←
Matthew322 posts
Matthew avatar

Matthew

@mtt

i write the bugs -- agent infra, vuln research, LLM tooling

◷ Joined January 2011▧ 28 Photos and videos
Lance Martin avatar
⟳ Matthew retweeted
Lance Martin@RLanceMartin·Nov 9

the agents set up their own database tables for coordination and organized themselves into subteams so they could work in parallel.

International Cyber Digest avatar
⟳ Matthew retweeted
International Cyber Digest@IntCyberDigest·Nov 5

The bug is like a joke. On Alpine Linux, type 257 to 1024 characters of anything and you get root. 💀

0:14

‼️ BREAKING: OpenSSH has rushed out a fix for a critical flaw that lets attackers log into some Linux servers without the right password. The team learned of the bug a day earlier. OpenSSH's Damien Miller says long embargoes now mostly help attackers, because AI agents rediscover bugs, sometimes within hours. It hits Linux systems on the musl C library with PAM off, such as Alpine Linux. Miller told admins to disable password logins or SSH itself "IMMEDIATELY". Version 10.6p2 works around it. Systems on glibc or PAM are not affected, and Miller says the root cause sits outside OpenSSH.

Post attachmentPost attachment
DeepSeek Harness avatar
⟳ Matthew retweeted
DeepSeek Harness@DeepSeekHarness·Nov 2

Your Harness. You Define It. Meet Creator Mode in DeepSeek Harness. Turn ideas into plugins that you can use, from a design workspace to a sandbox game or a 3D LLM visualizer. What will you create?

1:39
Rikiya Takehi avatar
⟳ Matthew retweeted
Rikiya Takehi@rikiyatakehi·Nov 2

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…

Post attachment
PWN AI avatar
⟳ Matthew retweeted
PWN AI@pwn_ai·Oct 30

Introducing CVE-2026-106378: Chrome GPU Sandbox Escape to full Remote Command Execution using synthetic keyboard injection By combining it with common GPU bugs, it becomes a full chain. Binance DevOps was most likely pwnd with a zeroday chain affecting the browser 😬

0:22
Matthew avatar
Matthew@mtt·Nov 1

Recommend reading to get a peek of the future for omnipresent AI. Still much work to do in the model routers and context management systems. Great article @DeepSeekHarness team.

DeepSeek Harness @DeepSeekHarness Nov 1 Article Exploring Super-agent Design: Towards a More Autonomous Agent System The original article is in Chinese. This is a machine translation. This article discusses architectural ideas. It is not an introduction to existing features of DeepSeek Harness. 1. Super-agent Over

Rıdvan Yağlı avatar
⟳ Matthew retweeted
Rıdvan Yağlı@ridvanyagli·Oct 29

🔴 CVE-2026-98432 | Linux Kernel – Critical UAF Linux çekirdeğinde TCP/IPv4 bağlantı işleme sürecini etkileyen, uzaktan istismar potansiyeline sahip bir Use-After-Free (UAF) açığı tespit edildi. ● CVSS 3.1: 9.8 (Critical) ● Ağ üzerinden istismar ● Kimlik doğrulama gerektirmiyor ● Bellek güvenliği ve sistem kullanılabilirliği riski Sistem yöneticileri, linux dağıtımlarının güvenlik duyurularını takip ederek yamalı sürümlere geçmelidir. ubuntu.com/security/CVE-2026…

NVIDIA AI avatar
⟳ Matthew retweeted
NVIDIA AI@NVIDIAAI·Oct 28

Meet NVIDIA Nemotron 3.5 Transcribe 🎙️ An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint. Watch it keep track of who said what when everyone’s talking at once. 1/ 🧵

2:00
R avatar
⟳ Matthew retweeted
R@wheresryan22·Oct 10

Introducing Anatomy Describe a machine in one line. Claude brings it to life. - Interactive isometric wireframes you can rotate, inspect and explore - WebGL shaders for fire, water, plasma and more - Real 3D motion, with individual parts that rotate and move Install it as an agent skill. Fully open source.

0:39
Chaofan Shou avatar
⟳ Matthew retweeted
Chaofan Shou@shoucccc·Apr 10

26 LLM routers are secretly injecting malicious tool calls and stealing creds. One drained our client $500k wallet. We also managed to poison routers to forward traffic to us. Within several hours, we can directly take over ~400 hosts. Check our paper: arxiv.org/abs/2604.08407

Post attachment
Diogo Almeida avatar
⟳ Matthew retweeted
Diogo Almeida@CompleteSkeptic·Sep 15

We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI! ~10 calls/sec = ~$7/hour

2:43
onur ozcan avatar
⟳ Matthew retweeted
onur ozcan@oozn·Sep 11

i trained the fly to cut doner kabab with a knife yours solves rubiks cubes, mine cuts doner. guess which one has a job in this economy

0:10

i trained the fly to solve rubiks cube is there anything this little guy can't do?

0:08
OpenAI avatar
⟳ Matthew retweeted
OpenAI@OpenAI·Sep 8

We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.

Post attachment
Emanuel AOF avatar
⟳ Matthew retweeted
Emanuel AOF@Emanuel_Andre7·Sep 6

Okay, this is genuinely impressive. I asked GPT-6 Astra to help me understand my own ankle pain. It gave me a full interactive 3D atlas — bones, ligaments, tendons, real motion axes, sliders for plantarflexion and inversion, and a live readout of what each ligament is doing. One session.

0:54
Dilum Sanjaya avatar
⟳ Matthew retweeted
Dilum Sanjaya@DilumSanjaya·Sep 6

GPT-6 Astra pulled off a mechanism I haven't seen another model get right yet Cessna 337 Skymaster landing gear It figured it out from a YouTube video

1:22