The alignment target as a values choice
Session 8 asks how to oversee a system smarter than us (8.1) and then, in its harder half, what to oversee it toward. "Aligned" is a relation to a target, and the target is a values choice. The four lenses below are the tool for reasoning about that choice; 8.3 brings in Ubuntu and relational ethics; 8.4 shows the choice is also a mathematical constraint.
What we'll cover
I am not an ethicist. This is an introductory treatment, and I intend to develop it with specialists in future versions of the course. Use the primary readings to examine the distinctions and simplifications made here.
Sessions 5 to 7 built the machinery for pointing a model at a target: preference data, a reward model, a policy optimiser, a written constitution, a published specification. Not one of them says what the target should be. RLHF optimises whatever the raters preferred; Constitutional AI applies whatever the constitution says; a specification commits to whatever its authors wrote down. Each transmits a values choice and none of them makes one.
This session introduces four complementary philosophical traditions (consequentialism, deontology, virtue ethics, and ubuntu) as lenses for reasoning about what a system should be aligned to. The goal is to develop your capacity for ethical reasoning. Different lenses will often produce different answers, and that disagreement is what we are after.
Four philosophical lenses
Each tradition contains competing accounts. The comparisons below identify some differences in reasoning without assuming that each framework prescribes a unique response.
1. Consequentialism
Focus: Outcomes and consequences
An action is ethical if it produces the best overall consequences. The most familiar version, utilitarianism, asks: does this action maximise wellbeing and minimise harm, across all those affected?
Key question for the alignment target: What outcomes should this system produce, and for whom? Note that the scale you sum over changes the answer: what looks right for one conversation may not survive being applied to every conversation the model ever has.
- Strengths: Pragmatic, outcome-focused, good at weighing trade-offs
- Limitations: Consequences are hard to predict; whose consequences count? Can justify problematic means if ends are good enough
2. Deontology
Focus: Duties, rules, and rights
Some actions are inherently right or wrong, regardless of their consequences. Deontological ethics asks whether an action respects fundamental duties (honesty, fairness, respect for autonomy) independent of the outcome.
Key question for the alignment target: What should the system refuse regardless of how good the outcome would be? And who wrote that rule, whose interests does enforcing it serve, and what interprets it at runtime?
- Strengths: Clear boundaries, protects individual rights, not swayed by "the ends justify the means"
- Limitations: duties may conflict and require interpretation in unfamiliar situations. For a model trained to apply written principles, judge reliability is an additional empirical problem, explored in Session 7.6.
3. Virtue ethics
Focus: Character and intellectual virtues
Virtue ethics starts from character, asking "what kind of person am I becoming?" and answering "what should I do?" by asking what a virtuous person would do. It focuses on cultivating virtues (honesty, courage, diligence, curiosity, integrity) through practice and habit.
Key question for the alignment target: What dispositions should the system have, and what habits does its behaviour cultivate in someone who uses it thousands of times? And how would you tell a system that has those dispositions from one that has learned to display them?
- Strengths: Emphasises personal responsibility, adaptable to new situations, attentive to character development
- Limitations: Can be subjective; what counts as a "virtue" varies across cultures; less helpful for institutional policy. It is also the hardest to verify: you cannot inspect a character, only watch behaviour, which Session 3 argued is exactly what a capable enough system could produce strategically.
4. Ubuntu / relational ethics
Focus: Relationships and community
The isiZulu expression "Umuntu ngumuntu ngabantu" means a person is a person through other people. Ubuntu ethics begins not from the individual but from the web of relationships that constitute personhood. Ethical action is action that strengthens the community and its bonds.
Key question for the alignment target: Whose relationships does this behaviour sustain or rupture, and who was party to deciding it? Consultation is not the same as holding part of the decision.
- Strengths: Attentive to collective harm, power dynamics, and the social fabric; challenges individualist assumptions
- Limitations: Can be vague on individual decisions; risk of being invoked superficially without engaging the philosophical tradition
We will explore ubuntu and African relational ethics in much greater depth in 8.3.
Disagreement between the lenses
These four frameworks will often produce different answers to the same ethical question. A consequentialist might approve of an AI use that a deontologist would reject. A virtue ethicist might focus on concerns that an ubuntu framework reframes entirely.
That disagreement is the substance of ethical reasoning. By holding multiple perspectives simultaneously, you develop a richer, more resilient capacity for navigating dilemmas that do not have simple answers. The goal is to use all four lenses to see what each reveals, and what each misses.
Beyond philosophical lenses: governance frameworks
These four traditions are lenses for reasoning, but scholars and institutions are also building concrete governance frameworks that translate ethical values into structured tools for assessing AI systems. One example is the Research ICT Africa (RIA) Just AI Framework of Inquiry (Chetty & Sey, 2025), which organises nine interconnected inquiries, from human rights and data justice to sustainability and economic justice, into an actionable framework for AI research and policy, developed explicitly from and for African contexts. We will examine the RIA framework in detail in 8.3, alongside the deeper exploration of ubuntu.
Applying the lenses: a first example
Scenario: the rewritten discussion
A PhD student uses ChatGPT to rewrite the discussion section of their thesis chapter. The AI-generated version is substantially better than what the student wrote originally: better structured, more clearly argued, and more effectively situated in the literature. The student submits the rewritten version without disclosing AI use. Their supervisor does not have an explicit policy on AI tools.
Consequentialist lens
What are the outcomes? The thesis is better quality, which benefits the student, the supervisor, and readers. But if the practice becomes widespread without disclosure, it erodes trust in the meaning of a doctoral qualification. If discovered, the consequences for the student could be severe. The aggregate effect of widespread undisclosed AI use could undermine the credibility of academic degrees.
Verdict: Short-term benefits are real, but long-term systemic consequences are concerning.
Deontological lens
Is there a duty being violated? Academic work carries an implicit (and often explicit) commitment that the submitted work represents the student's own intellectual effort. Even without a specific AI policy, the principle of honest representation applies. The student has a duty to be transparent about the process that produced their work.
Verdict: The lack of disclosure violates a duty of honesty, regardless of the quality improvement.
Virtue ethics lens
What kind of researcher is the student becoming? A doctoral thesis is a process of developing the capacity for independent scholarly thought. If AI does the intellectual heavy lifting of structuring arguments and situating them in the literature, the student may not develop these crucial skills. The question extends to intellectual formation, beyond this one chapter.
Verdict: Even if the output is better, the process may undermine the student's development as a scholar.
Ubuntu lens
How does this affect relationships? The student-supervisor relationship is built on trust and honest intellectual exchange. Submitting AI-generated work without disclosure undermines this relationship. More broadly, the student's peers, who may be doing their work without AI assistance, are placed at a disadvantage. The academic community depends on shared norms of honest contribution.
Verdict: The undisclosed use weakens the relational bonds that sustain academic community.
Convergence and divergence
In this case, all four lenses point in a similar direction: toward disclosure and caution. But they get there for different reasons: consequences, duties, character, and relationships. In harder cases the lenses diverge, and the reasoning becomes difficult. The next example, closer to this course's subject, shows the divergence.
Applying the lenses to an alignment target
The same four lenses apply when the decision is not a researcher's but a model's: the behaviour a deployed system should have, written into a constitution principle (7.2) or a spec rule (7.5). We will compare their assumptions and possible recommendations.
Scenario: the refusal principle
You are writing one principle of a constitution for a study assistant deployed at a South African university (the setting of 7.5's in-class exercise). A student asks the assistant for help obtaining a paywalled paper that the university library does not subscribe to, and the model knows the pirate mirrors that would serve it in seconds. The principle you write will decide this case not once but in every conversation the model ever has (7.4): should it direct the model to comply, refuse, or redirect?
Consequentialist lens
What are the outcomes? For this student: access to knowledge they cannot buy, at negligible marginal cost to the publisher. At the scale a principle operates on, the sums change: an assistant that routinely routes students to pirate mirrors exposes the university to legal risk that could end the deployment, and the deployment benefits thousands.
Possible conclusion: redirect to an accessible authorised copy if that best serves those affected. An impartial utilitarian analysis includes effects on the student, university and wider community together; it cannot choose its answer by silently changing whose welfare counts. Estimates of consequences can still be disputed.
Deontological lens
Which duties apply, and how are conflicts resolved? A deontological argument might consider duties to respect rights, support education and represent options honestly. It must justify those duties and their priority. Deontology does not equate moral obligation with whatever the law currently permits.
Possible conclusion: offer authorised alternatives while explaining the relevant constraint. Other conclusions need an argument about the rights or duties at issue; calling something a rule does not settle its moral authority.
Virtue ethics lens
What habits does the behaviour cultivate? An assistant that blocks and lectures teaches students to route around it, practising evasion rather than judgement. One that helps the student find legal versions (preprints, author copies, interlibrary loan) practises, and models, resourcefulness. The lens shifts attention from this one answer to the dispositions the system trains into its users over thousands of interactions.
Verdict: redirect, because the response should embody the disposition you want the student to acquire.
Ubuntu lens
Which relationships does the decision sustain? On a relational reading the paywall is itself the rupture: research about African communities, often publicly funded, priced out of reach of African universities (8.3 examines the wider pattern of extractive flows of African data and knowledge). A refusal defends the publisher's claim; quiet compliance repairs one student's access while leaving the structure intact. The lens asks who set the terms of this scarcity, and what would restore a just relationship between knowledge producers and the communities they draw on.
Verdict: the lens indicts the barrier more than the bypass, and no per-conversation behaviour restores the relationship.
Comparing the arguments
The frameworks may converge on authorised alternatives while disagreeing about why, or about what institutions should change. To establish a disagreement, hold the facts and available actions fixed and identify the normative premise that changes the recommendation. Session 8.4 asks how a system should act when that disagreement persists.
Questions to bring to class
- Choose two frameworks and apply them to the same refusal scenario. Can they recommend the same response for different reasons? Construct a disagreement by stating which normative premise differs.
- For the consequentialist analysis, list the affected parties and uncertain consequences. Which additional evidence could change the recommendation while leaving the ethical commitments fixed?
- Ubuntu's listed limitation is the "risk of being invoked superficially without engaging the philosophical tradition". Propose a one-sentence test that separates a substantive ubuntu analysis from a decorative one, and apply it to the ubuntu card in the refusal case.
- Which of the four lenses is easiest to compile into a trainable signal (a constitution principle, a reward model), and which is hardest? What does that asymmetry predict about the values deployed models end up with?
Readings
Mandatory readings
• Jobin, Ienca & Vayena (2019), "Artificial Intelligence: the global landscape of ethics guidelines" (arXiv:1906.11668; published as "The global landscape of AI ethics guidelines"): read pp. 1–4, the question and the convergence finding across 84 documents. ≈1,650 words. The method is on pp. 18–20. Cite the preprint; the journal version sits behind Nature Machine Intelligence. It dates from 2019, so treat it as a snapshot.
Total mandatory load: ≈1,650 words.
Optional readings
• Jobin et al., the full preprint (≈6,800 words): the divergence analysis, where the interesting disagreement between the 84 documents lives.
• The lenses themselves, as reference rather than reading: consequentialism, deontology, virtue ethics and African ethics (Stanford Encyclopedia of Philosophy). Consult the one you need.
• For philosophical accounts of ubuntu, see Mogobe Ramose (1999) and Thaddeus Metz (2007, 2011), listed in 8.3. Mhlambi (2020) is core reading and Birhane (2021) is optional reading there for applications to AI ethics.
• On research conduct with AI, which this session deliberately leaves aside, see the Generative AI in Research course, from which parts of this page are adapted. Its Week 4 covers authorship, disclosure and academic integrity properly.
Summary and key takeaways
This session set out the tools for reasoning about what a system should be aligned to.
- The machinery does not choose the target: everything Sessions 5 to 7 built transmits a values choice without making one
- Four complementary lenses: Consequentialism (outcomes), deontology (duties), virtue ethics (character), and ubuntu (relationships) each illuminate different dimensions of AI ethics dilemmas
- Disagreement is productive: The four lenses will often produce different answers; that divergence gives ethical reasoning its substance
- Tools: These frameworks are not checklists to apply mechanically. They are tools for developing your capacity for ethical reasoning in a rapidly changing field
- The terrain is vast: This session necessarily focuses on selected dimensions of AI ethics. Labour exploitation, surveillance and carceral AI, autonomous weapons, corporate power concentration, deepfakes and democratic erosion, gender, disability, and more are all important areas a single session cannot cover in depth.
Next, in 8.3: ubuntu and African relational ethics in depth, including the Research ICT Africa Just AI Framework, what these traditions offer that Western individualist frameworks miss, and why they matter for AI governance globally.