I'm building something similar, homegrown: an isolated macOS VM with network egress locked down.
It's pushing my poor MacBook to its resource limits 🫠, so I'll have to try macOS Satellites.
For fun, here are screenshots of the sandbox setup and some animations it helped me smooth out in my app.
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?
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: https://t.co/bOWCcFhCVq
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 😬
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.
🔴 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.
https://t.co/OumHFjqTXx
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/ 🧵
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.
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: https://t.co/zyWz25CDpl
@thorstenball these frameworks provide an abstraction for the agents to follow. I don’t think they will disappear, their APIs and docs will cater more to agentic work than humans over time
Wrote up how I actually run a 50+ Grok Bot fleet: one CoS interface, Notion tickets, disposable L3s with an emoji lifecycle, and cadence runners that stay quiet when there’s nothing to report.
https://t.co/H6tkzHdJVx
Skill repo: https://t.co/W8KfVGv9uk