degrigis
banner
degrigis.bsky.social
degrigis
@degrigis.bsky.social
Computer Security PhD student@UCSB Seclab | Binary tamer | hacking@shellphish
@saelo.bsky.social hey Samuel! Can you send me a PM? Have an interesting collab idea for V8 security.
July 13, 2025 at 12:34 AM
Aaaaand, another dive with another AIxCC team: 42-b3yond-6ug 🔥

youtu.be/ljuOnVlmCNk?...
42-b3yond-6ug's AIxCC Final Submission | 01A CTF Radiooo
YouTube video by CTF Radiooo
youtu.be
July 10, 2025 at 7:39 PM
A little dive into the past 2 years spent building an AI hacker for @darpa.mil's AIxCC competition with captains @clasm.bsky.social and @dreselli.bsky.social 🔥

youtu.be/ozp7fBoOsIQ?...
Shellphish's final AIxCC Submission with clasm and honululu | 019 CTF Radiooo
YouTube video by CTF Radiooo
youtu.be
July 8, 2025 at 9:14 PM
And that's a wrap! Artiphishell is in its final form! 🐟
Super excited to see what the other AIxCC finalists built and to see everyone CRS in action at DEFCON! 🏴‍☠️🏴‍☠️
June 26, 2025 at 6:02 PM
Back from a long hackathon with Shellphish, the things we are accomplishing with LLMs are really impressive and a demonstration of how much cybersecurity will change in the next year. Can't wait to show the world what we have been cooking! 🔥🔥
June 7, 2025 at 10:06 PM
Reposted by degrigis
My short impulse presentation from Cycon is online: youtu.be/qllU_B_Rmis?...
Fireside Chat: Gentleman Hackers with Thomas Dullien
YouTube video by natoccdcoe
youtu.be
June 5, 2025 at 8:51 AM
Reposted by degrigis
We are excited to announce that the 1st Workshop on Software Understanding and Reverse Engineering (SURE) will be co-located at ACM CCS 2025 in Taiwan! We invite the community to submit their awesome research sure-workshop.org/.

So, what is SURE? More in the 🧵
SURE 2025 | The Workshop on Software Understanding and Reverse Engineering
The Workshop on Software Understanding and Reverse Engineering
sure-workshop.org
April 25, 2025 at 4:00 PM
Reposted by degrigis
Never forget that in 1861 Charles Darwin wrote in a letter to a friend…

“But I am very poorly today and very stupid and hate everybody and everything"

…because this is my favorite reminder that we can do great things even if we don't always have great days
April 10, 2025 at 4:20 PM
Reposted by degrigis
+1, security product vendors, services companies, *and* internal teams must always operate under the Hippocratic Oath, "First, do no harm."
January 18, 2025 at 4:17 PM
Reposted by degrigis
These extraordinary photos of the LA fires have been shared widely on social media, often without crediting the photographer.

These are all the work of Ethan Swope, an LA-based photojournalist working for AP.

You can follow his remarkable reporting here👇
www.instagram.com/ethanswopeph...
January 9, 2025 at 12:44 PM
github.com
December 20, 2024 at 4:31 PM
Reposted by degrigis
When your LLM troll bot has a 2023 knowledge cutoff date
December 6, 2024 at 7:26 PM
Imagine GPT interrupting the conversation to tell you about the latest deals you can find at Target
OpenAI CFO Sarah Friar says the startup is weighing up an ads model, but plans to be "thoughtful"; sources say OpenAI has hired ad talent from Meta and Google (Financial Times)

Main Link | Techmeme Permalink
December 2, 2024 at 11:23 PM
This is too real 🫠
We misunderstood the concept of afterlife. What the religious texts meant to say is that the essence of your online life will be preserved as the weights of an LLM that handles airline customer support and prescribes Viagra in a telehealth app.
November 23, 2024 at 6:42 PM
I guess this is a new Hello World :)
November 21, 2024 at 6:46 PM