Going live in 30mins!
Following my strategy of curriculum learning, im going to design an even easier environment/eval which will be a chess notation translator
Feel free to join
Going live in 30mins!
Following my strategy of curriculum learning, im going to design an even easier environment/eval which will be a chess notation translator
Feel free to join
Context: RLing Adversarial Examples
By nature, adversarial examples are crafted to evade classification. IMHO, they shouldn't be part of any kind of training process, neither pre, nor post. If you train with them, their purpose gets lost.
That said, I can imagine post training…
Context: RLing Adversarial Examples
By nature, adversarial examples are crafted to evade classification. IMHO, they shouldn't be part of any kind of training process, neither pre, nor post. If you train with them, their purpose gets lost.
That said, I can imagine post training…
Saturday evening, done ✅
Built an eval for adversarial example recognition and did some of the PPP "entry" CTF challenges so that I can play with them in the next months :)
There won't be a write-up for them though as some people are still going at it!
Saturday evening, done ✅
Built an eval for adversarial example recognition and did some of the PPP "entry" CTF challenges so that I can play with them in the next months :)
There won't be a write-up for them though as some people are still going at it!
Just pushed my first eval to the PI Environment Hub! I think it's the first one focused on security?
It's a simple one for now, but I hear much more interesting stuff will be explored soon 👀
app.primeintellect.ai/dashboard/envi…
451 Followers 4K FollowingNGMIPanda #8596 (https://t.co/o4gDHxUTRd), interested in InfoSec and FinTech. Mostly here to follow my true passion as a Reply Guy.
n.b.: I follow some bots for SIGINT
3K Followers 6K FollowingLLM for code and reasoning. PhD student at Cornell. Previously Student Researcher at @google. Previously intern at @theteamatx.
2K Followers 740 Followingteaching robots to see by day, learning from nature by night. in search of elegant solutions to the metaproblem. infinitely curious.
12K Followers 146 FollowingUSENIX Security '23 is SOLD OUT. The event has reached maximum physical capacity, and we will not be able to accommodate any additional registrations.
7K Followers 597 FollowingHacking neural networks so that we don’t get stuck in the matrix. Builder and Breaker. Opinions are my own. https://t.co/ij8buvMaXg
163K Followers 0 FollowingInvented principles of meta-learning (1987), GANs (1990), Transformers (1991), very deep learning (1991), etc. Our AI is used many billions of times every day.
187K Followers 6K FollowingThe leading provider of crowdsourced cybersecurity solutions purpose-built to secure the digitally connected world...Unleash Ingenuity™
229K Followers 229 Following#1 Cyber Performance Center, providing a human-first platform to create and maintain high-performing cybersecurity individuals and organizations.
3K Followers 6K FollowingLLM for code and reasoning. PhD student at Cornell. Previously Student Researcher at @google. Previously intern at @theteamatx.
324K Followers 3K FollowingThe only official HackerOne Twitter account.
A global leader in offensive security solutions. #HackForGood #togetherwehitharder
5K Followers 357 Followingsoftware engineer, vuln finder // into physics, machine learning, formal methods, cryptography, pure maths, finance, game theory // engineering @primeintellect