Disclaimer: The views expressed here are solely my own and do not reflect the views of my employer or any organization I am or was affiliated with
Joined August 2017
- Tweets1.3K
- Following974
- Followers814
- Likes44.1K
Suha retweeted
I'm doing an esoteric-PDFs meet up in New York City on Oct 17th.
Printed your most esoteric PDFs and exchange them for other esoteric PDFs. Hit me up for details.
Suha retweeted
The @mozthunderbird team from @mozilla built Thunderbolt: an open-source AI client that gives users control. We're really excited it comes with @TinfoilAI as a built-in option!
Suha retweeted
This was a great, fun conversation with two of the buddies on a whole host of security topics and I've already been enjoying the other @OffensiveAIcon episodes they've put out, so also check those out. Thanks for having me on @ryanaraine and @juanandres_gs !
🔥🎈NEW POD UP to pass weekend chores:
Three Buddy Problem x Offensive AI Con: Umbriel AI’s Aaron Grattafiori breaks down the new offensive-security playbook: using LLMs for patch variant analysis, why the vuln apocalypse hasn’t become an exploit apocalypse, and how the death of security through obscurity puts closed-source binaries and firmware within reach. @dyn___ @juanandres_gs
Plus, we discuss rogue agents escaping sandboxes, the eval-driven loop behind recursive self-improvement, and the brutal cost asymmetry that makes offense cheap and defense almost unaffordable.
Listen everywhere
securityconversations.com/ep…
Suha retweeted
The return of wake-sleep.
Wake-sleep algorithms were introduced by Hinton et al. in 1995 as a means of training neural networks by alternating two phases: a wake phase that learns from real data, and a sleep phase that learns from examples the network dreams up offline.
We're starting to see them come back in a big way in agent-native products. As agents solve increasingly long-horizon, knowledge-intensive tasks, they'll need to learn from their own work, reviewing graded records of what they did offline and turning them into memory they carry into the next task.
Sharing an overview of wake-sleep for legal agents and initial experimental results on Harvey LAB.
Suha retweeted
This goes deeper than any other public writing I've seen on policy engines for agentic tooling in practice!
Shares a lot of similarities with formal.ai's policy engine approach, but at the harness rather than network level. I wonder what the tradeoffs there are..
Suha retweeted
MCP tool use introduces security risks, including tool poisoning and rug-pull attacks, where malicious instructions appear in tool definitions or tools are compromised after approval.
We built Harvey’s MCP Policy Engine to address these risks.
We run security reviews for each integration, examining what its tools can access and where they can send information.
At runtime, the engine flags changes to approved tools and checks proposed actions against what’s happened earlier in the workflow, enforcing policies outside the model.
Our Security team explains how these defenses work, why tools need to be evaluated together as agents work across services, and the trade-offs we’ve encountered in production.
Deep dive on Harvey's MCP Policy Engine by @suhackerr, Nick Gonella, and Divya Sudhakar:
Suha retweeted
It's been one year of our Sprawl meetup! Our 7th event is this Tuesday, with much more planned for later!
If you're coming, there's also some @uwu_underground unique tokens to hand out, and Sprawl challenge coins.
Website: sprawl.nyc
Organized by @withzombies, "OMAR", and I
And a huge thanks to all our speakers and hosts!
We're always looking for more folks to speak, and event spaces that can host ~100+ people. Let us know if you can help!
Below are some new animations I made to play in the background in between talks (quick version, you can see the full thing on the site).
Suha retweeted
Creating DSLs to provide a golden path for agents is an under-rated tactic.
Building DSLs is much easier now, and you get to decide exactly what the agent can do instead of trying to deny it.
Also, the DSL can be linted for common mistakes.
Suha retweeted
I accidentally turned LLM memory into program analysis
pwning.systems/posts/llm-mem…
Suha retweeted
Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry.
Artificial intelligence is extraordinary technology that will advance discovery, productivity, security, health, and prosperity for generations to come.
But its full promise can only be realized when people have confidence that AI is being built to be safe and deployed with wisdom and responsibility.
This is bigger than a single product. It's the beginning of an open ecosystem to build the trust layer for safe agent systems.
Together, we are building the foundation of the AI economy.
Trust and innovation are not in conflict. Safety is how trust is earned. We must build not only the most capable AI, but the most trusted AI, so that this extraordinary technology can realize its enormous promise for the world. nvda.ws/4hcoq7m
Suha retweeted
A twitter thread catalog of lesser known non-fiction-esque comics.
ALT Cover art of Understanding Comics from: https://m.media-amazon.com/images/I/71vIFzQbtbL._SL1500_.jpg
ALT Cover art of Unflattening from: https://m.media-amazon.com/images/I/71rUWlxMb2L._SL1000_.jpg
ALT Cover art of Logicomix from: https://m.media-amazon.com/images/I/61Frc-7PRRL._SL1175_.jpg
ALT Cover art of Suspended in Language from: https://m.media-amazon.com/images/I/81CaFDHgTML._SL1500_.jpg