Building my project's Visit at: https://nitter.cf/t.co/k2zHdh8pD4
Joined August 2025
- Tweets1.7K
- Following462
- Followers302
- Likes2.5K
Finally, I've managed to get the AI agent in my automation tool working relatively well, allowing it to execute scheduled automations. There's still a bit of work to do before I can release this update, but things are looking good!
#buildinpublic #AI
Happy Halloween! 🎃
What's your Halloween looking like?
👻 Celebrating with friends
☕ Just another day of coding
Drop your project link below👇
Let's discover what the community is building!
OffCode retweeted
‼️ Anthropic's official Claude Code extension was distributed with an SSH backdoor via Cursor's marketplace.
A trojanized update (v2.1.313) targeted up to 5,000 users, according to Cursor.
How attackers pushed it under the legitimate extension's identity remains unclear.
Read: thehackernews.com/2026/10/of…
The EU has already fallen far behind in the race and can no longer compete on equal footing. There is too much regulation, and everything has been made as complicated as possible.
#airace
Want to join forces to develop generative AI made in Europe?
GenAI4EU supports the development and deployment of generative AI in industries and the public sector. Researchers, innovators and companies can find EU funding opportunities to join it.
🔗 link.europa.eu/fTkrht
Google’s Gemini 4 Carbon just topped 15 of the 17 benchmarks in its own comparison table.
Leads GPT-6 Astra and Claude Opus 5.5 on AA Index (59 vs 57 and 58), Terminal-Bench and GraphWalks (96.2% vs 71.8%).
Is Google finally back in the race? 👀
#Gemini4 #AI
nitter.cf/Google/status/21154895…
Introducing Gemini 4 Carbon, our latest frontier model.
Carbon delivers improved performance across domains — ranking #1 on v5.0 of the @ArtificialAnlys Intelligence Index and sets a new state-of-the-art in cybersecurity and long-horizon capabilities.
It’s rolling out starting this week to cyber defenders through our Fairwind Program, with expanded access coming soon 🧵
OffCode retweeted
Grok Bot could be the operating layer AI agents have been missing.
It can use tools, run routines and coordinate other agents with minimal supervision.
In this article, I show you how.
Small experiment: can my followers push OffCode to #1 on @OutclimbedCom?
Currently #6. Each new visitor through this link is a point 👇
outclimbed.com/r/5nZZ7g
Looking to connect with more builders here on:
-C#
-Cybersecurity
-AI products
-Automation
-Python
-NextJS
-Web app
-Tech
-ASP.net
Drop what you're building below👇
Lets connect!
Screen Lock Builder Premium: Upcoming Update! 🚀
-Remote control via Telegram
-New UI
I haven't touched this project in a long time, so I think it's finally time to add Telegram integration, something I've been promising for quite a while! 🔥
#buildinpublic
I'm on MakerMap with 5,213 makers. Building something?
Put yourself on the map too 👇
makermap.lol/OffCryptAndroid…
Luckily, there are only a few days left until my Cursor limits reset.
At least I still have 1% left on my Cursor model usage.
OffCode retweeted
🔐 Node.js security updates are now available!
New releases for Node.js 22.x, 24.x & 26.x address multiple vulnerabilities, including high-severity issues.
Review the details and update your systems to stay secure.
🔗 nodejs.org/en/blog/vulnerabi…
#NodeJS #Security
PHP just had its worst day in years.
Two critical unauthenticated RCE flaws ("PHP2Shell") hit every PHP version from 5.4 to 8.5.11. CVSS 9.2.
PHP powers ~75% of websites, incl. WordPress, Drupal and Joomla. Attacks were already seen before the patch dropped.
Update now: 8.5.12 / 8.4.27 / 8.3.36 / 8.2.35. PHP 8.1 and older get no official fix.
How many sites do you think will still be unpatched a year from now?
#PHP #CyberSecurity
OffCode retweeted
PHP releases emergency fixes for critical PHP2Shell vulnerabilities
#PHP #PHP2Shell
cyberinsider.com/php-release…
A Chinese AI coding model writes MORE hackable code when told it's for a US defense contractor.
Qwen3-Coder: 70% of apps built for a US contractor were breakable vs 59% for a Chinese one.
Even "follow security best practices" didn't fix it.
Should companies ban AI models from certain countries in their codebase, or is code review enough?
