SELINA LABS
SURFACE 07ONGOING LIVE

Research

Four threads run underneath every product we ship. None of this is speculative work sitting in a paper. Each thread exists because a system already in production needed it to be true, and each result is measured against whether it survives contact with real users and real adversaries.

SHE NARRATES THIS SURFACE
ACTIVE THREADSFOUR
PRODUCTION LINKAGEDIRECT
ADVERSARIAL TESTINGCONTINUOUS
SPECULATIVE WORKNONE
STRATUM 00RESEARCH STATE ACTIVE

POSTERIOR COLLAPSE

Thread 01. Illustrative.

ATTACK SUCCESS VS DEPTH

Thread 02. Dashed is shallow persona, solid is authored depth. Illustrative.

RESEARCH LOG

THREAD 01ACTIVE ACTIVE

Inference under uncertainty

Most production systems collapse a distribution into a single number and present it as an answer. The number is easier to display, easier to act on, and strips out exactly the information a decision-maker needed most, which is how much to trust it.

We keep the distribution end to end. Bayesian estimation over sparse and adversarial data, posteriors that update sequentially as evidence arrives, and forecasts that carry credible intervals which widen honestly when the data thins rather than projecting false precision.

The practical consequence is a system that degrades gracefully. When evidence is thin it says so. When a regime shifts, the interval opens before the point estimate becomes wrong, which is the difference between a model that warns you and one that fails silently.

/ bayesian inference/ posterior estimation/ hierarchical modeling/ sequential updating/ credible intervals/ monte carlo sampling/ uncertainty quantification/ regime detection/ prediction modeling
THREAD 02ACTIVE ACTIVE

Narrative depth as an adversarial defense

A persona assembled from a list of traits is a thin surface and behaves like one under attack. There is nothing underneath the description, so an adversary who can get the model to reconsider the description has already won.

We authored a full-length novel and embedded it beneath the persona layer, giving the system an interior that was written rather than specified. The character has history, contradiction and continuity that were never enumerated as rules and therefore cannot be enumerated away.

Internal adversarial testing found this measurably improves resistance to identity hijack, impersonation and instruction override. The defense travels with the character across every model it runs on, because the depth lives in the authored substrate rather than in any single provider guardrail.

AGENT SWARM

Parallel adversarial probes against one target. Illustrative.

/ persona depth/ identity hijack resistance/ instruction override defense/ adversarial evaluation/ cross-model consistency/ authored substrate/ red team automation
THREAD 03ACTIVE ACTIVE

Memory that survives the session

Context windows are storage, not memory. They hold what was recently said and lose everything else on overflow, which is adequate for a tool and inadequate for anything meant to know your work over years.

Real continuity requires structure, consolidation and forgetting, plus a retrieval model that knows what is currently relevant rather than what is merely lexically similar. Episodic detail has to promote into durable understanding without losing the timeline that produced it.

We build memory as a maintained system with its own lifecycle rather than a transcript appended to a prompt. That means the working set stays coherent as it grows instead of degrading into an undifferentiated pile.

/ persistent memory/ consolidation/ temporal indexing/ relevance modeling/ context compaction/ retrieval architecture/ episodic to semantic promotion
THREAD 04ACTIVE ACTIVE

Cryptography as an architectural constraint

Privacy claims are worth what the architecture enforces and nothing more. A policy commitment is a statement about our future conduct. An architectural constraint is a statement about what is possible, and only the second survives a subpoena, a breach or a change of ownership.

We design so that the honest answer to whether we can read your data is structurally no. Per-user key isolation, hardware-backed wrapping, client-side encryption where the product allows it, and deletion implemented as key destruction so removal is a mathematical property rather than an operational promise.

We also publish where the guarantee stops. A system that claims more than it enforces is worse than one that claims less, because the first invites decisions the architecture cannot support.

/ zero-knowledge design/ per-user key isolation/ crypto-shredding/ client-side encryption/ authenticated encryption/ metadata minimization/ threat modeling
STRATUM 05PRACTICE ACTIVE

How the research reaches production.

01ORCHESTRATIONMulti-agent pipelines with explicit state, retry semantics and observable failure modes.
02DATALarge-scale ingestion, transformation and feature pipelines built for continuous operation.
03PROVIDERSModel-agnostic routing across Anthropic, OpenAI, Gemini, xAI and ElevenLabs.
04INFRASTRUCTUREGoogle Cloud Platform. Cloud Run, Cloud Jobs, Cloud SQL, Redis, Celery, Stripe.
05EVALUATIONAdversarial suites run continuously rather than at release, because the threat surface moves.
06DISCIPLINEProduction quality as the entry condition. No prototypes promoted to production by accident.
MEET SELINA