Google fixes 1,072 Chrome security bugs in two releases using AI, pilots twice-weekly updates

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."

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.

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: