Aaron retweeted
Security things from the last few days:
- CopyFail (linux pwn'd)
- CopyFail 2/Dirty Frag
- 13 advisories in Next.js
- Over 70 CVEs addressed in MacOS 26.5
- ~50 CVEs addressed in iOS 26.5
- YellowKey (Windows Bitlocker pwn'd entirely)
- GreenPlasma (Windows privilege escalation)
- CVE-2026-21510 and CVE-2026-21513 confirmed to be used by Russia for Windows RCE
- CVE-2026-32202 separately confirmed to be used by Russia for sensitive document access
- Mini-Shai Hulud (over 300 JS and Python packages compromised via GitHub Action cache poisoning)
- Google confirms they have identified AI-powered exploitation of zero days in an unidentified "open-source, web-based system administration too"
- Canvas (popular LMS used in most schools) pwn'd entirely
- PAN-OS (palo alto networks) pwn'd with a 9.3 severity CVE-2026-0300
Are you scared yet?
Do you even understand what this means?
An open source model just released that is:
• Just as smart as Sonnet 4.5
• Incredible at coding
• Can run on almost any modern computer
If you have 32gb of RAM (most Mac Minis do) you can have unlimited super intelligence on your desk. For free.
Sonnet 4.5 was released 5 months ago
In 5 months that level of intelligence went from frontier to free on your desk
And not only that, can run on any laptop with 32gb of RAM
If you have the memory, do the following immediately:
1. Download LM Studio
2. Go to your OpenClaw and ask which of these new Qwen models is best for your hardware
3. Have it walk you through downloading and loading it
4. Build apps with it knowing you are using your own personal, private super intelligence on your desk
The people denying this is the future are so beyond lost.
🚀 Introducing the Qwen 3.5 Medium Model Series
Qwen3.5-Flash · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-27B
✨ More intelligence, less compute.
• Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B — a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts.
• Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models — especially in more complex agent scenarios.
• Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring:
– 1M context length by default
– Official built-in tools
🔗 Hugging Face: huggingface.co/collections/Q…
🔗 ModelScope: modelscope.cn/collections/Qw…
🔗 Qwen3.5-Flash API: modelstudio.console.alibabac…
Try in Qwen Chat 👇
Flash: chat.qwen.ai/?models=qwen3.5…
27B: chat.qwen.ai/?models=qwen3.5…
35B-A3B: chat.qwen.ai/?models=qwen3.5…
122B-A10B: chat.qwen.ai/?models=qwen3.5…
Would love to hear what you build with it.
Aaron retweeted
I always wondered which Ollama model my machine could run properly.
Now you can easily do that using llms-checker
It's a CLI tool that checks your system specs and recommends the best models to run on Ollama based on what your machine
npm install -g llm-checker
github.com/Pavelevich/llm-ch…
Aaron retweeted
I'm joining @OpenAI to bring agents to everyone. @OpenClaw is becoming a foundation: open, independent, and just getting started.🦞
steipete.me/posts/2026/openc…
Aaron retweeted
Try it now on OpenRouter: openrouter.ai/minimax/minima…
Aaron retweeted
An open-source alternative to Claude Cowork, powered by OpenCode, offering the same agentic desktop flow for free with local MCP agents, custom skills, Slack and WhatsApp connectors, file level permissions, and visual dashboard
OpenClaw 2026.2.2 🦞
169 commits. 25 contributors.
• Feishu/Lark - first Chinese chat client 🇨🇳
• Faster builds (tsdown migration)
• Security hardening across the board
• QMD memory plugin
This project moves fast because the community does. github.com/openclaw/openclaw…
Aaron retweeted
True! This is why Canonical, RedHat, Valve (and us) are all betting on them. Because they solve no problems whatsoever 🙃
Immutable Linux distros solve a problem most home users don't have
bit.ly/4tdLpD0
OpenClaw 2026.2.1 🦞
🔒 Major security hardening: path traversal, LFI, exec injection fixes
🧵 Discord thread routing + gateway message timestamps
🔐 TLS 1.3 minimum, system prompt guardrails
🛠️ Streaming stability, memory search fixes
20+ community PRs 🙏 github.com/openclaw/openclaw…
Aaron retweeted
We have an announcement for you this fine Tuesday! #Valheim is coming to Mac, and it’s happening next week! 🍏 There will, of course, be full crossplay support.
Aaron retweeted
ADHD inconsistency in a nutshell:
It’s not that I can’t get my shit together.
It’s that I can’t ✨keep✨ my shit together.
Aaron retweeted
Thought for today: autistic people are super vulnerable to being gas lit. It’s taken me years to realise the extent of this. We believe people, even when they tell us what we are and aren’t experiencing.
Aaron retweeted
Who's in the US and would like a RackNerd shirt and coffee mug? All you have to do is retweet this, and we'll DM you! We're doing this for the next 30 minutes, so please retweet this by 11:59AM PST. 3/26/2021
Aaron retweeted
Mr. President, if you grant only one act of clemency during your time in office, please: free Julian Assange. You alone can save his life. @realDonaldTrump
Aaron retweeted
Do you want free unlimited premium ☕ all summer? 500,000 votes for YES by 6/22 and it's yours, America. #FREECOFFEE4SUMMER
87%Yes!
13%Nah, I prefer to pay
588,748 votes • Final results Aaron retweeted
Thankful for our @ring doorbell catching and alerting us to somebody trying to break in during the night. Was able to scare them off with the house alarm and call the Gardai before they managed to get in.

























