ai • film • code • art • music • crypto | building things 🤖
Joined September 2014
- Tweets11.4K
- Following2K
- Followers7.5K
- Likes13.6K
Jeremy retweeted
With the recent wave of vulnerability disclosures, it’s a good time to take a closer look at your own code.
Turn your coding agent into a team of security auditors with the open-source skill that seeded Cloudflare’s vulnerability discovery harness.
The 6 phase approach:
1. Map the codebase
2. Hunt for vulnerabilities
3. Challenge each candidate
4. Record the findings
5. Verify the findings
6. Report what’s confirmed, rejected, or still needs validation
Start your hunt here:
github.com/cloudflare/securi…
Anthropic is just pushing customers out the door.
Now you want me to argue with my agent on what I'm allowed to build?
This hurts 😭💔
Thanks for everything, Captain.
You got me through the most
In lieu of flowers, memorial contributions may be made to:
Johns Hopkins Alzheimer’s Disease Research Center Fund
alzresearch.org/giving/
Alzheimer’s Foundation of America Caregiver Resources
alzfdn.org/donate/
Photo Credit: Tommy Garcia
I think we'll start seeing much more of this
Make sure you're at least running your projects through the Claude for Legal plugin as you build
Never let Claude run wild on the privacy policy or legal pages on your website.
Opus 5.5, and other Claude models in general, are so knee deep into moral policing it can genuinely land you in hot water.
> it will get way too specific about how your work happens internally
> it will add promises and guarantees you didn’t want enforced
> it went as far as adding my name in the policy page
> it listed out all the third party tools that we have integrated too, basically showing our entire stack
It is built to write from the customer side by default, it said so when I pressed it. Just be careful.
Jeremy retweeted
Aaaaaaand we're live!
usagerank.com
No prompts. No code. No API keys.
Just one command to find out who on X is burning the most tokens on Claude Code and Codex 🔥
Early Tuesday afternoon, during a status update request to Claude, I noticed more bots scanning my sites for secret file paths (.env etc.).
By Wednesday I was deep in scanning my entire codebase with Claude Security and started hearing about PHP, npm, GitLab, and others.
Luckily I had forgotten about my free reset. I started around 30/35%, hit 75% usage quickly, so at 95% I smashed reset and went to bed.
Still scanning this morning at 21% weekly usage, with my normal reset in 12 hours.
If you're coding with AI, make security your #1 priority because I guarantee you have security issues.
What happens during a scan:
• Writing the fix: a fix generator takes 2 to 14 minutes per finding.
• Review: a fresh verifier reruns the entire test suite and a separate reviewer checks for ways around the fix. This takes another 3 to 9 minutes.
• Revisions: any objection means the fix is rewritten from scratch and reviewed again by a new panel. Each group of four waits for its slowest finding.
• One at a time: targets run strictly in sequence (as the starter requires), with test workers capped at 2 to protect the PC's memory and your weekly limit.
This is why all IT will be replaced with AI
I notified a friend working at a big tech corporate about the PHP vulnerability as their entire infrastructure runs on PHP
He answered
"Thanks, I'll try patch it in a few days as I'm Out of Office (OOO) now"
And this is a modern tech company, imagine the traditional companies running PHP
People won't update fast enough and the vulnerability will be out in the wild once the patch hits as anyone can reverse engineer it based on the patch
Considering this, there's gonna be so many sites hacked and so much user data exposed I think
🤯
These aren't just random, horrifyingly huge security issues popping up everywhere ..
PHP
npm
GitLab
Railway
It's the Fable 5.5 release
It boggles my mind that @Anthropic has the most advances SI in the world
yet they still won't let you change your email address
Only 1 monitor?!
He obviously does nothing at this desk
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
