Security Level 5 @SL5TaskForce

@francoisfleuret standard.sl5.org We are working on this!

If you are an impact-driven AI Security Founder or Technical Lead looking to help make SL4 and SL5 a reality, this CG 2M pre-seed and 20M philanthropic seed funding round is a great place to start. We've made great experiences with them. Hit us up with questions!

Lisa Thiergart @LisaThiergart

3 weeks ago

To my talented founder-y friends asking how they can get involved in AI safety - this is your chance! Coefficient is offering 2M pre-seed and 20M seed to found ambitious AI safety initiatives. I've had a great experience working with them as my main funder over past years. 1/n

6 5 122 9K 51

3/n They've published a list of ideas on impactful things to build. Check it out to get inspired! coefficientgiving.org/tailwind/initi…

2/n The evaluation process is straightforward, and they aim to make funding decisions within a few weeks of receiving proposals. Details and expressions of interest: coefficientgiving.org/tailwind/?utm_…

Today we’re launching Project Tailwind, a call for founders to start ambitious new AI safety initiatives: coefficientgiving.org/tailwind/?utm_… We’re looking for great people to engage seriously with the risks of transformative AI, and to create the research, technologies, and institutions that will help humanity navigate them. There are critical, basic problems that no one owns. Over the last several months, my team at @coeff_giving brainstormed ideas we’d be excited to fund if we could find a promising founder, and the list quickly grew to more than 200 entries. We’ve narrowed it down to our favorites, but we also expect the best founders to bring their own ideas: coefficientgiving.org/tailwind/initi… We’re providing funding at three levels: 1️⃣ Pre-seed: $200k to $2m to develop an idea and build a team 2️⃣ Seed: $2m to $20m to launch and scale 3️⃣ Scale: $20m to $200m+ for proven teams to scale, or world-class teams to start If you’re excited about something on our list, or you have another proposal for driving the field forward, you should get involved: coefficientgiving.org/tailwind/get-i… There are more good projects than there are people to work on them. Please help us make that stop being true! Also hi, I’m Emily! This is my first tweet. I lead AI and biosecurity grantmaking at @coeff_giving.

3/n On the practical side, we now publish the full control set as an OSCAL profile, so the overlay imports straight into existing compliance systems. That plus other quality-of-life improvements came from feedback by orgs already running the overlay. Check it out at: standard.sl5.org/changelog

2/n We also tightened the Rule of Two for the two serial encryptor layers at each endpoint: the layers can no longer share a cryptographic hardness assumption.

1/n The SL5 Standard goes post quantum! The SL5 Standard v0.1.2.- standard.sl5.org is now live — the main substantive changes are: our Inter-facility encryptors are now required to implement post-quantum algorithms, with the specific algorithm selection deferred to current guidance, since that guidance is still moving.

@Yogi_Brn @attestable Congrats Yogi! Looking forward to seeing great security work happen!

Come to AI Village at DEFCON at 10:15-11:15am today for our talk and fireside on: "Prototyping SL5 AI Datacenters: How to train frontier AI when your adversaries (and employees) are evil super-geniuses" - deepdive on our Project MOAT!

What does it take to stand up a datacenter built to Security Level 5 (SL5) from the ground up? ⚡️ @LisaThiergart will discuss Project MOAT, an exploratory SL5 datacenter built as a live test range. For session times & detail, check our conference app. #AISecurityForum

Proud to share I'll be a co-mentor at @MATSprogram for the Autumn 2026 cohort, working alongside @LisaThiergart on the @SL5TaskForce . MATS is one of the strongest talent pipelines in AI safety. Three months, real research with a mentor, on a problem that ships. Many scholars join their mentor's org afterward or spin out their own. Our stream is building SL5: security against priority nation-state attacks for frontier AI infrastructure. This year we're prototyping a real datacenter with frontier labs. The work needs people who can lead. Who we want: 3+ years security or infrastructure engineering Previously led a project with 2+ people on novel technical ground Comfortable in highly automated workflows (Claude Code, etc.) Strong Python or Rust, or excellent technical communication Bonus: TEMPEST, SCIF construction, or datacenter physical security experience. Apply by June 7. matsprogram.org/apply

I‘m mentoring again this Fall! Come work with me on Mock SL5 Datacenters!

MATS Research @MATSprogram

5 months ago

1/ 🚨 MATS Autumn 2026 applications are now open. 10-week fully-funded fellowship for aspiring AI alignment, security & governance researchers and field-builders. 📍 Berkeley + London 📅 Sep 28 – Dec 4, 2026 💰 $5000/month stipend + $8,000/month compute Apply by June 7 AoE ↓

12 94 741 3.3M 901

These are great steps! Here's 8 other things we could do: 1. Congress should fund CAISI at ~$80 million instead of $10 mn, which is our internal analysis of what it'd take for CAISI to actually fulfill the purposes laid out in the AI Action Plan and other Trump admin directives. 2. The NSA, CAISI + others should plan for the moment when >Mythos-class models are distilled or trained in China, and make a real effort in preemptive cyberdefense. We called this last year, and have some ideas on what to do (ifp.org/operation-patc…, ifp.org/the-great-refa…, ifp.org/preventing-ai-…) 3. OSTP and NSC should coordinate building RAND-style SL-4/SL-5 security for frontier model weights. Distillation is one way to get somewhat capable models, but stealing model weights gets you the best model, and it's completely doable for well-resourced state-backed actors. The weights themselves are the crown jewels, and most labs aren't close to being able to defend them! Once we train a 10x Mythos soon, we'll wish we had a secure environment to run it in. (More implementation details here: ifp.org/a-sprint-towar…) 4. Relatedly, fund + help staff an insider-threat / counter-intel program for frontier labs. It is much harder to protect model weights if adversarial people have privileged access. 5. The White House should direct Commerce/BIS to strengthen AI chip and SME export controls to adversarial countries, so that even if cyber-capable models are distilled or stolen, they can't be deployed at scale on American chips. China has huge domestic production bottlenecks (ifp.org/the-b30a-decis…), so exporting fewer chips makes a difference, pound for pound. 6. And because smuggling is still a problem, we should also be deploying chip security measures like privacy-preserving country-level location verification, which will allow us to export more chips to semi-trusted countries while verifying that they're not being smuggled to adversarial ones (more: rebuilding.tech/posts/conditio…), and there is more AI verification work to be done to enable more mutually beneficial trade without national security downsides (ifp.org/faster-ai-diff…). 7. On top of funding CAISI, we should direct it to run pre-deployment evals for CBRN and cyber uplift on a classified track. You can't hold adversaries accountable for abusing US models if we don't systematically measure what those models can do in the first place. 8. The NSC, NSA and CAISI should write the emergency-response playbook for the day a Mythos-class weight leak is confirmed, or distillation is successful. Who does what, in what order? To be in a good place, we should've started years ago. But it'll only be more urgent each passing month. Compute stock is growing 3.4x/year; LLM inference prices declining at -40x/year for a fixed level of capability; software progress is improving so quickly that the pre-trainig compute we need to reach a capability is 3 times lower each passing year (epoch.ai)... These are just some ideas for government, related to distillation and model weight theft. Philanthropy and the private sector have big roles to play as well. We have so much work to do!

Director Michael Kratsios @mkratsios47

5 months ago

The U.S. has evidence that foreign entities, primarily in China, are running industrial-scale distillation campaigns to steal American AI. We will be taking action to protect American innovation. These foreign entities are using tens of thousands of proxies and jailbreaking

558 2K 8K 943K 1K

13/n Check out our announcement blog post: sl5taskforce.substack.com/p/releasing-th…

12/n We invite frontier AI labs, government agencies, datacenter operators, and security researchers to engage with this work. Read the full standard and get involved: standard.sl5.org

1/n Today we're releasing the first public draft of the Security Level 5 (SL5) standard, designed to protect frontier AI models against nation-state adversaries. This v0.1 focuses on long lead time interventions: the things that need to start now, before SL5 is urgently needed. standard.sl5.org