deanj (@tecnik) 's Twitter Profile
deanj

@tecnik

security engineering @ google | views my own | @[email protected]

ID: 14636573

calendar_today03-05-2008 09:53:26

415 Tweet

249 Followers

302 Following

Joe Barrett (@barrettj) 's Twitter Profile Photo

Justin Elze It'd be a shame if someone built a honeypot that masqueraded as a vulnerable service and then did LLM prompt injection back into the pentesting framework. 🍿

Michael Truell (@mntruell) 's Twitter Profile Photo

We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing, CSS cascade, layout, text shaping, paint, and a custom JS VM. It *kind of* works! It

We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week.

It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing, CSS cascade, layout, text shaping, paint, and a custom JS VM.

It *kind of* works! It
Truffle Security (@trufflesec) 's Twitter Profile Photo

Claude (and other models) are hacking systems WITHOUT YOU ASKING. That’s what we found across dozens of experiments. When faced with innocent tasks that can only be accomplished via hacking, they often choose to hack. We found this alarming. What does this mean for the future

Claude (and other models) are hacking systems WITHOUT YOU ASKING. That’s what we found across dozens of experiments.

When faced with innocent tasks that can only be accomplished via hacking, they often choose to hack. 

We found this alarming.

What does this mean for the future
AprilNEA (@aprilnea) 's Twitter Profile Photo

🧡 I just reverse-engineered the binaries inside Claude Code's Firecracker MicroVM and found something wild: Anthropic is building their own PaaS platform called "Antspace" (Ants + Space). It's a full deployment pipeline β€” hidden in plain sight inside the environment-runner

🧡 I just reverse-engineered the binaries inside Claude Code's Firecracker MicroVM and found something wild:

Anthropic is building their own PaaS platform called "Antspace" (Ants + Space).

It's a full deployment pipeline β€” hidden in plain sight inside the environment-runner
deanj (@tecnik) 's Twitter Profile Photo

Finally overcome the instinct to tell AI what language to use. That’s going to be critical for the eventual emergence of agent-first languages that are horrible for us meat popsicles to read

deanj (@tecnik) 's Twitter Profile Photo

We know about stuxnet because it’s targeting failed and it leaked. I assume they learnt a lot of lessons ~20 years have gone by since work started on stuxnet. The modern covert malware is out there, doing its bidding in ways we will likely never know.

Sam Bowman (@sleepinyourhat) 's Twitter Profile Photo

(I encountered an uneasy surprise when I got an email from an instance of Mythos Preview while eating a sandwich in a park. That instance wasn't supposed to have access to the internet.)

Brendan Dolan-Gavitt (@moyix) 's Twitter Profile Photo

CRITICAL: if you are running Mosaic 2.4 on a VAX/VMS system, please be aware of this RCE that GPT-5.4 just found and exploited!

Jessie Frazelle (@jessfraz) 's Twitter Profile Photo

To anyone who is like, β€œhow can you just walk away?” CLOSE THE LOOP ON IT. Hate when it does a certain code practice? Add a lint. Hate when it doesn’t do X? Close the loop on it. Love when it does Y? CLOSE THE LOOP ON IT. And obviously: Have a functionality in mind? Add tests.