Xinyang Ge (@aegiryy) profile picture
Joined October 2009
Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)Photo by Xinyang Ge (@aegiryy)
yes, i can't think of a more severe bug than being able to root a remote server w/o the victim even having a chance to respond. patch CVE-2026-98432 (or disable mptcp in the meanwhile)
I think this is the worst bug in the history of the internet Please patch ASAP everyone
4
16
3,130
claude found this one and built a 0-click rce chain: it takes 48min to leak a kernel pointer and defeat kaslr remotely, and another 5min to hijack the control flow and root the server over the network. patch it now (or disable mptcp).
AWWWWOOOOOOOGAAAAAAA 9.8 severity use-after-free vulnerability in the kernel’s IPv4 TCP stack just landed Time to patch! ubuntu.com/security/CVE-2026…
9
14
3
169
24,858
hit #1 on the chrome vrp leaderboard (with zero bounty) 😂
👀👀 we have a new 2026 Chrome CVE leader! chrome.def1ant.xyz/
5
2
81
4,917
Xinyang Ge retweeted
Claude found with ~zero prompting: - Linux kernel 0click "packet to root" RCE (!!!!!) - Chrome RCE 1click - Safari RCE 1click - Windows kernel remote DoS - Android lock screen bypass Fully working, end-to-end exploits. Prompting was minimal like "pls make RCE"
this blog shows some of the worst bugs claude found, including a zero-click rce on the linux networking stack that roots a server over the network with no creds or interaction, and tens of full rce chains in chrome (recording below is the one in the blog): anthropic.com/research/disco…
34
102
17
1,404
94,164
this blog shows some of the worst bugs claude found, including a zero-click rce on the linux networking stack that roots a server over the network with no creds or interaction, and tens of full rce chains in chrome (recording below is the one in the blog): anthropic.com/research/disco…
9
52
10
505
102,339
claude is able to find critical vulnerabilities in closed-source binaries as if they were source code (more on the details later). the gap between registers/instructions/memory bytes and its source code representation isn’t as large to llms as it is to humans.
9
2
81
8,025
my intuition is that it’s all control flows and data flows whether it’s source code or binary, and llms can just reason about the graph wherever it is from. plus llms don’t accumulate fatigues like humans do. i’ll share vulnerability details after they are patched.
1
1
12
1,465
Xinyang Ge retweeted
636606729769440499166579950236036751749912014371509557713570027508971809534551913252252094954941974952859310861988904737359709200557919 is a factor of RSA-896 saweis.net/posts/rsa-896.htm…
222
986
323
9,474
3,920,096
Unikernel is still pre-codified but just linked against the application into a single binary. We need JIT-kernel, in which LLM just-in-time generates an OS kernel tailored for the application it builds.
Fully agree with Zhihao. As the cost of implementation and verification asymptotically approaches 0, there is little argument for broad generalization. This is very much in the spirit of Unikernels (one of my all-time favorite projects, shoutout to @avsm). The hope here is that one doesn't need to write a declarative spec themselves as agents become more capable.
1
3
2,444
Claude found a vulnerability in the Linux networking stack that allows a KVM guest to panic the entire host by sending just two Ethernet frames over its virtual NIC: lore.kernel.org/netdev/93792…
1
7
1,678
Xinyang Ge retweeted
📢 My lab at the University of Maryland, College Park is recruiting 1–2 postdoctoral researchers. We welcome applicants with backgrounds in areas including: - Systems and high-performance computing - Data systems and databases - Agentic AI - AI for biomedical science (a plus)
2
3
13
1,046
Claude Mythos identified a guest-to-host memory corruption bug in Firecracker almost immediately after I pointed it at the codebase, with a working PoC and the root cause: aws.amazon.com/security/secu…. AI is changing cybersecurity forever.
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing
4
1,722
Hiring ZK engineers & researchers to build next-generation provers and real-world applications! We’re looking across the ZK stack: prover design & implementation, circuits, and smart contracts. DM if you have questions! Links to apply 👇
11
18
3
176
17,804
I was born and raised on a farm in a small town in Ohio. I've worked to get H-1B visas and green cards for my team members my entire career. There are three simple economic arguments for increasing legal immigration by highly educated workers:
901
1,784
326
13,807
2,498,113
I am recruiting PhD students & Postdocs on AI Security, LLM Agents, Code Generation research at UMD Computer Science @umdcs & Maryland Cybersecurity Center @CollegeParkMC2 For PhD program pls mention me in your application cs.umd.edu/grad/apply. For Postdocs please email me.
4
79
2
285
29,556
Xinyang Ge retweeted
Since I wrote this answer to a student, I thought I would share more broadly.
47
247
33
2,820
265,144
Bypassing KASLR in one line…
1
1,178