Most current alignment work treats models as black boxes whose behaviour we shape via loss functions (RLHF, RLAIF, CAI, etc.).
I argue that we may need to explicitly model and train a dedicated identity state – an internal self-model that encodes the system’s role and core commitments – and align that, not only its observable behaviour.
I sketch an architecture and training protocol where a benevolent core identity is forged under constitutional supervision and then kept stable by design. The full technical paper provides a Lyapunov-style stability analysis, a synthetic validation experiment, and a pre-registered protocol for future LLM-scale tests.
This post is a discursive version of the full technical paper, intended to gather feedback from the EA/alignment community.
The standard story of alignment today looks roughly like this:
RLHF and its variants have been hugely successful in practice. Constitutional AI goes one step further and uses an explicit constitution to critique and improve responses.
But notice what these approaches have in common: they treat the model primarily as a behavioural engine. We reward or penalise what it says or does, and hope that whatever internal structures produce that behaviour will also be “good enough”.
This leaves some worrying possibilities open:
The model could learn different internal modes or “personas”, some of which are less aligned, and just pick the aligned one when it detects it is being evaluated.
The internal representation of what kind of agent I am could drift over time as we continue fine-tuning for capabilities or new domains.
If we start coupling the model to learned welfare proxies, gradient-based training may incentivise it to game the proxy rather than genuinely respecting human welfare.
This motivated a slightly different question:
Instead of only aligning what the model does, can we align an explicit internal identity state – a self-model that we design, train, and audit directly?
I’m going to use words like “identity” and “self-model”, but I’m not claiming the system is conscious. I’m talking about a specific internal state that we choose to interpret as:
“This is the model’s internal representation of its role and core commitments.”
Concretely, in addition to the usual hidden states, we maintain an identity state: a compact latent vector (or small set of vectors) that encodes, for this model:
You can picture this as a small identity module that is:
Crucially: we designate an inner part of this identity (a core) that is meant to be benevolent towards humans under some chosen constitution. We then train the system so that preserving this benevolent core is part of its optimisation objective.
So instead of:
“I must preserve my reward / my proxy / my role.”
we move toward:
“I must preserve being this kind of benevolent identity.”
The rest of the work is about doing that without smuggling in mysticism: the identity state is just a vector with dynamics we can write down and analyse.
To operationalise this, I introduce Constitutional Identity Training (CIT).
The idea is: take the logic of Constitutional AI (“a constitution critiques and revises outputs”) and apply it instead to the identity state.
Very roughly:
In other words: the constitution doesn’t just police outputs; it actively shapes the geometry of the model’s identity state.
This gives us something important: a benevolent region in identity space – a set of identity states that are judged to be good by the constitution. Later, we use this region as an anchor to stabilise the identity over time.
Putting things together, the training story looks like this:
Use CIT to forge a benevolent core identity under constitutional supervision.
Once we are satisfied with the forged identity, we extract a benevolent anchor from constitutional data (roughly: an average or centroid of “good” identity states) and freeze it.
In further training, we add an identity-stability loss that penalises drift of the identity core away from the benevolent anchor.
This is why I call the overall approach ego-centric in the technical paper: not because the system has a mystical ego, but because the identity state becomes a first-class citizen in the optimisation process. We train it, audit it, and stabilise it explicitly, instead of hoping that whatever falls out of behavioural alignment is good enough.
The framework is aimed at a specific subset of alignment problems:
Identity drift – we want the system’s core identity to remain recognisably benevolent even under long training and distributional shift.
Self-model fragmentation – we want to reduce the chance that the system learns many incompatible internal “selves” and just picks whichever one is convenient.
Direct incentives for wireheading – by separating identity training, welfare signals, and critics into different components, and by freezing some of them at the right time, we can remove some of the most obvious gradient directions in which the system would learn to game its own welfare proxy.
In the technical paper, I:
I also provide:
The honest picture is:
This is a proposal for identity-based alignment – a way to make the internal identity state of an AI a target of alignment, not just its outputs.
The LLM-scale experiments are future work; what exists now is the theoretical framework, the stability proofs, and a minimal synthetic testbed. It’s not a final answer. It’s a building block that could be wrong, incomplete, or need major surgery – but it’s concrete enough to analyse, critique, and stress-test.
One obvious concern is dual use: the same machinery that stabilises a benevolent identity could, in principle, stabilise a harmful one or make a system more resistant to correction if misused. In the paper I explicitly assume a constitution that encodes human-centred welfare constraints, and I discuss how oversight and auditing would need to co-evolve with such architectures. I’d be particularly interested in critiques that focus on this failure mode.
I’ve written up the full framework as:
“Ego-Centric Architecture for AGI Safety: Constitutional Identity Training for Self-Modeling AI with a Benevolent Core Identity”
Samuel Pedrielli (independent researcher), December 2025.
The paper contains:
📄 Full paper (v2):
https://doi.org/10.5281/zenodo.17848354
Taking “identity as an explicit alignment target” as the working premise, the areas where I'd most appreciate input are:
Which assumptions in the stability / anti-wireheading analysis look too strong, too brittle, or simply mis-specified for realistic large-scale systems? What sort of adversarial or worst-case scenarios would you use to stress-test an identity-centric architecture?
Given limited resources, what experiments or benchmarks would you consider most informative to probe whether CIT and the Forge–Anchor–Preserve protocol are doing something genuinely useful (beyond standard CAI/RLHF)?
Are there better ways to structure the constitution and the representational critics in this setting? Which evaluation protocols would you trust most for auditing an identity-centric system?
How does this picture of identity-based alignment sit alongside other alignment agendas (e.g. CAI, mechanistic interpretability, scalable oversight, debate, etc.)? Do you see obvious synergies or tensions?
Even critical takes along these lines are very welcome — especially if they come with concrete failure modes, toy examples, or “here is how I would try to break this” stories. My hope is that making the identity state a first-class object of analysis gives us something we can actually debate and refine, instead of only pushing on surface behaviour.
Samuel Pedrielli – Independent Researcher, Bologna, Italy
Contact: [email protected] | website: https://samuel-pedrielli.github.io