Ractor

Writes
The
Hack

[Hacking Articles @hackinarticles]

Pic of the Day

#infosec #cybersecurity #cybersecuritytips #pentesting #cybersecurityawareness #informationsecurity

[Ractor @Ractorrrrr]

@ravikiran_dev7 Good luck, they removed anthropic models 😂

[Tushar Verma @TusharSoni014]

Let's be honest Claude Code was not working good with local LLMs.
So, I Tried using @opencode with @lmstudio
using Qwen 3.5 9B model on my RTX 5080 GPU.
It's very usable and much faster than Claude Code.
I'm actually planning to use this setup to build an entire vibe coded SaaS

[Ractor @Ractorrrrr]

Claude Opus 4.6 leaked its entire system prompt (15,000 tokens) in just 4 prompts.

Not a zero-day. Just someone asking nicely.
The "safety-first" AI company forgot the basics:
- File system layout exposed
- User location data exposed

Stronger locks. Taped to the window.

[Timon Wong @t31kx]

Claude Code: "You've hit your limit · resets 7pm"

Me from 5-6.59pm

[Ractor @Ractorrrrr]

Is this about ethics, or just bad security ops?

[Ractor @Ractorrrrr]

Anthropic got labeled a national security risk.

First company in US history.

Two weeks earlier, someone posted their full system prompt on GitHub.

[Ractor @Ractorrrrr]

Maybe the Pentagon label helps.

Now there's a consequence for bad opsec.

[Ractor @Ractorrrrr]

7/ What's your take on AI courses vs. learning by doing?

Reply below - curious what actually worked for you.

[Ractor @Ractorrrrr]

I just finished Anthropic's official "Claude Code in Action" course.

Got the certificate.

Completely wasted my time.

Here's why it fails (and what to do instead) 🧵

[Ractor @Ractorrrrr]

6/ If you want to learn Claude Code, here's the actual course:

Open it. Break things. Read the docs. Build something real.

That's it. No certificate required.