools, Google says it has patched more security flaws in its Chrome browser in the last month than in the past two years combined. The tech giant announced on Thursday that it has fixed a whopping 1,072 security bugs in the last two versions of Chrome, both released in June. That is more than the number of bugs patched in the previous 23 versions released over the last two years, which totalled 1,036 fixes. Ever since the advent of LLMs, cybersecurity experts have warned that AI-powered systems would find an increasingly and exponentially enormous amount of bugs, forcing defenders to also use AI to get ahead of malicious hackers. That prediction is starting to become true, and it's backed by real data. A chart published by Google, which the company revealed as part of a white paper on the company's efforts to use AI to find flaws and patch them faster, shows the exponential increase. For context, Chrome's 126 was released in June 2024, while the latest two Chrome releases, Chrome 149 and 150, were released last month. Google calls each version a "milestone." Doug Turner, Chrome's director of engineering, told TechCrunch in a statement that LLMs have "fundamentally shifted the economics of cybersecurity, transforming vulnerability discovery into an automated, industrial-scale operation." "By applying models like Gemini, we are preemptively fixing vulnerabilities, outpacing our adversaries and making Chrome safer with every update," said Turner. Google is not the only company seeing this trend. Earlier this month, Microsoft announced that it had patched a record 570 security flaws across its product lines as part of its monthly round of scheduled patches -- colloquially known as "Patch Tuesday." Microsoft cited its own use of AI to explain the sudden jump in bug fixes. Apple, meanwhile, does not appear to be registering the same exponential increase. According to an independent count of bugs fixed by in its products, Apple has patched 482 bugs in 2026, which is roughly on pace to equal or surpass the number of fixed buts from last year, and also roughly equal from the number of bugs that Apple patched in 2015. TechCrunch reached out to Apple for comment, but did not hear back.

Chrome Needs Twice-a-Week Patching Thanks to AI Bug Hunting

Google's Chrome browser has always been focused on pushing security updates. A decade ago it was controversial that the browser, the first to add automatic updates, distributed patches every six weeks. Now it's the norm for critical, widely used software to get security fixes every few weeks, but as AI vulnerability hunting produces a torrent of bugs in any and all software, the quantity and frequency of patches is spiking -- and the race to deliver them is on. In a report published Thursday, the Chrome security team says the browser's two major version releases in June included fixes for 1,072 security bugs -- more patches than the team shipped in the prior 23 big releases combined. And though many of these bugs come from researcher submissions, the spike has largely been driven by the Chrome security team's rapidly evolving internal process for using AI tools in vulnerability discovery, triage, and patch development. "In chrome we've been using machine learning -- using AI before it was called AI -- to help find vulnerabilities in particular and automate security fuzz testing work since at least 2012. It's been a huge part of how we find vulnerabilities and empower developers," Parisa Tabriz, Chrome's vice president and general manager, tells WIRED. "But I do think this year is very different. It really feels like an inflection point both for offense and defense." Chrome is already moving toward a new normal of pushing out a major release every two weeks with additional weekly security updates. But the frenzy of vulnerability discoveries has been so intense, and the team has had so much success incorporating new AI models and capabilities into the workflow of finding and fixing new bugs, that for now the group is piloting a cadence of releasing security fixes twice a week. "The way we ended up here is we had so many vulnerability fixes, so being able to provide two [updates per week] during this time, it made the most sense to us," says Doug Turner, Chrome's director of engineering. "Will that last forever? Who knows." Turner, like other security researchers, says he sees evidence that the AI vulnerability boom time (or apocalypse, depending on how you look at it) may not last forever. For mature, stable products like Chrome, at least, there seems to be a drop off at a certain point in the number of new vulnerabilities that will be discovered overtime once the bulk of bugs that can be found with AI have been fixed. This is partly because AI models can be trained to have an encyclopedic understanding of how software projects have evolved over time. "We're training our model such that it knows about every security vulnerability that we have seen in the past," Turner says. "So every CVE, every bug the model knows about. And the second really cool thing is every line of code in Chromium's history, it knows the reason why that line was changed." All of this context allows AI tools to home in on possible weaknesses across Chrome's massive and complex codebase, including for features (say, printing) that are no longer under active development and may not attract as many human eyes anymore. Tabriz and Turner emphasize, too, that in addition to whack-a-mole patching, the Chrome security team is also extremely focused on the idea of making structural changes to how the browser is designed (such as rewriting portions of C++ code in the more secure, "memory safe" programming language Rust) so the software is no longer affected by whole categories of common bugs. "There's this near-term spike, but I do think there's going to be a new equilibrium," Tabriz says. "Across the industry I think it's really important that people who are building and thinking about software security are incorporating AI into their development workflows. My highest hope is that everything gets more secure. But I don't assume everything is going to just get better. I don't think it's going to come for free."

AI is finding bugs faster than humans can fix them: How enterprise security teams must adapt

Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways * AI-discovered security problems are growing like a tidal wave. * Whether using a PC or running a data center, everyone will be affected. * We are not ready for what's coming. The good news is that AI is finding security holes faster than ever. The bad news is that AI is finding security holes faster than ever. It's both: While it's great that we're finding all those bugs, trying to fix them all is a monster of a job. Sure, if you're Google, you can fix more bugs in Chrome in June 2026 than you had in the last two years, but most companies aren't Google. They don't have anything like the resources to fix that many security holes. Indeed, even Apple -- yes, Apple -- has been overwhelmed by AI bug reports. As a result, in June, Apple told security researchers it "restricted the number of potentially dangerous software bugs researchers can submit to its internal security team. If you find a truly horrendous vulnerability, but you're over the limit, too bad. Try again next month. Also: How Google used AI agents to find and fix 1,072 Chrome security bugs - in 60 days Hence, the problem. AI-assisted vulnerability discovery is accelerating the pace of bug reports, but the real story is the growing mismatch between what machines can surface and what humans can realistically triage. Thus, we've ended up with an ever-growing burden on developers, security teams, and companies trying to separate exploitable issues from machine-generated noise. It's not just developers, however, who are having trouble. System administrators, CISOs, and end users are all caught trying to keep up with one patch after another. The AI security tidal wave The old security workflow assumed high-value bugs would arrive in relatively manageable numbers. You'd look at the Common Vulnerabilities and Exposures (CVE) score and immediately patch the really high ones. You'd also hope that a zero-day vulnerability wouldn't come along and ruin your day. That was then. This is now. Also: AI is both a cyber weapon and a massive target, CrowdStrike warns AI has broken that assumption by making it cheap to find large volumes of flaws. While open-source programs have gotten most of the headlines, this is, in no way, shape, or form, an open-source problem. For example, Microsoft's July 2026 Patch Tuesday shipped 570 patches, including three zero-days. This set a record. I'm sure it will be broken before the end of the year. Why? Not because Windows is less secure than it's ever been. It's because, as Microsoft explained in May, "AI helps defenders discover more issues, customers will see a higher volume of security updates included in each security release." These numbers will only increase. As Dan Lorenc, co-founder and CEO of security company Chainguard, recently said in a webinar, AI is "now finding vulnerabilities in the software they write and the software they use at a pace that is far exceeding defenders' ability to patch and get updates and fix the vulnerabilities." He noted that it was always easier to find vulnerabilities than to fix them, but AI has "poured another giant jug of gasoline onto the fire before inventing a better fire extinguisher." Also: How to keep your AI conversations as private as possible What makes this especially difficult to manage is that not all of these issues are equal. A small number are active, urgent, and exploit-driven, while many others are part of the background hum of fixes. Security teams are being forced to triage issues where the volume itself is a risk multiplier. For instance, I used to recommend that Windows users hold off on patching their PCs because so many patches ended up going awry, such as the January 2026 Patch Tuesday update. Now, with zero-day attacks coming fast and furious, you may not have any choice but to grit your teeth, update, and hope the patches themselves don't screw you over. For better or worse, as Greg Kroah-Hartman, maintainer of the Linux stable kernel, put it, "If you're not using the latest stable/long-term kernel system, your system is insecure." These days, the same is true for Windows, MacOS, and, really, pretty much all programs. Not just a Linux problem Some of you may think this is a problem mostly for Linux and open-source software. It's not. The Linux kernel is only the most visible case because its maintainers are public and opinionated, and they're already stretched thin. How bad is it? In July, there were 432 CVEs reported in two days in the Linux kernel. The same thing is showing up across proprietary software; companies are just not telling us about it. You can tell by how much larger their patches and systems have grown. Sure, some of it is Microsoft adding more AI to Windows, but I strongly suspect a lot of it is fixes for potential AI security holes. Also: Open weights vs. closed: An AI civil war's afoot, and the stakes are existential For example, Adobe's Acrobat Chrome extension security foul-up, HermeticReader, exposes sensitive WhatsApp Web data with only a visit to a malicious page. These webpages look just like any other kind of page, but when you visit one, the trap springs and opens a sleeping program inside the extension. It then reaches into your WhatsApp and grabs your chat list, contact names, messages, the profile name, and the text of whatever conversation is open -- you know, pretty much everything. The attack was created by AI linking together three different vulnerabilities that enabled "an unauthenticated, single-visit, zero-click write into the extension's own storage from any web page." Adding insult to injury, this attack was then automated by a crook using the DeepSeek LLM via the Hermes Agent framework. Also: Microsoft goes all in on new AI-powered Windows security strategy The one good thing about this potential disaster is that Adobe quickly released an updated version of the extension, which patched the security hole before too much damage was done. We won't always be so lucky. As Linux Foundation CEO Jim Zemlin said at the North America Open Source Summit, "Today the mean time to exploit has disintegrated from 63 days to -7 days. Exploitation is happening before a patch is even released." Is that great or what? The triage tax At the same time, another cost of AI-generated bug reports is not just false positives; it's the time required to prove they are false. Maintainers still have to read them, reproduce them, and decide whether they're duplicates, hallucinations, or genuine vulnerabilities buried inside bad framing. That is an expert attention tax, and it hits hardest where teams are small. Also: AI is getting scary good at finding hidden software bugs - even in decades-old code This issue doesn't only hit maintainers. It's a matter of concern for you sitting at your home PC and for Fortune 500 CISOs trying to decide whether to patch or not to patch their systems; that is the question. Do you want to be patching and rebooting your system every other day? Can you afford to? Can you afford not to? The day when you could rely on a solid, stable program running for weeks or even years is over. The patching pace has sped up, and it won't be slowing down anytime soon. Severity scores help less when everyone is drowning in a sea of "high" and "critical" findings. How companies are feeling it Companies, just like Odysseus, are caught between Scylla and Charybdis. They want faster detection, but they also need less noise. AI can help surface real defects earlier, yet the same tooling can generate reports that look authoritative enough to demand review while adding no value. That creates a feedback loop in which security teams spend more time validating reports than fixing the underlying problems. What's a business to do? Now you may ask yourself, "Why can't AI fix those bugs?" The answer is easy. It can't. It's far easier to find security holes than to fix them. An academic study of 20,000+ issues fixed by AI found that LLMs introduce "nearly 9x more new vulnerabilities than developers, with many of these exhibiting unique patterns not found in developers' code." In short, the cure can be worse than the disease. Even the best patching AI-driven programs, such as PatchitPy for Python code, still have only an 80% successful repair rate. That's good, but it's far from perfect. Adding insult to injury, some developers have found that after "multiple rounds of AI fixes, the number of critical vulns can go up, not down." Why is it so hard? One big reason, according to Ben Hawkes, a computer security expert and former manager of Google's Project Zero, is that "it's hard to capture the fact that a bug can be super serious in one type of deployment, somewhat important in another, or no big deal at all -- and that the bug can be all of this at the same time. Vulnerability remediation is hard." He's got that right. So what can you do about it? Google has some suggestions. These boil down to: * Narrow scope: Ask the model for minimal, targeted changes (e.g., "mirror this upstream fix" or "update this dependency to version X") instead of "eliminate the vulnerability." * Separate remediation and verification: Treat verification as its own stage. That means re-running scanners, fuzzers, and targeted tests for the CVE after applying the patch, rather than relying on "compiles and tests pass" as proof of security. * Human review for complex changes: Use AI as a draft generator or search assistant, but keep human engineers in charge of design-level changes, multi-file refactors, and anything touching authentication, authorization, or data handling. There is also a risk to a company's reputation. If a company appears to ignore vulnerability reports, it looks negligent. If it treats every machine-generated report as urgent, it burns staff time and delays real fixes. The practical outcome is a growing need for stronger security teams, stricter proof requirements, and better use of exploitability signals rather than raw report counts. Are you ready for this? I doubt it. Also: 'I'm not a programmer' anymore: Linus Torvalds on the only two tools he uses now Companies say they're looking for IT security people, but they're not hiring as many people as they did in 2022. Even more disturbing, "ISC2 now ranks budget constraints as the #1 cause of staffing shortages, displacing 'lack of qualified talent' for the first time (ISC2 2024). This shift matters: it means the gap is increasingly a leadership and investment problem, not a skills supply problem. ISACA data corroborates this, showing teams remain understaffed even when qualified candidates exist in the market." This will not end well. What changes next The next phase of this problem is likely to be procedural rather than technical. Organizations will need more aggressive triage rules, clearer disclosure policies, and stronger automation for deduplicating and scoring reports before humans see them. Otherwise, AI will keep increasing both the number of discoveries and the amount of junk wrapped around them. Also: Linux is getting a security wake-up call - why it was inevitable, and I'm not worried The key lesson from Linux, Microsoft, and Adobe is that this is now an ecosystem-wide operational issue. AI is not merely finding more bugs; it is changing the economics of vulnerability management, and that shift is hitting every layer of software supply and support. We must treat these matters seriously, or in the next few months we're going to see IT security problems that will make past major incidents, from the Morris worm to the Marks and Spencer £300 million ransomware attack, look like tempests in a teacup.

Google Tests Doubling Chrome's Security Patch Cadence to Outpace Hackers

Since 2023, Google has released weekly security updates for the Chrome browser, but the company is now testing a twice-per-week cadence to stay ahead of "AI-powered attacks." A Google white paper released Thursday details its efforts to use large language models to accelerate the discovery of software vulnerabilities. The report includes a graph that shows the number of security bugs fixed in Chrome's stable releases has skyrocketed in recent months. "At this point, we have LLMs generating candidate fixes for most vulnerabilities," the company wrote. "In the last two milestones, Chrome 149 and 150, we have fixed 1,072 security bugs, surpassing the total number of security bugs fixed across the prior 23 milestones combined," dating back to June 2024. The problem is that hackers are now using AI models to uncover software vulnerabilities and exploit them quickly. When Google publicly discloses and patches a flaw, details of exploiting the bug are often vague. Still, the very act of publicizing the fix can provide enough hints for an attacker to try to reverse-engineer the issue and "exploit the bug before the fix reaches users' machines," the company noted. "Since fixes committed to the main 'tree' typically take weeks to reach the Chrome Stable channel (what the vast majority of our users run), minimizing this patch gap is a critical part of our strategy," Google added. As a result, the company says it needs to increase the security fix output. "In the face of fast-moving, AI-powered attacks, our delivery cadence must accelerate even further. To meet this moment, we are piloting a shift to two security releases per week," the company said. This comes after the company announced in March that Chrome would "move to a two-week release cycle, from the current four-week cycle," for stable releases, in an effort to ensure the latest browser enhancements reach users. The two-week cycle for stable releases kicks off in September with Chrome 153. Although increasing the security release cadence promises to protect users, it also means users need to restart their Chrome browser for the fixes to take full effect. "A restart can be disruptive, requires scheduling in between tasks, and is rarely the top priority at any given moment. To eliminate this friction, we are pioneering ways to shift the burden away from the user," Google says. One method, called "dynamic patching," promises to replace background processes with updated binaries "on the fly," eliminating the need to restart Chrome. Another effort involves finding "opportune moments to restart automatically," and then offering a session restore to bring back all the tabs. "For example, in Chrome 150, we rolled out a change to take advantage of the unique application state on macOS, where applications typically continue running in the background even after all windows are closed. Now, if Chrome detects a pending update while in this windowless state, it automatically restarts," the company says. Google didn't say when dynamic patching will arrive. For now, Google is saying "stay tuned" as it develops the feature. But it noted: "Our long-term vision is a browser that is always up-to-date - continuously and dynamically patched, and automatically restarted during opportune periods of minimal disruption. While we're working on this, you can keep your Chrome up to date by clicking on the update message in the top right corner."

Google says AI helped Chrome fix 1,072 security bugs in two releases

Google says artificial intelligence is dramatically increasing the number of security vulnerabilities it can find and fix in Chrome, with more than 1,000 security bugs patched across the browser's two most recent releases as it expands its use of AI. According to Google, Chrome 149 and Chrome 150 fixed 1,072 security bugs, surpassing the total number fixed across the previous 23 Chrome milestones combined. The company says it now uses large language models throughout the vulnerability management process, including discovering flaws, reproducing reports, determining severity, assigning bugs to developers, generating candidate patches, and creating tests. Google began using LLMs to improve security fuzzing in 2023 before working with Project Zero on Naptime, a system that provided AI models with specialized vulnerability research tools. The company later collaborated with Google DeepMind and Project Zero on Big Sleep, an AI-powered vulnerability discovery agent that found flaws in Chrome's V8 JavaScript engine and graphics components. In early 2026, Google created a Gemini-powered agent harness to search the broader Chrome codebase for vulnerabilities while reducing false positives. One vulnerability discovered by the system was a Chrome sandbox escape that had remained in the codebase for more than 13 years. If exploited, the flaw would have allowed a compromised renderer to escape the sandbox and trick the browser into reading local files. Google is also encouraging its developers to add SECURITY.md files describing trust boundaries and threat models, helping its AI systems better identify operations with security implications. The company says its multi-agent AI workflows help rather than replace existing security testing, including fuzzing, which remains effective at discovering complex vulnerabilities. Google has also seen a sharp increase in reports submitted through the Chrome Vulnerability Reward Program, and by March 2026, the company had received more security bug reports than during all of 2025. This prompted Google to modify its program to prioritize reports that add to what its already finding and processing through its automated tooling. The company is also automating vulnerability triage, including filtering spam and duplicates, reproducing proof-of-concept exploits, assigning severity ratings, and routing reports to the appropriate developers. Google estimates that this automated process saves hundreds of hours of developer time each month. After a vulnerability is confirmed, fixing agents generate multiple potential patches, while another agent evaluates the proposed fixes and produces additional information for developers to review. In May, these systems reportedly prevented more than 20 vulnerabilities from reaching production, including one issue classified as critical. However, Google says finding and fixing vulnerabilities more quickly also requires accelerating how patches are delivered to users. Once a security fix is committed to Chrome's public source code, attackers can inspect the change and attempt to reverse-engineer the vulnerability before the update reaches users. Google is also transitioning Chrome to a two-week major release cycle with weekly security updates and is piloting two security releases per week to reduce this patch gap. To reduce disruptions, the company is developing "dynamic patching," which would allow Chrome to apply updates without restarting the browser. Starting with Chrome 150 on macOS, the browser can automatically restart to apply a pending update when it is running in the background without any open windows. Google says its long-term goal is to keep Chrome continuously updated through dynamic patching, automatic restarts during periods of inactivity, and improved session restoration.

How Google used AI agents to find and fix 1,072 Chrome security bugs - in 60 days

Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways * AI found a decade-old Chrome flaw humans repeatedly missed. * Google said its AI workflow saves weeks of developer time. * Chrome may need twice-weekly patches to keep billions safe. Chrome and its open-source project, Chromium, are, by scale, among the most complex open-source projects on the planet. With some 73% of the global browser market share, there are about 3.5 billion active Chrome users. To put that in perspective, 3.5 billion is more than 10 times the entire population (adults and children) of the United States. I couldn't find a good reference for the overall adult population, so I used math. Based on data for the overall population of the world and the number of children on the planet, there are a little under 6 billion adults on Earth. The math shows us that Chrome is the primary way more than half of us earthlings access the internet. Also: Claude AI shared chats indexed by Google - see if your conversations were exposed The stakes, therefore, are incredibly high for Chrome's developers. Just letting one security flaw loose into the wild immediately puts half the adult humans currently alive at risk. Google clearly takes this responsibility quite seriously. Last week, the Chrome security team released a blog post detailing how it is using AI to "improve vulnerability discovery, triage, and patching." Also: This powerful Gemini setting made my AI results way more personal and accurate The scope, the challenge, how AI is helping, and how AI is also exposing overwhelming numbers of new vulnerabilities make for quite the story, one worthy of deconstruction. The whole story in one chart Google called its releases "milestones," which occur about once a month. The chart below begins with Milestone 128, which dropped on Aug. 20, 2024. For each milestone up to M145, Google fixed roughly 50 bugs. Then M146 jumped to about 80 bugs. M147 fixed about 130 bugs. M148 fixed about 350 bugs. Month by month, the number of bugs found and fixed doubled. Then, for M149 and M150, Google fixed 1,072 bugs, "surpassing the total number of security bugs fixed across the prior 23 milestones combined." There are ... implications The logistics of this are mind-blowing. With Google issuing major new releases on a monthly basis, the potential for causing disruption worldwide is fairly high. If, instead of fixing a bug, Google were to introduce a serious bug that made it past deployment before discovery, it could ruin the day for half of all living adult humans. For each of the 40 or 50 bugs dealt with back in M128, Google had to validate the bug, fix the bug, QA the fix to make sure it didn't conflict with the billions of web pages and hundreds of thousands of Chrome extensions, release a fix, and then encourage users to update their browsers. Also: Google Earth added Nano Banana, and I immediately reimagined Philly with zombies and evil clowns That's a lot to accomplish in roughly a month, even with a developer army that a company like Google can task with the work. To be sure, Google has been using AI tools to manage these earlier releases. Back in 2023, Google used AIs to increase security fuzzing coverage (basically testing with lots of unexpected, random inputs). By 2024, about the time of M128, Google started to add specialized AI tools to do vulnerability analysis. In 2025, the company said, "We collaborated with DeepMind and Project Zero on Big Sleep, an AI vulnerability discovery agent that successfully found bugs in the V8 JavaScript engine and graphics stack." Then, in 2026, Google upped its game with an agentic harness (a structure for interacting with LLMs) based on Gemini that was designed to find vulnerabilities across the entire Chrome codebase. This is not a linear process. It's not just a matter of looking at code and realizing that inputs weren't properly sanitized. Instead, it's much more like a game of chess, except the AI is predicting moves thousands of moves ahead. It's not just looking at the code. It's gaming out scenarios. Billions of scenarios. Doing this doesn't necessarily find flaws in the code. The code could be rock-solid. Instead, it's finding vulnerabilities, which reflect patterns of interactions that could cause a security failure. One example of this is a vulnerability called a sandbox escape that has existed in Chrome since 2013. This is a bug that, if exploited, would trick the browser into reading local files. That flaw lived in the Chrome code, passing test suite after test suite, for more than a decade. Gemini found it in early 2026. Also: How to keep your AI conversations as private as possible But here's the thing. While 40 or 50 vulnerabilities in a month are moderately manageable for a Google-sized team, 1,072 bugs over two releases are nothing short of overwhelming. Here are the two main implications. First, if the AI can find that many vulnerabilities, perhaps it can help manage, repair, test, and deploy fixes. Second, if Google's AI can find that many vulnerabilities, so can AIs operated by enemy actors. And who's to say that the vulnerabilities Google finds and fixes are the same ones that the bad guys find and exploit? It's all very disturbing. An explosive arms race The thing is, the rate of reaction has to be at warp speed. Billions of people are depending on it. But all those people aren't just counting on a continual flow of fixes; they're counting on those fixes not making things worse. To manage this, Google has developed a four-stage triage operation. At Stage 1, AI agents help filter out the bad reports, duplicate reports, and bug reports that don't really describe a Chrome security vulnerability. Google calls this "filtering out the noise." Think of it like going through your email and clearing out the junk. At Stage 2, AI agents actually reproduce the bugs. Chrome is put through its paces in virtual environments that correspond to the specific browser and operating system reported in the bug. If the bug can be reproduced, the AI adds additional details, like stack traces, to the report. Also: Open weights vs. closed: An AI civil war's afoot, and the stakes are existential This is a time-consuming stage when humans have to do it. When I get a bug report for my small product, it can take me hours to try to confirm that what a user is reporting is actually true. That's not fixing time. That's just time to determine if the bug should stay on my to-do list. If Google can get Gemini to do this automagically, the time savings for the coding team can be considerable. At Stage 3, AI agents "enrich the report with metadata." How many detective shows have we all seen where the detective is handed a police report or folder on the crime? That folder contains all the background information on the case before it is handed off to an investigator. That's what Stage 3 is doing. The AI agents are building that report in preparation for handoff. Then, at Stage 4, the AI agents identify the right human owner and hand off all the case information to that investigator. This allows the investigator to focus on the investigation and not spend a bunch of time on the administrative details necessary to initiate the case. Also: I let Chrome's AI agent shop, research, and email for me - here's how it went Google said, "While it's hard to measure precisely, we estimate that this new process is saving hundreds of hours of developer time per month." Machines fighting machines. It's really the only way to handle the rapid acceleration in exploit velocity. But the last thing you want is some AI hallucinating a fix that's delivered to half the adults on the planet and then fails. But still, with thousands of vulnerabilities being found at speed, Google needed to scale up the bug-fixing process. To do this, the blog post describes a multiagent workflow. Also: Google Search will let you instantly generate AI images for free - here's how There's a fixing agent that writes code, producing a bunch of what Google calls candidate fixes. Then there's a critic agent. This AI evaluates the fixes, determines which would be the best fit for the problem, and provides additional supporting information for developers to evaluate the fix. The two agents, the fixer and critic, cycle in a way similar to a traditional code review process until they can be sure the code is functional and meets style guidelines. Next up is the small test-writing agent army. These agents construct tests and run Chrome through the tests across all of Chrome's supported platforms. In this way, problems can be found and submitted back to the fixer and critic before any human developer has to review the fix. Google said this process saves weeks of developer time. But users are stubborn There is a gap in time between when attackers find and exploit bugs and when the fixes are released. Even when Google knows there's a bug in the wild, it has typically taken weeks for the fix to reach the Chrome stable channel. Google is working to transition to a two-week delivery cadence for major milestones and a weekly release for security updates. But with the uptick in attack velocity, Chrome is pushing to do two security releases each week. For almost a decade, Chrome has used a silent background download mechanism that would stage updates on disk, automatically running updates once a user restarted Chrome. Also: Tired of AI Overviews? I found 9 Google Search alternatives that showed me links again And yeah, none of us wants to install two new Chrome releases each week. We also don't want to restart Chrome. But that's a problem because the time between when a bug fix is downloaded and when a user restarts Chrome could be long enough for an exploit to take hold. Google said it has been working on ways to push updates without being intrusive. It is trying out a mechanism for dynamic patching that may eliminate most browser restarts. It is also working on saving the state of the browser locally so it can be resumed easily. Another tactic is to find opportune and nonintrusive opportunities to restart the browser. Also: Chrome vs. Edge vs. Firefox: I tested each browser's AI, but I'm only sticking with one As a user, I really don't like it when a vendor decides to nanny me and force updates. But I also don't like it when bad guys try to exploit my machine. It looks like Google is trying to walk that fine line, and it might just work. Save the browser, save the world Google is publishing a lot of technical information about how it is integrating AI into its defensive workflows. While the technical details are interesting, it's the strategic implications that are more profound. Also: Google is training AI on even more of your data now, unless you opt out - here's how AI has escalated the pace of attack. It can also escalate the pace of defense. The arms race is hotter and more intense than ever before. If Google can identify and find two years of bugs in two months, we can derive the pace of innovation from that ratio. Code lives in a faster timeline than ever. Two years in two months means that a year of AI-enabled coding, attack, and defense will produce the output that previously took 12 years. That's more than a decade of advancement every year. It's overwhelming. AI is causing that speed increase, and because of it, we're now dependent on AI to defend us at speed. You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter, and follow me on Twitter/X at @DavidGewirtz, on Facebook at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, on Bluesky at @DavidGewirtz.com, and on YouTube at YouTube.com/DavidGewirtzTV.

AI is finding so many Chrome security flaws that Google may start updating it twice a week

Serving tech enthusiasts for over 25 years. TechSpot means tech analysis and advice you can trust. Forward-looking: Google is speeding up Chrome's update cycle as AI tools uncover a growing number of security flaws in the browser's code. Chrome versions 149 and 150, released within weeks of each other, carried a combined 1,072 bug fixes, more than the previous 23 versions delivered combined, reflecting how quickly AI-driven analysis is surfacing issues. These tools are scanning code at a scale and speed that were not previously possible. In at least one case, the technology exposed a flaw that had remained in Chrome for 13 years. If exploited, the bug could have allowed attackers to bypass the browser's sandbox protections and access local files. The rapid pace of discovery is forcing Google to rethink how it delivers updates. The company has already shortened its release cycle to every two weeks, but it is now testing an even faster model that could push updates out twice a week. The goal is to reduce the time between identifying a vulnerability and getting a fix into users' hands. The same AI capabilities helping Google find bugs could also be used by attackers to locate weaknesses just as quickly. Faster patching is one way to limit that risk. But releasing updates more often creates another problem: users do not always install them right away. Chrome typically downloads updates in the background, but it still depends on a browser restart to complete installation. Many users delay that step, leaving systems exposed longer than intended. Google is starting to address that issue. In Chrome 150 on macOS, the browser can now update itself when all windows are closed, but the app is still running in the background. The company calls this a "zero window restart." When the user opens Chrome again, the update has already been applied, avoiding the need for a manual restart in many cases. Google is also working on a more advanced approach known as "dynamic patching." This would allow updates to be applied without any restart at all. Google has not provided details on when that capability might be ready, but it says it is continuing to invest in the effort. The increase in AI-driven vulnerability detection is unlikely to slow down. As those tools become more capable, the pressure to respond quickly will only grow, which may be why Google is moving to a different model for browser security. Rather than relying on periodic updates that require user action, Chrome is moving toward a system in which fixes are delivered continuously and with little or no disruption.

Google is rebuilding Chrome security using AI to catch hidden vulnerabilities

To prevent attackers from exploiting known vulnerabilities before users update, Google is piloting two security releases a week and pioneering "dynamic patching" to apply critical background updates on the fly without requiring a full browser restart. Google is fundamentally overhauling how it secures Chrome, leveraging AI to discover, triage, and patch vulnerabilities at a speed traditional security workflows simply can't match. As the browser picks up user-facing tweaks like an Appearance menu and under-the-hood scroll performance upgrades, Google's underlying defense mechanism is undergoing its biggest structural shift in years. According to a deep dive published on the Chromium Blog, the Chrome Security team is now deploying custom Gemini-powered agent harnesses alongside specialized AI tools from Google DeepMind and Project Zero. The push is yielding immediate results: across the Chrome 149 and 150 release milestones, Google squashed 1,072 security bugs, which is more than the combined total of the previous 23 milestones. The automated pipeline even flagged a high-severity sandbox escape bug that had quietly survived in Chrome's codebase for over 13 years. To manage the sudden influx of bug reports (which surged past 2025's total volume by March 2026), Google automated its triage and patching pipelines, with multi-agent workflows now handling the heavy lifting. "Fixing agents" draft potential candidate code, while separate "critic agents" evaluate the patches against Chromium standards, and "test-writing agents" generate cross-platform test suites. Integrated directly into Google's continuous integration setup, these models scan every commit every 24 hours, blocking over 20 vulnerabilities (including a critical S1+ flaw) from reaching production in May alone. Behind the scenes, Google is also tackling memory safety, one of the root causes for high-severity browser vulnerabilities. While the team continues to harden legacy C++ code, Google's long-term architectural solution is a migration toward memory-safe languages like Rust. However, discovering and fixing a bug only solves half the problem. Once a patch lands in Chrome's public open-source codebase, attackers race to reverse-engineer it to exploit unupdated browsers, a window known as the "patch gap." To shrink this vulnerability window, Google is piloting a shift to two security releases per week, down from its typical weekly update schedule. Getting updates shipped quickly is useless if users delay applying them. People naturally postpone restarting their browsers to avoid interrupting their active workflows, leaving their machines exposed to exploits. To fix this without frustrating users, Google is pioneering "dynamic patching," a method that leverages Chrome's multi-process architecture to hot-swap background processes such as the Renderer and GPU on the fly, without a full browser restart. Additionally, Chrome on macOS now uses windowless background states to trigger silent auto-restarts, moving toward a future in which browser security updates happen continuously, seamlessly, and entirely in the background.

Google's AI is digging up Chrome bugs that humans missed for years

Here's how Google is using Gemini AI to find, triage, and patch Chrome security bugs faster than ever. I've always assumed Chrome's endless update notifications were just routine housekeeping with a batch of actually useful features every now and then. Turns out some of them are patching bugs that have been quietly sitting in the browser's code for over a decade. So how exactly is AI catching these bugs? Google has built an AI agent powered by its in-house AI model, Gemini. Its entire purpose is to scan Chrome's entire codebase for vulnerabilities, and it's already proven itself. Among the other fixes, one catch stood out. It was a sandbox escape bug that let a compromised part of the browser trick Chrome into reading local files. The most interesting and frightening fact is that the flaw had survived undetected for more than 13 years. Recommended Videos The system also handles triage now, sorting incoming bug reports through automated steps that filter spam, reproduce the issue, and attach severity ratings, work that used to take a human five to 30 minutes per report. Once a bug is confirmed, a "fixing agent" generates candidate patches, followed by a "critic agent" that reviews them, and test-writing agents verify whether everything works across every platform Chrome supports before a human developer even looks at it. Google says this is saving hundreds of developer hours every month. So does this actually mean more bugs are getting fixed? Across just two recent Chrome updates, versions 149 and 150, Google fixed 1,072 security bugs combined, more than the previous 23 updates put together. Google is also racing to close the "patch gap," the window between a fix existing and it actually reaching your browser, by piloting two security releases per week instead of one. It's also testing "dynamic patching" that could eventually eliminate needing to restart Chrome entirely for most updates. Don't get me wrong, though. None of this means Chrome suddenly has more bugs than before. It means Google's finally catching the ones that were always there, faster than attackers can exploit them.

Stronger with every update: How we're making Chrome and the web safer in the AI Era

* The bug is found. * The bug is triaged. * The bug is fixed. * A new update of Chrome with the bug fix is released. * Chrome is restarted and the update is applied. Our goal is for every one of these steps to happen as quickly as possible. Finding vulnerabilities The Chrome Security team has been using LLMs for years. In 2023 we developed ways to use LLMs to increase security fuzzing coverage and performance. In 2024, we worked with Project Zero on Naptime, giving LLMs specialized tools for vulnerability research. And in 2025, we collaborated with DeepMind and Project Zero on Big Sleep, an AI vulnerability discovery agent that successfully found bugs in the V8 JavaScript engine and graphics stack. In early 2026, we built an agent harness that used Gemini to find vulnerabilities across the broader Chrome codebase with higher efficiency and lower false positives. One of the bugs we found was a sandbox escape that would allow a compromised renderer to trick the browser into reading local files -- a bug that quietly survived in our codebase for more than 13 years! For many of us, this moment cemented the potential of AI-powered vulnerability detection. From there, we improved on our vulnerability finding agent harness by: * Adding support for model interoperability to leverage the unique strengths of both open-weights and proprietary models. * Building a knowledge base of Chrome, including all previously identified CVEs and Chrome's entire Git history, to extend the LLMs reasoning capacity past its training data. * Encouraging developers to add SECURITY.md files, which help models better understand trust boundaries and develop an accurate view of the threat model. * Adding a "critic" agent with a separate context to consume these SECURITY.md files. * Introducing the ability to run vulnerability finding models over the codebase multiple times to account for model non-determinism and model improvements over time. We've built all of this with safety in mind, and have put in place guardrails to mitigate the risk of AI behaving unexpectedly. Our AI analyzes source code strictly at rest, operating on locked-down machines that lack general internet access. We also utilize a dedicated setup for these internal scans that intercepts all network requests, employing strict allowlists based on the initiating application and destination, blocking any suspicious model activity. Furthermore, we never run models in an unrestricted mode, and we strictly limit our subagents from modifying the local system or accessing files outside of designated source code directories. AI-powered vulnerability detection complements our existing security testing infrastructure. For example, fuzzing continues to be especially effective at finding bugs that arise from long-range interactions between disparate parts of our codebase, or those requiring a combination of seemingly unrelated operations. We also want to continue to reward external researchers for their expertise and creativity in finding the most challenging and impactful vulnerabilities via the Chrome Vulnerability Reward Program (VRP). In early 2026, we saw a gradual increase in all categories of bug reports, but by March, the shift was apparent: we received more bug reports than we had in the entirety of 2025. This led us to change our VRP to focus researchers on bug submissions that are additive to what we are finding internally, and easily ingestible by our newly automated processing pipelines. Triaging vulnerabilities As we discover more security vulnerabilities with AI-powered tools, we've simultaneously used AI to scale and automate validating, triaging, and fixing bugs. Historically, triaging a single security report took anywhere from 5 to 30 or more minutes, and relied primarily on human expertise. We have been increasingly shifting our triage process towards an automated approach that blends rule-based systems with AI to increase throughput and accuracy. The automated triage process is broken down into four key phases: While it's hard to measure precisely, we estimate that this new process is saving hundreds of hours of developer time per month, allowing our team to focus on other security priorities. Fixing vulnerabilities Across Google, developers share the responsibility of prioritizing security fixes with the security team, but scaling bug discovery requires an equally scalable bug fixing process. To achieve this, we rely on multi-agent workflows throughout: * After initial build steps that bring in context from a specific issue, we run a fixing agent that returns multiple candidate fixes. * A critic agent then evaluates which would be the best fit, producing other relevant artifacts for developers to evaluate the fix. * The fixing and critic agents work in a loop that mimics a typical code review process to ensure that code is functional and compliant with Chromium and Google style guidelines, as well as other local code conventions. * Test-writing agents help write tests for fixes. These agents can ensure that tests work across the full array of Chrome supported platforms and configurations before a developer reviews the fix, saving up to weeks of developer time. At this point, we have LLMs generating candidate fixes for most vulnerabilities, dramatically increasing the rate of security fixes in recent Chrome releases:

Google's AI patched more Chrome bugs in two releases than it had in two years, including a 13-year-old flaw

Google has published a white paper detailing how AI is transforming Chrome's security pipeline. Chrome versions 149 and 150, both released in June, collectively fixed 1,072 security bugs. That figure exceeds the total number of bugs patched across the previous 23 Chrome versions combined, dating back to June 2024. Google has been building a multi-agent AI workflow for vulnerability research since 2023. Today, its AI-powered agents are scanning code at a scale and speed that were not previously possible. In one case, this AI-driven analysis uncovered a Chrome sandbox escape vulnerability that had remained hidden in the codebase for more than 13 years. If exploited, it could have allowed attackers to escape Chrome's sandbox and access local files. The pace of discovery is now fast enough that Google is rethinking its entire update delivery model. Chrome moved to a two-week major release cycle earlier this year, but the company is now piloting a shift to two security releases per week for targeted patches. In other words, Google wants to reduce the time between identifying a vulnerability and getting a fix into users' hands, giving attackers less time to reverse-engineer vulnerabilities and develop exploits. The company is also working on several approaches to make Chrome updates faster and eliminate the need for a restart, a step many users delay and one that can leave their systems exposed longer than intended. Chrome 150 on macOS introduced what Google calls a "zero window restart," which takes advantage of the way macOS apps continue running in the background after all windows are closed. Another solution is dynamic patching, which would allow Chrome to apply security updates without requiring a restart by replacing background processes with updated binaries on-the-fly. Google has not provided a timeline for when dynamic patching will arrive in stable builds, but describes it as an active area of investment. That said, the increase in AI-driven vulnerability detection is unlikely to slow down. Microsoft also cited AI tools when explaining its record-breaking 206-flaw Patch Tuesday back in June.

Google AI Finds Sandbox Escape Bug in Chrome's Codebase

Google is using AI to improve security in its Chrome browser codebase. Recently, the California-based giant announced its new AI vulnerability agent, created with its Gemini security LLM model. It detected a long-lived sandbox escape bug that could trick Chrome into reading local files. The bug went unnoticed for over 13 years, says Google. * Make Telecom Talk My Trusted Source Google also announced tweaks to the security LLM model to ensure security integrity. They are adding restrictions to set boundaries for the AI agent when detecting vulnerabilities. Moving forward, Google is scaling up AI to automate bug validation, triaging, and fixing, tasks that usually rely on human expertise. Here is everything we know so far: Also Read: Google Pixel 11 Pro Fold Design, Renders Surface Google's Vulnerability AI Agent Fixes the 13-year-long Sandox Bug Since the AI boom, Google has been building a dedicated trusted AI agent to streamline operations. Google has worked on LLM models for years and in 2023 used them to improve overall performance. Adding AI to core security is a crucial initiative for a company like Google. To make this a success, Google spent years collaborating and building multiple projects to build an AI agent from scratch. Google collaborated with Naptime on Project Zero and developed an AI vulnerability agent with research capabilities. The following year, in collaboration with DeepMind, Project Zero and a new project called Big Sleep helped build an AI vulnerability agent that can research, find, and fix bugs within Google's core codebase.