- Working on scalable oversight of offensive security agents: judge models, RL, and synthetic data.
-
Dreadnode
- St. Louis
- https://hackbot.dad
- @shanejcaldwell
Highlights
Pinned Loading
-
phreakAI/metasploit-gym
phreakAI/metasploit-gym PublicAn environment for testing AI agents against networks using Metasploit.
-
-
permission-to-stop
permission-to-stop PublicForked from safety-research/impossiblebench
Can progressive monitoring prevent agent reward hacking without reducing capability?
Python
-
phreakbot
phreakbot PublicForked from nat/natbot
Drive a browser with GPT-3 and fuzz requests for common vulns
Python 5
-
NanoDiloco
NanoDiloco PublicA minimalist & hackable torch implementation of DiLoCo: Distributed Low-Communication Training of Language Models.
Python 1
-
NoahRJohnson/AlphaZeroMiniShogi
NoahRJohnson/AlphaZeroMiniShogi PublicApplying the Alpha-Zero self-play framework to Mini Shogi.
If the problem persists, check the GitHub status page or contact support.





