Everyday is zero-day these days

I disagree with @mattpocockuk that the code should be the source of truth when building with AI. - The intent in our minds is the true source - How we capture that in English is 2nd - Code is an implementation, and it's actually 3rd Writing is closer to thought than code. danielmiessler.com/blog/writ…

Hey @DanielMiessler I'm pretty pumped for ourlifeos.ai v8. Any updates on release timeline? I'm def also wanting to try out vector. Is there an explainer around how the two will work together?

Me too. Justice for P’nut.💔

Do jews ever feel stressed that maybe that guy really was the messiah

This is long overdue

Oh what do you know, another @github outage. Shocking.

I feel like everyone is going to figure out at the same time (in 1-4 months or so) that our biggest problem today with AI isn’t actually an AI problem. The problem is we’re not giving our AIs clear enough definitions of what we want. So our AIs basically go off and build in some direction, but not exactly the direction you want to go in. This problem has three main parts: 1. You knowing what you want 2. You being able to articulate that thing thoroughly and accurately 3. Your AI being able to do that thing Everyone assumes the problem is with number 3, but it’s usually a combination of 1 and 2. The next biggest advancement in AI (or one of them anyway) is going to come from harnesses building this concept of ideal state, evals, and hill-climbing directly into their DNA. In the model providers can help as well by eliciting this from the user and building this before any work is done. Ideal State, Evals, and hill-climbing. This is where it’s at.

This is the way

It’s the thought that counts 😅🏌️

Next time someone asks you to review their PRD, don't open it first. Write back: "Happy to! What does done look like, and how would we know if it failed?" thatsjet.com/blog/can-you-re…

When your AI agent does this the first time and you give it a memory to never do this shit again. Ever.

Jesus defeated death so you can live.

There is a better way, Arizona! Go Biggs or go home.

The Constitution only gives people the right to pursue happiness. You have to catch it yourself. ~ Ben Franklin (maybe)

AI coding has changed my security workflow dramatically: Old way: Write code → review code → find security bug → fix bug → repeat. New way: Tell the AI the security requirements → generate secure code → verify it. Turns out the cheapest vulnerability to fix is the one your AI never writes. manicode.ai

Okay did @OpenAI release another clanker that took down @github or what?

🚨 Strong General Security Recommendation: Try to reduce your number of public-facing listeners as much as possible. For both work and personal stuff. That means the number of VPNs, SSH servers, public services, etc. Anything listening, especially if it’s like remote access / admin interfaces. We should expect all public services to be far more vulnerable going forward. Or, more precisely, for AI to be able to discover and exploit those vulnerabilities. I recommend you try to put as much as possible behind protection layers, i.e., not publicly available at all.