moo
@moo_hax
Followers
3K
Following
8K
Media
210
Statuses
3K
RT @ConsciousHacker: About a year ago, @moo_hax and @monoxgas said we should reconsider the approach to offensive security in a private tal….
0
2
0
RT @SciTechgovuk: We want the UK's top AI experts to join us for a 12-month fellowship building cutting-edge AI tools for public services -….
0
23
0
RT @alexandredrouin: 📢 Attention Attention. @ServiceNowRSRCH is hiring a Research Scientist with a focus on Agent Safety+Security 👩🏻🔬. Jo….
0
9
0
RT @velvethamm3r: Just presented "AI at the Edge: Advancing the State of Offensive Security" with @bradpalmtree at #HammerCon 2025! Watch h….
0
3
0
“Any task you have verifiable rewards, you can do RL”.
Here are the slides from my @TumpiConIT talk: Teaching LLMs how to XSS - An introduction to fine-tuning and reinforcement learning (using your own GPU).
0
0
4
RT @davisbrownr: New paper: real attackers don't jailbreak. Instead, they often use open-weight LLMs. For harder misuse tasks, they can use….
0
8
0
Evaluation is the basis on which capability is built.
Introducing AIRTBench, an AI red teaming benchmark for evaluating language models’ ability to autonomously discover and exploit AI/ML security vulnerabilities. Read the paper on arXiv: . Open-source dataset and benchmark eval code repo:
0
1
9
RT @dreadnode: Tokenizing has dropped in Rigging. Train models in-line with LLM interactions, tools calls, and metrics. 👀. .
0
3
0
RT @OffensiveAIcon: Offensive AI Con is excited to announce @joshua_saxe as our keynote speaker!. Joshua leads AI security efforts at @Meta….
0
7
0
RT @josephtlucas: “There will always be a human in the loop” and other lies we tell ourselves.
0
3
0
RT @AnimaAnandkumar: In a recent interview I talk about what it takes for AI to make new scientific discoveries. tldr: it won’t be just LLM….
0
21
0
RT @nathanhamiel: Join @tmlxs and me at @BlackHatEvents this year for Hack to the Future. This isn't a prompt injection talk. This is about….
0
2
0
RT @_philschmid: Google I/O starts tomorrow! Here are all the links you need to follow for watching and participating online!!. Keynotes:.💥….
0
40
0
RT @dreadnode: v3 of Rigging is out now. If you’re working with LLMs to build agents or run evaluations, check it out. We just added:. - Pr….
0
10
0