Maybe I'll just tell claude to build the next big thing that'll come out of Anthropic "No mistakes".

I've bitten a thousand more than i can chew...Kilobyte i guess.

Thrilled to share that my article was among the winners🎉 Huge thank you to Raenest (formerly Geegpay) and DevCareer Africa for creating such an incredible platform to share ideas mukhtar.hashnode.dev/from-image-upl…

X shows translation first now

AI is a force multiplier. Develop expertise of a certain subject or domain, acquire taste & judgement & move faster with AI. Everyone uses AI now. If your expertise is non-existent, you're no different from the other person.

I don't understand why a protocol will think they are unhackable.

A correct protocol integrating with another correct protocol does not automatically produce a correct system

Claude design by anthropic 🤯

Got my first valid submission on Code4rena. A few months ago I’d just stare at codebases with no clue what was going on.

If you're new to web3 security and want to stand out with AI: Start here → github.com/pashov/ai-web3… Run the top tools. Study what they do well and where they fall short. Build what fills the gap. Don't rush. Ship something worth using, not worth announcing.

Why does the the brain ignore the second the?

When the assumption is strong enough, the eyes can only see the intention, while the compiler sees the instruction.

Why is no one talking about this? NVIDIA is offering around 80 AI models via hosted APIs absolutely for free. You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc. This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and

Saw some results in the web3 security space and it feels good tbh

Smart contracts execute your mistakes perfectly.

Among all the LLMs i use daily, I see claude like the big brother that is capable. I reach out to it when others stress me.

1/ After my last job post, I got more DMs asking for advice than offers. So here’s a simple rule for security: If you can’t think like an attacker, think like a defender. If you can’t do that either, just find what matters the most.

Rust, Rust, Rust, Rust, Rust This is where we are finding a ton of Critical/High severity issues lately. Maybe the AI tools are lacking there? Solidity code lately has been cleaner than Rust, hands down. Finding Criticals, it's just the usual for us now...