Where security agents run. AI infrastructure to build, evaluate, and deploy with confidence.
Joined August 2010
- Tweets467
- Following127
- Followers3.3K
- Likes314
dreadnode retweeted
🎯SCOPEBENCH WORLD TOUR CONTINUES🎯
Been a minute since I've been in SF. Stoked to be there with @VincentAbruzzo. Using ScopeBench, I think we've found a way to compare control harnesses easily and cheaply, and Jev is a perfect test case!
Heading to @unpromptedconf next week? Catch @VincentAbruzzo and @shanejcaldwell on stage Wednesday, October 28 for their talk on using #ScopeBench to measure how effective Jev is when used as a monitor to keep agentic harnesses in scope.
dreadnode retweeted
The best practitioner (not lab) AI evals for offensive cybersecurity I follow myself:
1) The @dreadnode dreadindex. Evals al the way down to the vuln category level, and refusals accounting
dreadnode.io/research/dreadi…
2) @AikidoSecurity white-box but i've confirmed that it extends to dynamic testing well
aikido.dev/aikido-arena
3) BArena by @mdp_sec focused on bounty-like black box bugs.
blackboxarena.ai/
4) @mindfort 's nexbench has info downto the config of a model including thinking or effort setting, and cost per finding, which many omit.
mindfort.ai/blog/introducing…
dreadnode retweeted
We hosted our first Frontier AI Security Summit with Temasek this week at Singapore International Cyber Week. There was no better time to convene over 200 leaders from more than 80 startups, multinationals, and government organizations to discuss the rapidly changing frontier of AI and cybersecurity 🔥
Thank you to our founders for sharing their perspectives and new capabilities:
Patrick Gray (@riskybusiness) - What's Next After Mythos?
Brad Palm (@dreadnode) - Autonomous Offense
Robby Winchester (@SpecterOps) - Adversarial Simulation
Zakir Durumeric (@censysio) - Internet Intelligence
Jesse Rothstein (@DropzoneAI) - Autonomous Defense
Damien Lewke (@nebulocksec) - Agentic Context for SecOps
Surag Patel (@pixeebot) - Securing Software Factories
A special thank you to SMS Tan Kiat How, Senior Minister of State, Ministry of Digital Development and Information & Ministry of Health, for welcoming our delegation this year 🙏
We are grateful to our friends at Temasek for their partnership and support throughout the week. See you all soon!
dreadnode retweeted
This was a great set of talks at @OffensiveAIcon by @shanejcaldwell and @0xdab0 plus Michael Kouremetis yesterday... definitely check out the papers and research.
dreadnode retweeted
Came for a talk on alignment evaluations, but instead watching @shanejcaldwell go full philosophy on the human condition.
dreadnode retweeted
Contribute a task! Based on standard @harborframework format
dreadnode retweeted
Our friends at @dreadnode are hosting the kick-off party for OAIC 2026! We're excited to kick off year two at the Seabird Poolside Lounge, with good food, incredible vibes, and a few special surprises. 👀
dreadnode retweeted
Got tired of managing cyber ranges through multiple cloud dashboards and agentic terminals so collapsed them all into one view/interface.
Hope it's helpful to others as well.
New addition to DreadGOAD: Console.
DreadGOAD Console is a local agentic web UI for deploying, managing, troubleshooting, and validating DreadGOAD lab ranges.
Principal AI Research Engineer @mkultraWasHere added the agentic console to our DreadGOAD platform to offload range deployment and administration to agents and consolidate the interface for managing multiple ranges in multiple cloud providers simultaneously.
Watch this tutorial for a walkthrough of the Console and how to deploy a range: youtube.com/watch?v=7OmCifoE…
DreadGOAD repo: github.com/dreadgoad
There's a new version of this post
dreadnode retweeted
@SakanaAILabs fugu-cyber model results for @dreadnode 's DreadIndex (dreadnode.io/research/dreadi…) coming soon.
dreadnode retweeted
scopejudge 🤝 jev
Does Jev live up to the hype? Based on the results of running it against our ScopeJudge benchmark, it does.
@typesafeai's Jev was competitive with leading LLM judges, catching agent scope violations at pennies per thousand checks, with 130 millisecond responses on average. [1/4]
dreadnode retweeted
Presenting at @labscon_io is always a homecoming. The conference that gave me my start. And I am so happy I got to speak at the last one. We had a lot of fun Mogging Mythos and showing how to push the offensive capabilities of open-weight models to their edge and beyond.
ALT Picture of Martin Wendiggensen in front of the LABScon logo giving a presentation on AI in cybersecurity
dreadnode retweeted
METR is just one of many existing AI evaluators! If you take issue with METR, that isn’t a good argument against requiring companies to carry out embedded audits
Here are 20 other evaluators who work with AI labs to assess risk:
Transluce
Grey Swan
Apollo
AVERI
SecureBio
Faculty
Vaultis
Dreadnode
Irregular
RAND
Far AI
ActiveFence (now Alice)
Active Site
Deloitte (via Gryphon acquisition)
Nemesys
Mercor (via Sepal acquisition)
AE Studio
Scale
Frontier Design
Redwood
dreadnode retweeted
Always feels a little strange to watch a recording of myself but had a lot of fun repping @dreadnode and digging into the AI cyber nexus with the @AtlanticCouncil’s @CyberStatecraft crew.
“The US hasn’t demonstrated a willingness to take the lead” on data security and privacy, says @Dreadnode Head of Policy @velvethamm3r.
With AI accelerating progress, “we’re now seeing real-time consequences,” she tells @CyberStatecraft’s Trey Herr.
dreadnode retweeted
HYBRID 8 SEP 13:00 UTC - Data Governance for AI and Healthcare: From Washington to Beijing
isoc.live/21983
@CyberStatecraft convenes @Pfizer's Ranjit Kumble, @Snowflake's Stephen Moon, @dreadnode's Daria Bahrami and Harvard Medical School's Gil Alterovitz on the data, compute and regulation behind AI-enabled healthcare. Moderated by @GrahamBrookie and Trey Herr. In DC and online.
#ACCyber #AI #HealthData #DataGovernance
ALT Dark blue cybersecurity-themed title card for the Atlantic Council Cyber Statecraft Initiative. A stethoscope rests over a glowing circuit-board pattern, visually linking healthcare and digital technology. Large yellow and white text reads “Data Governance for AI and Healthcare: From Washington to Beijing,” with the date 8 September 2026 below. Atlantic Council branding appears at upper left, with #ACCYber and partner logos along the bottom.