Hub · DelhiOpen globally

Delhi AI Alignment and Safety Collective

The science of how intelligence goes wrong.

Join the CollectiveSee meetups
Line drawing of Delhi: the Qutub Minar, Humayun’s Tomb and India Gate.
  • WeeklyDiscussions on alignment and misalignment
  • Any fieldCuriosity about foundations is enough
  • OnlineAnd in person in Delhi
  • 4 areasOf research, intelligence dynamics first
Delhi AI Alignment and Safety CollectiveDelhi Collective Join

Now and next

  1. Weekly discussion group

    Structured discussions on alignment, misalignment and intelligence dynamics. Beginner-friendly and open to all.

    Active now

  2. Research working group

    Members move into active research, with real output: papers, preprints and policy memos.

    Late 2026

Research focus

Alignment as a consequence of how intelligence works, not a patch.

  • Intelligence dynamics and misalignment

  • Multi-agent systems

  • Alignment and control

  • Foundations of intelligence

Who it’s for

  • Researchers in AI and ML

    You work on safety-adjacent problems and want rigorous theoretical grounding.

  • Scientists from adjacent fields

    Cognition, complex systems, neuroscience. The problems here are interdisciplinary.

  • Students

    CS, ECE, cognitive science. Any year, any university.

  • Mentors

    Active in technical alignment or complex systems research.

  • New to AI safety

    Start with a free six-week course, Technical AI Safety or AI Governance. Our AI safety career guide for India shows the next steps. Questions about the Collective? Write to us through the AI Safety India contact page.

Meetups in Delhi

In person, from our Luma calendar.

Next meetup

No upcoming Delhi meetups right now

New meetups go up on our Luma calendar first.

Subscribe on Luma
Last meetup in Delhi
Sat, 24 October 2026

AI Collusion Research Sprint

See the event: AI Collusion Research Sprint

Every event in Delhi NCR

Meetups and research sprints in Delhi NCR since September 2026. Each has its own page with the full details. Every sprint is also on our AI safety hackathons page.

  1. AI Safety India Meet Up

    20 September 2026, 6:00 pm IST · MeetupAn evening to meet people working on AI safety in India: an introductory talk by Aditya Raj, founder of AI Safety India, a surprise talk, a mixer with researchers and organisers, and dinner. Hosted with the Delhi AI Alignment and Safety Collective.

  2. AI Collusion Research Sprint

    24 October 2026, 4:30 pm IST · Research sprintThe Delhi NCR in-person session of an Apart Research sprint on catching AI agents that collude: a one-hour session to meet, form teams and pick a research question, before building the projects online through the weekend. On the same day as our Bengaluru sprint.

  3. AI x Epistemics Research Sprint

    Research sprintThe Delhi hub of Apart Research’s AI x Epistemics sprint, in person over a weekend with the Delhi AI Alignment and Safety Collective; the event page has the times. Teams build benchmarks, verification tools and products that help people think better.

A full room at the Delhi meetup in September 2026, listening to a talk under the brick wall and the jaguar mural.

Understand how intelligence goes wrong, not just patch it.

Who runs it

A field-building initiative with the AI Safety India community.

Illustrated avatar for Rishika Rai.
Collective organiser

Rishika Rai

Researching the science of scheming through dynamical systems and multi-agent modelling.

About Rishika

Built a computational model of emotional neuroplasticity using neural networks: a state-space formulation of how adaptive cognitive systems reorganise under affective and attentional dynamics (Brainstorm: A Neuroscience Challenge, Devpost 2025).

Currently researching the science of scheming through dynamical systems and resilience engineering, with a focus on emergence, attractor formation and modelling multi-agent systems.

MSc, Computer Science (Machine Learning and AI), Woolf University

Rishika on LinkedIn

With the support of

  • AI Safety India

    Collaborator: curriculum and mentors

Research focus

Intelligence dynamics and misalignment

How behaviour emerges, stabilises and fails across intelligent systems: attractor formation, scheming detection in model organisms, and deceptive alignment.

We treat alignment and safety as parts of a broader problem, not endpoints. The usual frame: a system produces bad output, so fix the output. Ours: understand what makes intelligence coherent, controllable and stable.

Research focus

Multi-agent systems

Coordination failures and unsafe emergent behaviour in networks of AI agents.

Research focus

Alignment and control

Scalable oversight, control evaluations and deceptive alignment, studied as structural properties, not output constraints.

Research focus

Foundations of intelligence

Physics-like invariants and constraints in intelligent systems, and how new abstractions emerge from them.

Join the Collective

Bring your questions to the next discussion.

Step 1 of 2Saved

About you

Two short steps, about 3 minutes in all.

Session invites come here.

For example, NIT Agartala or BITS Pilani.

Current role

Programmes

Hubs