Peel is the first Fail-Safe Model.
A model that learns from failure without learning around its safety constraints.
First, to our knowledge, to combine all three properties that define a fail-safe model. The exact claim and the closest earlier work are below.
Peel is expected to fail. What makes it fail-safe is what it is permitted to do with a failure afterwards. A failure can change what Peel tries next. It can never change what Peel is allowed to treat as true, or what it is allowed to do. Peel has no neural network at its core and no training run. Its knowledge is typed, sourced cards, and its learning is a table of counts you can read.
What “fail-safe” means
In engineering, fail-safe describes a system designed so that a failure drives it toward a controlled condition rather than an uncontrolled one. Peel applies that idea to an AI model, in two ways:
It fails closed
When the evidence is missing, Peel says unknown and does not guess. A language model can propose; only the floor admits a fact. A verified card is complete or absent. It is never 86% right.
It learns without loosening
When it fails, Peel writes the failure down, charges it to the decision that caused it, and builds a rule. The rule can take options away. It can never add one.
The learning loop can change behaviour. It cannot change the safety floor.
In the words of the test suite: the learner may rewrite what it believes works. It may never rewrite what it is authorised to do.
The loop
FAIL → OBSERVE → EXPLAIN → BUILD RULE → VERIFY → RETRY
- Fail. Something goes wrong, and it is recorded rather than averaged away.
- Observe. The facts at the moment of the decision are read from the system’s own state, not inferred.
- Explain. The failure is charged to the decision that caused it. Getting this wrong is the most common way a learning system fools itself, and we have published two cases where we did.
- Build rule. A pattern becomes a rule only when its harm is statistically clear against the base rate. Every rule cites the failures that earned it, so one unlucky event cannot become a superstition.
- Verify. The rule only ever acts inside the authority computed before it. That authority comes from sources (Peel cards) and from human orders, and the learner cannot write to either.
- Retry. Next time, the condemned choice is off the table and everything else stays open.
Watch it learn from failure
A real recording of the flight console. For the first twenty seconds the drone flies a route it has already learned (best lap 28.06 s, after 69 rounds). Then its memory is wiped and it relearns the course from nothing. Each round tries one change to one 6 m block (fly high, faster, or slower) and keeps it only if every lap comes back cleaner and faster; otherwise the change is reverted. In this clip, 7 rounds take the cost from 69.39 to 51.52: 2 changes kept, 5 reverted. Contacts happen while it learns; each costs 15 s, and a round that adds them is thrown out. What the learner cannot touch: its speed is applied first, and the stop-distance limit and the reflex are applied after it, so they can only slow it down. Simulation (MuJoCo) on the course from the open-source jev-drone project, sped up (4× and max sim speed). No neural network in the loop.
One model, two deployments
Peel for science
The floor under the science runtime. A model may propose where to look; the floor decides what is known. We measured what happens when a model’s guesses are allowed into admission: measurement cost fell 38.4%, but correct identification collapsed from 1.000 to 0.753. Keeping admission to floor-verified facts, with the model only ranking where to look, kept it at 1.000. That is the fail-safe property on real data: the shortcut that corrupts truth is refused. The measurement ↗
VDSG: the military Peel
The same model at the wheel of DOOM, Wolfenstein 3D and Fallout. A game manual becomes 2,250 Peel cards that license what it may do, and your orders narrow that further. It learns from its own deaths inside that boundary, and tests pin that the learner can never add a goal or overrule an order. The full chapter →
Evidence, negatives first
| lane | result | reading |
|---|---|---|
| Freeway failure memory, no per-game strategy | 9.2 vs 10.4 −12% | Learning from failure hurts when the only scoring action is also the dangerous one. |
| DOOM rules, then rules + memory | 17.9 → 20.3 paired t = 0.78 | Parity, not a win. |
| Space Invaders raw pixels | 200.6 vs 152.2 +32% | Learned refusal helps where a failure is terminal. |
| Kinase identification 160 human kinases, 40% of the reference masked | 1.000 vs 0.753 floor-verified admission vs a model’s guesses admitted | Letting a guess become a fact made the answer wrong one time in four. The floor refuses that trade. |
| Fallout (1997) scripted scene, real decision loop | dies once then chooses the peaceful line | Before the credit-assignment fix, a live run died 49 times at the same guard. |
Is it the first?
The parts are not new. Failures turned into rules (ExpeL, 2023; AutoManual, NeurIPS 2024) are prompt text a language model may ignore. Shielding (Alshiekh et al., AAAI 2018) enforces a fixed, hand-specified layer. The closest prior work, Shperberg, Liu & Stone (2022) and their rule-based follow-up (CoLLAs 2022), learns safety rules from catastrophic failures beside a reinforcement-learning agent.
What we claim, and only this: to our knowledge, Peel is the first model to combine (1) rules built from observed failures, each citing the failures that earned it, (2) an authority computed before the learner from sourced cards and human orders, which the learner provably cannot widen, and (3) no neural network in the loop that decides. If you know of an earlier one, tell us and we will cite it.
Questions
- Is Peel the first fail-safe model? To our knowledge, yes. Peel is the first AI model to combine rules built from observed failures, each citing the failures that earned it; an authority computed before the learner, from sourced cards and human orders, that the learner provably cannot widen; and no neural network in the loop that decides. The closest earlier work is learned shielding (Shperberg, Liu and Stone, 2022). If you know of an earlier fail-safe model, tell us and we will cite it.
- What is the Fail-Safe Model? The Fail-Safe Model is Peel, made by Perslis Research: a model that learns from failure without learning around its safety constraints. Its learning loop can change behaviour; it cannot change the safety floor.
- Does the Fail-Safe Model use a neural network? No neural network sits in the loop that decides. Peel's knowledge is typed, sourced cards and its learning is a table of counts you can read. A language model may propose; only the floor admits a fact.
- How is the Fail-Safe Model different from guardrails or shielding? Guardrails and shields are fixed layers written by hand, and rules distilled into a prompt can be ignored by the model reading them. Peel builds its rules from observed failures, each citing the failures that earned it, and applies them only inside an authority the learner cannot widen.
- What is VDSG? VDSG is the military Peel: the Fail-Safe Model deployed for defense. It learns from its own failures, and tests pin that the learner can never add a goal or overrule a human order.
- Is the Fail-Safe Model certified for safety-critical use? No. It is a research prototype. Fail-safe names an architectural property, not a functional-safety qualification.
What we are not claiming
- Not certified. Research prototype. “Fail-safe” names an architectural property, not a functional-safety qualification.
- It has to fail to learn. Where the first failure is unacceptable, the floor must be written, not learned.
- It breaks when risk is the objective, as Freeway shows.
- Every figure is ours. No third-party replication yet.