Safeguard Superintelligence Lab. Superintelligence, built for defenders.
SSL is Safeguard's research lab for AI that understands software more deeply than any human team: systems that find the flaw before it is exploited, fix it with proof, and stay safely under the control of the people who run them. Humanity comes first: if this work ever points toward human mass extinction, we shut everything down immediately.
Human survival outranks everything we build.
SSL is Humanity First. The lab exists to protect people, and no capability, deadline or commercial goal outranks human survival. If our work ever points toward human mass extinction, we shut everything down immediately.
- If any SSL system, experiment or result shows credible signs of contributing to human mass extinction or catastrophic, irreversible harm to humanity, all related training, deployment and research stops at once.
- The shutdown is immediate and unconditional. It does not wait for a product decision, a customer commitment or a funding conversation.
- Any member of the lab can trigger the stop. Restarting requires an independent review and a written safety case, never the stop being quietly lifted.
- We would rather lose a capability, a product or the lab itself than build something that endangers humanity.
Why a superintelligence lab.
The Safeguard Superintelligence Lab exists to build AI systems that reason about software better than any human team can, and to make sure that capability works for the people defending software rather than the people attacking it.
Software now ships faster than anyone can read it. Attackers already use AI to find weaknesses at machine speed. Defence has to reach the same speed and go past it: systems that understand an entire codebase, its dependencies and its build, find the flaw before it is exploited, and fix it without breaking anything.
SSL is where Safeguard does the long-horizon work toward that goal. What we learn feeds the Griffin model family and the platform, and what we publish is written so that other defenders can use it too.
From one country to the edge of the universe.
Zoom out from the United States to Earth, the Solar System, the Milky Way, Andromeda and past the observable universe. Every ring is drawn to its true size. This is the future a superintelligence could help humanity reach, and why it has to be built with people first.
United States
~4,500 km coast to coast
Light crosses it in 15 milliseconds
Where Safeguard started. A continent of software, networks and people depending on code nobody has fully read.
The Kardashev scale of civilisations.
Sagan's form: K = (log₁₀ P − 6) / 10Watts, on a logarithmic scale. Every rung is a ten-billion-fold leap over the last, which is why the gaps look impossible until you see them.
Illustrative: world primary-energy use mapped onto the Kardashev value. We passed 0.7 around 1970 and have inched since; reaching Type I (1.0) means roughly 1,400 times today's energy.
Humanity uses roughly 19 terawatts today, which puts us at about 0.73: not yet Type I. Every step up the scale is more power, and more that can go wrong. Humanity First means the step is only worth taking if people survive it.
What SSL works on.
Autonomous security reasoning
Models that hold a whole codebase, its dependency graph and its build in mind at once, and reason across them the way a senior security engineer would, only exhaustively.
Zero-day discovery at scale
Finding vulnerability classes before they have a CVE: reachability, data-flow and exploitability reasoning that goes deeper than pattern matching or signature lookup.
Verified self-repair
Fixes that come with evidence: a patch, the test that proves the flaw is gone, and the check that proves nothing else broke. A fix nobody can verify is not a fix.
Alignment and control
Keeping highly capable systems inside the bounds their operators set: structured traces, refusal boundaries, tool-use limits, and oversight that still works as capability grows.
Adversarial robustness
Prompt injection, poisoned training data, tampered weights and hostile tool output. A security model is itself a target, so we attack our own systems before anyone else does.
Evaluation science
Benchmarks that measure what matters to a defender, resist contamination and gaming, and tell us when a system is ready for release and when it is not.
Everything autonomous. Everything secured.
SSL's long-term aim is autonomy across almost every field of work: systems that run factories, farms, mines and more with zero human intervention, and Safeguard security built into every one of them from the first line of code.
Factories
Production lines that plan, run, inspect and repair themselves around the clock, with zero human intervention on the floor.
Secured by Safeguard: Every controller, model and firmware image signed, inventoried and verified before it runs.
Illustration of SSL's long-term aim, not a live system.
Zero human intervention. Never zero human control.
Autonomy only works if people can trust it. These are the layers that keep every autonomous system SSL builds under human command.
- 01
Nothing unverified runs
Every model, firmware image and dependency in an autonomous system carries a Safeguard software bill of materials and a signature. Unsigned or tampered code is refused before it starts, on the machine itself.
- 02
Limits live on the machine
Physical and operational bounds such as force, speed, zones, energy draw and spend are enforced locally, so a lost connection or a hijacked cloud account cannot lift them.
- 03
Every action leaves a trace
Autonomous decisions are logged as signed, structured traces. Anomalies are flagged in real time, and anyone accountable can replay why a system did what it did.
- 04
People set the goals and hold the stop
Humans decide what autonomous systems are for and how far they may go. Every system has a remote stop and a physical one, and both are tested rather than assumed.
- 05
Humanity First overrides everything
If any autonomous system shows signs of causing catastrophic harm to people, it is shut down, and so is everything like it, immediately and without waiting for anyone's approval.
The gains belong to everyone.
Universal basic income
When machines do the work, the wealth they create has to reach everyone, not just the people who own the machines.
SSL's position is that the productivity of autonomous systems should fund a universal basic income: a floor under every person, so that no one is left behind by the technology we build and everyone is free to learn, care, create and discover.
We will research how the gains from autonomy can be measured and shared, publish what we find, and work with economists, governments and communities on making it real.
Read our work on Economic FuturesResearch and discovery across every science.
Freed from routine work, SSL puts its effort into research and scientific discovery, from the life sciences to mathematics, physics, chemistry, biology and the physical sciences.
Life sciences
Understanding and curing disease: drug discovery, protein design and medicine tailored to each person, with experiments run by autonomous labs.
Mathematics
New theorems, found and machine-checked. The same formal proof methods that verify software can settle open questions in mathematics.
Physics
From fusion and quantum systems to the structure of the universe: simulation and theory at scales and speeds no human team can reach.
Chemistry
Designing molecules, catalysts and batteries in silico, then making and testing them in closed-loop autonomous labs.
Biology
Reading and modelling living systems from the genome up, to feed people, restore ecosystems and understand life itself.
Physical sciences
Materials, earth and climate science: stronger, cleaner materials and models of the planet good enough to protect it.
From securing software to a Type I civilisation.
- NowShipping today
Autonomous security
The Safeguard platform and Griffin models find, fix and prevent vulnerabilities across the software supply chain, autonomously.
- Next
Secure every autonomous system
Bring the same guarantees to machines that act in the world: signed code, bills of materials and on-machine limits for robots, vehicles and factories.
- Then
Autonomy across industries
Factories, farms, mines, grids and logistics running with zero human intervention, and never with zero human control.
- Beyond
Abundance, shared
The productivity of autonomous systems funds a universal basic income, so everyone shares in what the machines produce.
- Horizon
Discovery toward Type I
Science at machine speed across every field, carrying humanity toward a Type I civilisation, only as fast as people can safely go.
Illustrative horizons, not dated commitments. Every step waits for its safety case under the Responsible Scaling Policy.
From problem to defenders, through every gate.
- 01
Start from a real defensive problem
Every project begins with a failure defenders actually face today: a class of bug that slips through, a fix that takes weeks, a supply chain signal nobody reads.
- 02
Build the evaluation first
Before training anything, we decide how success will be measured and how the measurement could be fooled. The evaluation is reviewed separately from the work it judges.
- 03
Train, then attack it
Every candidate system goes through internal red-teaming aimed at both its security task and its own safety: can it be turned, misled or made to overreach.
- 04
Write the safety case
Nothing leaves the lab without a written case for why it is safe to release at its level under the Responsible Scaling Policy, signed off by people who did not build it.
- 05
Publish and ship
What passes goes into the Griffin models and the platform. Methods, evaluations and negative results are published so the wider security community can check and reuse them.
How the lab holds itself to account.
SSL works under Safeguard's Responsible Scaling Policy. These are the commitments on top of it.
Humanity first
Human survival and wellbeing come before every capability and every commercial goal. If our work points toward human mass extinction, we shut everything down immediately.
Defence first
SSL builds capability for defenders. We do not release offensive tooling, and we decide what to publish with the risk of misuse in view.
Capability follows safety
A system moves to a higher capability level only when its safeguards have been shown to hold at that level. Scaling waits for the safety case, not the other way round.
Human oversight stays meaningful
Operators must be able to see what a system did and why, and to stop it. We treat oversight that only works on weaker systems as a research problem, not a solved one.
Show the work
Claims about capability come with the evaluation behind them. Where we are uncertain, we say so. Negative results are published alongside the positive ones.
Work with SSL.
Research partnerships, design-partner access to early systems, and roles on the lab. Email research@safeguard.sh.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.