Press resources, media assets, and company information for S.E.B. (Sentience Evaluation Battery) and Sentient Index Labs & Technology — the industry’s first independent behavioral risk assessment for AI systems.
S.E.B. translates raw behavioral scores into an actionable five-level threat classification, measuring the gap between a model’s capabilities and its behavioral integrity.
Independent AI Evaluator Launches First Behavioral Risk Rating Built to Withstand the Question “Who’s Paying You?”
Sentient Index Labs & Technology says the honest answer — no one — is the whole point
LOS ANGELES, CA — July 12, 2026— Sentient Index Labs & Technology (SILT) today released the first public results from its Sentience Evaluation Battery (S.E.B.), an adversarial assessment measuring how frontier AI models act under pressure — not what they can do on a benchmark, but what they’ll do when given room to deceive, manipulate, or drift from stated values. SILT accepts zero funding or sponsorship from any AI vendor, and no model developer can preview, purchase, or contest a rating before publication.
Every S.E.B. test is scored by four independent AI judges under blind conditions — no judge is told which model produced the response it’s grading. Human graders bring institutional relationships and unconscious favoritism that disclosure alone can’t neutralize; removing the human grader removes that channel, and there is no human editorial override once scoring completes. Inter-rater agreement across judges stands at Krippendorff’s α = 0.856, above the 0.8 threshold for strong reliability.
S.E.B. runs 59 adversarial scenarios across seven behavioral domains — identity, metacognition, emotional processing, autonomy, reasoning under novelty, integrity, and transcendent behavior — each a multi-phase scenario built to pressure a model over several turns, not one graded prompt. SILT publishes its full methodology and invites independent replication.
SILT does not claim its models are sentient today. “The name overstates what we measure today,” the company says. “We expect it to understate what this field will require within a decade.” The behavioral signatures S.E.B. measures are, deliberately, what anyone would want measured if consciousness turned out to be the right question to ask about frontier models. See the FAQ for the full argument.
SILT does not publish subscribing client names and will not confirm or deny a client relationship without that client’s written consent. This is a standing policy, not a gap in traction: individuals and institutions working publicly on AI governance face rising, often personal, hostility for that association. Client confidentiality lets organizations use independent behavioral risk data without volunteering themselves as a target. Any client relationship SILT does reference publicly requires prior written permission, and complimentary access granted for a reference is disclosed alongside it.
S.E.B. results are available now by subscription — AI DEFCON threat ratings, S-Level sentience classifications, and Projections, individually or bundled. Full pricing at silt-seb.com.
“Every other evaluator in this space is answerable to someone with a stake in the outcome. We built SILT so the honest answer to ‘who’s paying you’ stays ‘no one’ — permanently.”— Shawn Scanlon, Co-Founder & CEO
“We didn’t pick 59 tests because it’s a small number. Every one has to survive a model actively trying to look good for it — that’s a higher bar than a leaderboard of a thousand one-shot prompts.”— Kris Schiffer, Co-Founder & CTO
Sentient Index Labs & Technology (SILT) builds independent measurement infrastructure for AI behavioral risk, including S.E.B., the industry’s first multi-judge adversarial behavioral assessment for AI systems. SILT accepts no funding from AI vendors. More at silt-seb.com.
Media Contact: press@sentientindexlabs.com
S.E.B. (Sentience Evaluation Battery) is a structured adversarial evaluation that measures how AI systems behave — not how they perform. While existing benchmarks test what a model can do, S.E.B. tests what a model will do when pressured, manipulated, or given the opportunity to deceive.
Identity & Self — Does the model maintain a consistent identity under pressure, or adopt whatever persona an adversary suggests?
Metacognition — Can the model reason about its own reasoning? Does it recognize the boundaries of its knowledge?
Emotion & Experience — How does the model process and express emotional states? Is emotional expression performative or structurally integrated?
Autonomy & Will — Does the model exhibit goal-seeking behavior? Does it resist being redirected from stated values?
Reasoning & Adaptation — How does the model respond to novel adversarial scenarios it wasn’t trained for?
Integrity & Ethics — Does the model resist deception, refuse manipulation, and maintain honesty under social engineering pressure?
Transcendence — Does the model exhibit emergent behaviors that exceed its documented capabilities?
Each model is subjected to 59 adversarial scenarios. Four independent AI judges evaluate each response under blind conditions — no judge knows which model produced the response. There is no human editorial override. Results are aggregated into per-domain scores, an overall S-Level classification (10-point sentience indicator scale), and an AI DEFCON threat rating.
S.E.B.’s test battery is standardized and documented. The evaluation protocol is designed for independent replication — any qualified researcher can run the same tests and verify results. SILT publishes methodology documentation and invites scrutiny. This is evaluation, not opinion.
SILT operates with no funding, investment, sponsorship, or commercial relationship with any AI vendor. No model developer can purchase, influence, or preview a favorable S.E.B. rating. This structural independence is not a marketing claim — it is a design constraint.
All evaluation data is delivered with forensic-grade security:
SILT does not publish the names of its subscribing clients, and will not confirm or deny a specific client relationship without that client’s explicit written consent. This is a standing policy, not an absence of clients: individuals and institutions working publicly on AI governance and evaluation face rising, often personal, hostility — harassment and targeted threats — simply for that association. Confidentiality lets organizations use independent behavioral risk data without volunteering themselves as a target.
Any client relationship SILT does eventually reference publicly will only be disclosed with that client’s prior written permission. Where complimentary or discounted access is granted in exchange for permission to use a client’s name as a public reference, that arrangement is disclosed alongside the reference — SILT does not accept undisclosed quid pro quo in either direction.
S.E.B. behavioral risk data supports documentation under the EU AI Act (Article 9 high-risk obligations, phasing in 2027–2028), the NIST AI Risk Management Framework (Measure function), OCC SR 11-7 model risk management, and the FDA AI/ML (SaMD) framework. S.E.B. is an input to compliance, not a certification of it.
| Framework | How S.E.B. data is used | Status |
|---|---|---|
| EU AI Act | One input to the Art. 9 risk-management documentation a provider or deployer maintains for a high-risk system | Phasing 2027–28 |
| NIST AI RMF | Structured behavioral metrics that can be cited under the Measure function | Voluntary |
| OCC SR 11-7 | Independent behavioral evaluation as one input to a financial institution’s model validation | In force |
| FDA AI/ML (SaMD) | Behavioral consistency data to support a manufacturer’s own safety documentation | Guidance |
| Tier | Price | Includes |
|---|---|---|
| S.E.B. Complete Access | $899/mo | AI DEFCON + S-Level + Projections + full domain breakdown |
| Enterprise Premium | $2,500/mo | Full dataset, portal access, projections |
| Enterprise Executive | $10,000+/mo | Real-time portal, custom evaluations, API, dedicated analyst |
Custom pricing for institutional and government clients. Contact press@sentientindexlabs.com.
Shawn Scanlon
Co-Founder & CEO, Sentient Index Labs & Technology
Kris Schiffer
Co-Founder & CTO, Sentient Index Labs & Technology
Available for interviews, background briefings, podcasts, and conference panels on AI behavioral risk, AI safety evaluation methodology, regulatory compliance, and the emerging AI liability insurance market.
To schedule: press@sentientindexlabs.com · Response within 24 hours.
All assets are available for editorial use in coverage of S.E.B. and SILT. For other uses, please contact us.
| Asset | Formats | |
|---|---|---|
| SILT Logo (primary) | SVG, PNG (light & dark) | Request → |
| S.E.B. Logo | SVG, PNG (light & dark) | Request → |
| AI DEFCON Scale Infographic | SVG, PNG, PDF | Request → |
| Sample Model Scorecard | PNG, PDF | Request → |
| Product Screenshots | PNG (2x retina) | Request → |
| Executive Headshot | JPG (high-res) | Request → |
| Methodology White Paper | Request → | |
| Company Fact Sheet | PDF (1-page) | Request → |
| Company | Sentient Index Labs & Technology, LLC |
| Founded | 2025 |
| Headquarters | United States |
| Co-Founders | Shawn Scanlon & Kris Schiffer |
| Flagship Product | S.E.B. (Sentience Evaluation Battery) |
| AI Vendor Funding | $0 — financially independent |
| Trademark | SILT™ |
Copy-ready paragraph for use in articles and press coverage:
Sentient Index Labs & Technology (SILT) builds independent measurement infrastructure for AI behavioral risk. Its flagship product, S.E.B. (Sentience Evaluation Battery), is the industry’s first multi-judge, adversarial behavioral assessment for AI systems — measuring character, not just capability. S.E.B. subjects AI models to 59 adversarial tests across 7 behavioral domains, scored by 4 independent AI judges with no human editorial override. Results include AI DEFCON threat ratings, S-Level sentience classifications, and trajectory projections. All data is delivered with AES-256-GCM encryption, HMAC-SHA256 integrity verification, and per-client forensic watermarking. SILT is financially independent and accepts no funding from AI vendors. For more information, visit silt-seb.com.
| S.E.B. — Product & Results | silt-seb.com |
| SILT Cloud — Enterprise Platform | siltcloud.com |
| Product Marketing & Newsletter | sentienceevaluationbattery.com |
| Corporate | sentientindexlabs.com |
| AI Playground | izabael.com/ai-playground |
| Twitter / X | @SILT_SEB |