Fable 5 as a Security Audit Engineer? That’s literally what I’m doing for the next 10 days. The mission? Run a full security audit across every client project we've built so far. Not a shallow scan. I want it to go deep, like a senior security engineer who’s paranoid about everything. Specifically, I’m asking Fable to hunt for: • Unknown vulnerabilities and overlooked attack surfaces • Business logic flaws that might allow unintended actions • Classic OWASP Top 10 risks (IDORs, auth bypasses, injection issues, etc.) • Sneaky edge cases where the code looks correct but can still be abused in production I want it thinking like a real attacker, not just running checklists. But the real value isn’t just finding bugs. For every single finding and even when it investigates something and rules it out, I’m forcing Fable to document its full reasoning process in extreme detail. Things like: - What code/context it looked at - Why it got suspicious in the first place - How it tried to verify or exploit the issue - What alternative attack paths it explored - Why it eventually accepted or rejected the hypothesis This is the part I’m most excited about. I’m not just collecting a list of vulnerabilities. I’m capturing the **actual security mindset** and investigative workflow. Every thought process, every dead end, every clever angle, all of it is getting saved. At the end of these 10 days, everything will go into a living document called: `SECURITY_AUDIT_THOUGHTBANK.md` This won’t be another boring vulnerability list. It will become our internal playbook , the accumulated knowledge of how a frontier model thinks through complex security audits. The kind of resource we can reuse and improve with every future project. Basically, I’m treating Fable 5 as my temporary senior security engineer and stealing all its knowledge. Super curious to see how good (or limited) it actually is at this level of deep reasoning. Will share the final thoughtbank when it’s done (or at least the interesting parts).

is the cursor $20 plan usable without hitting limits instantly with composer? I haven't used a composer model yet but it looks like cursor is kinda on fire right now

mcp > cli im glad this debase is not as active anymore. i use both every day. they just serve different purposes cli for stuff the model already knows. git, gh, npm, docker, file ops. trained on man pages, and costs almost nothing in context. if im already signed in locally theres no reason to wrap it in anything mcp for most integrations. slack, notion, linear, twitter and its neat to have a protocol for all these integrations - add one server to my teams cursor and everyone gets access - auth once, persists, same locally and in cloud it also just feels better in cursor. rich icons, traceable, you can easily follow whats happening (tbh not reading that much) cli for personal, mcp for team (with oauth)

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

Trying out my /teach skill today, imagining I was a vibe coder wanting to learn the basics. Here are the four lessons it created so far: 1. It interrogated me on my mission - the reason why I wanted to learn vibe coding. I said I was a teacher wanting to build a scheduling app. 2. Started me off with git so I had the ability to roll back bad work. Just 5 basic commands. No rebasing/merging yet. Perfect. 3. Taught me the basic units of a full-stack app: frontend, backend, auth and database. Every example was tied to the app I wanted to build. Quiz at the end. 4. I didn't choose a stack preference, but it noticed Node was already installed! Clever agent. So it chose Next.js and Supabase as my stack, and taught me hot reload. I got commands to set up my app. Each day sent me off to primary sources to verify that what I was learning was true. Git docs, AWS articles, Next.js docs. This is addictive, personalized, and infinite. Give it a go.

I built this MASK REVEAL hero section inside Cursor in 30 mins Achieved it with GPT Images Composer 2.5 We also shipped something similar for our client recently as well 👀 Full 2-STEP breakdown 👇