This project focuses on creating internal and external guides for PauseAI to increase active membership. The outputs will be used by the team of volunteers with high context and engagement, including the key decision makers. 

Activism and advocacy has historically been cornerstones for policy and social change. A movement's size is critical to achieving its goals. The project's outcome will be an official growth strategy for PauseAI Global: an actionable guide for increasing active members (volunteers, donors, protesters) within 6-12 months.

PauseAI currently lacks comprehensive growth strategies and tactics, and there's uncertainty about resource allocation soon. This project will delve into tactics that have aggressively accelerated growth for other movements, both historical and recent.

By the end, we'll refine our findings, analyze PauseAI's current tactics, and recommend clear guidelines for immediate action. This guide will also include tactics applicable to national PauseAI chapters.

• Familiarity with doing research 

• Working with uncertainty 

• Social intelligence, high EQ

This project aims to build an AI Policy course that explores how traditional legal frameworks are increasingly outdated, providing no clear answers to AI capabilities and advances. The course will highlight the vulnerabilities in current regulations and the potential for corporations and authoritarian governments to use AI tools to exploit gaps in areas such as IP, privacy, and liability law.

This course would focus on identifying and understanding these new legal gaps and critically exploring proposed solutions. This would be achieved through literature review, case law and ongoing legal disputes. 

It will explore, for example, how AI can be used to violate IP and privacy rights, or how current liability structures are weak against AI generated damages. This weak framework incentivises AI developers to take greater risks, increasing the chance of catastrophic consequences. It will also analyse the lack of regulation on adopting AI-driven decision-making systems in essential sectors. (E.g. employment, law, housing). Reporting the erosion of fundamental rights, socio-economic risk and the threat automation by algorithms pose to democratic procedures.

Policy researcher:

• Strong writing and communicative skills.

• Strong research and analytical skills. In particular experience researching and reviewing one of two key areas:

  1. Law and policy:

     • Case law

     • Regulations

     • Policy reports 

     • Soft law and treaties

     • Legal analysis and commentary.

     • Think tank (or similar entities) reports

  2. Socio economic literature and data:

     • Literature and reports on AI use impact on the legal areas identified

     • Reports and data on negligent AI use in the loophole areas identified.

     • Other relevant data analysis or reports

     • Think tank (or similar entities) reports

Web developer

• Web building and design skills.

• Flexibility to make changes as the course structure and content develops.

• Allow the website to be editable by the team to allow more flexibility.

Course materials designer

• Educational science skills. 

  • E.g. Previous experience or studies on developing educational materials. 

  • Teaching skills or experience.

• Curriculum development and instructional design skills to deliver the content in an engageful way. 

The intention of this project is to be an engine for mobilisation of the Stop AI campaign. The goal is to get 1 million people a week to see a series of video ads composed of 30 sec/1 min videos. These ads will be video soliloquies by 1) famous people and/or experts in the AI field saying why AI is a massive problem, and 2) ordinary people such as teachers, nurses, union members, faith leaders, construction workers, fast food employees, etc. saying why they believe we need to Stop AI.

Each ad will have a link attached which takes people to a regular mobilisation call. The attendees at this call will be presented with pathways to action: join a protest, donate, record a video ad, invite 3 people to the next call.

Roles

Project lead: Will lead the video pipeline – from collecting, to editing, to posting videos on social media. Receives stipend of $1,500 total.

Scout: Will receive a target demographic to research contact lists for. Will directly contact these people asking if they would like to participate in the campaign, either by phone, email, social media or all three.

Canvasser: Will canvas in-person on the ground, asking people to contribute their video.

Editor: Someone who can edit down phone camera recordings into easily watchable and relatable clips. 

Write a blogpost on LessWrong summarising simulator theory—a lens for understanding LLM-based AI as a simulator rather than as a tool or an agent—and discussing the theory’s implications on AI alignment.  The driving question of this project is: “What is the landscape of risks from uncontrolled AI in light of LLMs becoming the (currently) dominant form of AI?” 

• At least a basic understanding of AI safety theory

• Solid writing and communication skill

• (Optional) it would be good to have at least one person on the team who is not especially familiar with ML or LessWrong, but has generally good communication skill, and can act as a test audience to prevent the group from leaning too heavily on jargon and in-group assumptions.

• (Optional) deep understanding of Machine Learning for fact-checking.  If we don’t find someone for this role, I will look for an external advisor.

• Time and willingness to participate!

There are many open research questions around LLMs' general reasoning capability, their ability to do causal inference, and their ability to generalize out of distribution. The answers to these questions can tell us important things about:

• Whether LLMs can scale straight to AGI or whether further breakthroughs are needed first.

• How long our timeline estimates to AGI should be.

• Whether LLMs can potentially do AI research, kicking off a cycle of recursive improvement.

We can address several of these questions by directly investigating whether current LLMs can perform scientific research on simple, novel, randomly generated domains about which they have no background knowledge. We can give them descriptions of objects drawn from the domain and their properties, let them perform experiments, and evaluate whether they can scientifically characterize these systems and their causal relations.

This should be a pretty accessible project for anyone with these skills:

• Comfort with writing straightforward Python code (or willingness to learn ahead of time)

• A basic understanding of LLMs, which needn't be deeply technical -- you should be able to describe in general terms what the following are and why they matter: attention heads, MLP layers, the residual stream.

Optional bonus skills, absolutely not requirements:

• Experience with interpretability -- this project could include some interesting interp aspects if anyone is excited to go in that direction, but doesn't have to.

• An understanding of the underlying mathematics of latent space in transformers (understanding the contents of this 3Blue1Brown video is sufficient) 

Sycophancy and deceptive Alignment are an undesired model behaviour resulting from misspecified training goals e.g. for Large Language Models through RLHF, Reinforcement Learning by Human Feedback (AI Alignment Forum, Hubinger/Denison). While sycophancy in LLMs and its potential harms to society recently received media attention (Hard Fork, NYT, August 2024), the question of its measurement remains challenging. We will review existing Sycophancy Benchmarking datasets (Output 1+2) and propose new Sycophancy Benchmarks demonstrated on empiric experiments (Output 3+4). 

Mandatory requirements:

- strong interest in AI Safety

- research-oriented coursework, experience working with papers

- statistics background

- basic coding: Python preferred

Optional:

- experience as a Research Assistant

- knowledge on meta studies and methods surveys

- coursework on experimental design

-AI Safety standardisation, background knowledge

With the release of increasingly powerful models like OpenAI's GPT-4 and others, there has been growing interest in the reasoning capabilities of large language models. However, key questions remain: How exactly are these models reasoning? Are they merely performing advanced pattern recognition, or are they learning to reason in a way that mirrors human-like logic and problem-solving? Do they develop internal algorithms to facilitate reasoning?

These fundamental questions are critical to understanding the true nature of LLM capabilities. In my research, I have begun exploring this, and I have some preliminary findings on how LLMs approach reasoning tasks. Moving forward, I aim to conduct further experiments to gain deeper insights into how close and reproducible LLM reasoning is compared to human reasoning, potentially grounding our assumptions in concrete evidence.

Future experiments will focus on layer-wise analysis to understand attention patterns, perform circuit discovery, direction analysis, and explore various data science and interpretability techniques on LLM layers to gain insights and formulate better questions.

Required

• Proficient in Python and PyTorch and good with data science aspect of things.

• Significant software engineering / general programming experience.

• Experience working with transformer language models and transformer interpretability framework.

Preferred

• Proficiency in reading research papers and understanding how specific ideas could be applied to the project.

• If someone who also has some knowledge of frontend would be good as I’m not so proficient with that.

• Have experience in paper writing and is familiar with LaTeX.

In the last year, there has been much excitement in the Mechanistic Interpretability community about using Sparse Autoencoders (SAEs) to extract monosemantic features. Yet for downstream applications the usage has been much more muted. In a wonderful paper Sparse Feature Circuits, Marks et al. do the only real application of SAEs to solving a useful problem to date (at the time of writing). Yet many of their circuits make significant use of the “error term” from the SAE (i.e. the part of the model’s behaviour that the SAE isn’t well capturing). This isn’t really the fault of Marks et al., it just seems like the underlying features were not effective enough. 

We believe that the reason SAEs haven’t been as useful as the excitement suggests is because the SAEs simply aren’t yet good enough at extracting features. Combining ideas from new methods in SAEs with older approaches from the literature, we believe that it’s possible to significantly improve the performance of feature extraction in order to allow SAE-style approaches to be more effective.

We would like to make progress towards truly understanding features: how we ought to extract features, how features relate to each other and perhaps even what “features” are.

Required skills:

• Everyone:

  • Understand what SAEs are (e.g. have read Towards Monosemanticity or my blog post). If you haven’t read either of these yet, go have a look! Just want to check you find the SAE problem interesting

  • Has taken >=1 course on Linear Algebra or has watched the 3b1b Linear Algebra videos 

  • Has some understanding of how transformers work (e.g. at least one of: have watched the 3b1b Neural Network videos, have built a transformer from scratch, have read A Mathematical Framework For Transformer Circuits etc.) 

  • Like giving clear feedback - you feel able to read a paper/blog post draft and say “hm i didn’t like that part because X”

  • Enjoy (or think you would enjoy) collaborating with others

• Engineers: 

  • Comfortable with PyTorch (or Jax) but don’t need to have done MechInterp research before

  • Has some code which is open source (or is not public but are willing to share). Doesn’t need to be anything fancy or even ML - a class project, some weekend curiosity notebook or anything works! Alternatively have worked as a software engineer

  • Strongly encouraged: Likes types in Python

• Theorists/Distillators

  • Able to code-switch between formalism and informality

  • Desire to clarify conceptual confusion 

  • Background in mathematics, statistical theory, physics or analytic philosophy

Diverse and interesting skills (nice to have and definitely apply if you have them but not necessary!):

• Philosophical background 

• Interest in category theory, model theory or functional analysis 

• Strong in geometry, topology, information theory or information geometry 

• Technical social scientist or humanities person (e.g. an economist who can code / a theologian who understands group theory) 

• Contributions to open-source ML eg. HuggingFace/TransformerLens etc.

• Has a blog (especially if about ML) and/or enjoys writing papers 

• Good intuition for reasoning about high dimensional spaces

• Artistically minded: likes graphic design and/or web design; can draw technical diagrams in Figma, Canva, Powerpoint or Google Slides

• Understanding of compressed sensing or sparse coding theory 

• Reads a lot of papers: can synthesise themes and spot good, but underexplored, ideas

• Research experience in any field (e.g. from a PhD, Research Masters or academic internship etc.) would be useful

• Interest in the craft of storytelling in both fiction and non-fiction: good communication is universal and good research tells a story

The Tiling Agents problem (aka reflective consistency) consists of analysing when one agent (the "predecessor") will choose to deliberately modify another agent (the "successor"). Usually, the predecessor and successor are imagined as the same agent across time, so we are studying self-modification. A set of properties "tiles" if those properties, when present in both predecessor and successor, guarantee that any self-modifications will avoid changing those properties.

You can think of this as the question of when agents will preserve certain desirable properties (such as safety-relevant properties) when given the opportunity to self-modify. Another way to think about it is the slightly broader question: when can one intelligence trust another? The bottleneck for avoiding harmful self-modifications is self-trust; so getting tiling results is mainly a matter of finding conditions for trust.

The search for tiling results has three main motivations:

* AI-AI tiling, for the purpose of finding conditions under which AI systems will want to preserve safety-relevant properties.

* Human-AI tiling, for the purpose of understanding when we can justifiably trust AI systems.

* Tiling as a consistency constraint on decision theories, for the purpose of studying rationality.

These three application areas have a large overlap, and all three seem important.

• Some experience with mathematical proofs is required.

• A basic understanding of logic and probability theory is required.

• A significant math background is preferred.

• Proficiency in decision theory is preferred (EG understand the difference between CDT and EDT, familiar with some arguments for/against them).

• An understanding of updateless decision theory is preferred.

• Philosophy background is a bonus.

• Writing skill is a bonus.

• Learning theory is a bonus.

• Game theory is a bonus (EG, took at least one graduate-level course in the subject).

Factored Space Models (Link of Arxiv will be here, when we have uploaded the paper, probably before November (Overview) were first introduced as Finite Factored Sets by Scott Garrabrant and are an attempt to make causal discovery behave well with deterministic relationships. The main contribution is the definition of structural independence that generalizes d-separation in Causal Graphs and works for all random variables you can define on any product space, e.g. a structural equations model. In this framework we can naturally extend the ancestor relationship to arbitrary random variables. This is called structural time.

We want to use and extend the framework for the following applications taken, in part, from Scott’s blog post.

1. Embedded Agency

2. Causality / Interventions

3. What is (structural) time?

4. Efficient Temporal Discovery

Here are slides from a talk (long form) explaining Factored Space Models with a heavy focus on structural independence starting from bayesian networks. 

You have to be comfortable with basic levels of Mathematics, including finite probability theory.

Questions to check if you have the minimum requirement:

Prove A ⊆ B ⇔ A ∩ B = A

Prove that the space of probability distributions on a finite set Omega is convex.

Given a cartesian product Omega = Omega_1 times Omega_2, is the space of product probability distributions on Omega convex?

TL;DR: Can we develop methods that prevent online learning agents from learning from rewards that reward harmful behaviour without any agent supervision at all!? 

This project uses a novel AI Safety Paradigm, developed in a previous AI Safety Camp, Representation Noising, that prevents adversarial reward optimization, i.e. high reward which would result in learning misaligned behaviour, by the use of “implicit” constraints that prevent the exploration of adversarial reward and prevent learning trajectories that result in optimising those rewards. These “implicit” constraints are baked into deep neural networks such that training towards harmful ends (or equivalently exploring harmful reward or optimising harmful reward) is made unlikely.

The goal of this project is to extend our previous work applying Representation Noising to a Reinforcement Learning (RL) setting: Defending against Reverse Preference Attacks is Difficult. In that work we studied the single-step RL (Contextual Bandits) setting of Reinforcement Learning From Human Feedback and Preference Learning.

In this project, we will apply the same techniques to the full RL setting of multi step reward in an adversarial reward environment that is in the machiavelli benchmark. The significance of this project is that if we can develop models that can not optimise adversarial rewards after some intervention on the model weights, then we will have made progress on safer online learning agents. 

Roles 

Role Type (0): Ideally one person with solid organisational skills will volunteer as Team Coordinator.

Role Type (1): Ideally half the group will have interest and background with technical execution of empirical experiments in either LLMs or RL.

Role Type (2): Ideally the other half of the group will have interest in conceptual or theoretical development of our ideas, algorithm formulation, or policy development.

Commitment Requirements
In order to participate in the project, you will be asked to complete an average of one task per week. 

Skill requirements

This project requires a mixture of skills from different backgrounds. Candidates are encouraged regardless of how strong they feel their skills are in each skill track as long as they have sufficient interest and commitment to self-learning in areas where they feel like their background is deficient.

The main asks are:

1. Competency with and understanding of Large Language Models including

   1. Experience with training LLMs and behavioural evaluation

   2. Experience with analysing LLM internals 

   3. Basic fluency with LLM research and research techniques

   4. Comfort in execution of empirical experiments and analysis with high level guidance

2. OR Competency with and understanding of Reinforcement Learning including

   1. Experience with using popular Deep RL algorithms like PPO, DQN

   2. Familiarity with the current Deep RL research landscape

   3. Comfort in execution of RL environments, modelling, and training with high level guidance

3. Some familiarity or exposure to algorithm analysis

   1. Comfort with reading proofs and standard mathematical notation

   2. Exposure to correctness proofs and/or deriving bounds

   3. Wishlist: basic familiarity with one of: Optimization, High Dimensional Statistics, Differential Geometry, Information Theory

For (1) and (2) basic competence with independently writing and running code is assumed. Experience for (1) and (2) can be as basic as “taken the hugging face course on LLMs or RL” or “read a book on machine learning (Sutton and Barto for example) and did the exercises”.  (3) is not required but is desired.

Candidates may apply without this background and we can discuss a plan for them to gain the appropriate skills before the project begins as long as they feel comfortable committing to this pre-study. For example I may ask candidates to complete https://huggingface.co/learn/deep-rl-course/en/unit0/introduction before joining if they are lacking in (2) or to review https://web.stanford.edu/group/sisl/k12/optimization/#!index.md if lacking in (3).

Candidates who are theoretically or conceptually oriented (mathematics-wise) are encouraged to apply even if they do not meet (1) or (2).  We are especially looking for folks who have a background or interest in optimization (3).

Candidates who have a policy or conceptual interest (non-mathematical) are also encouraged to apply and have many opportunities to work on fleshing out the policy implications of our work out and working alongside us to make sure the technical work is grounded in real world problems.

Non-requirements (Who should not consider this project)

You should not consider this project if your intention is: to only give advice, feedback, or only participate in conversations. We are happy for you to participate as an external reviewer if this is the case but you should not apply if this is the intention. Folks with conceptual, policy, and theoretical skills will need to demonstrate this through the production of writing artefacts.

This project aims to extend and enhance the Multi-Turn Human Jailbreaks (MHJ) dataset introduced by Li et al.. We will focus on developing lightweight automated multi-turn attacks, evaluating transfer learning of jailbreaks, and conducting qualitative analysis of human jailbreak attempts. By expanding on the original MHJ work, we seek to provide more comprehensive insights into LLM vulnerabilities and contribute to the development of stronger defenses. Our research will help bridge the gap between automated and human-generated attacks, potentially leading to more robust and realistic evaluation methods for LLM safety. 

Required:

- Strong Python programming skills

- Experience with large language models

Recommended:

- Familiarity with AI safety concepts and jailbreaking techniques

- Good scientific writing and communication skills

Nice to have:

- Experience with prompt engineering and adversarial attacks on LLMs

- Knowledge of red teaming practices

- Familiarity with qualitative data analysis techniques

- Experience with open-source collaboration and Git version control

In August 2024, Sakana published their research on the ‘AI Scientist’. https://sakana.ai/ai-scientist/. They fully automate the ML research process - from generating ideas to writing a formal paper - by combining various LLM-based tools in an appropriate pipeline. The headline result is it generates weak graduate level research for about $15 per paper.

The aim of this project is to adapt and refine this tool for AI Safety research.

Minimum skills / attitudes

• Enough Python skills to quickly learn how to run LLMs and do prompt engineering

• Ability to read and understand ‘simple’ AI safety research papers

• Willingness to think critically: ask questions of one’s own work and of others work to help us all improve.

• Willingness to learn, both things that are directly related to project but also soft skills

• Willingness to work on an open-ended project in an agile way. Goals of the project will shift depending on the skillset of people working on it and on the progress made week by week

Ideal skills. I do not expect any single individual to have many of these.

• Strong software engineering skills. Comfortable navigating new medium size codebases (e.g. the one by Sakana), knowledge of how to sandbox experiments, can create front-end tools / VSCode extensions

• Use best practices in collaborative coding. Use GitHub, regular commits, regular pull requests, well-documented code and experiments.

• Experience with LLMs and prompt engineering

• Experience fine-tuning LLMs

• Broad understanding of AI Safety space, to judge what is good/useful research in a large range of topics.

• Ability to reproduce large range of AI safety papers

The ultimate goal of this interdisciplinary research program is to contribute to AI safety research by actually constructing an ideally virtuous AI system (iVAIS). Such an AI system should be virtuous as its deep character, showing resilience (not complete immunity, which is vulnerable) to prompt injections even if it can play many different characters by pretending, including a villain. The main content of the current proposal consists of two components: 1. Self-alignment and 2. The Ethics game, which are both based on the idea of agent-based alignment rather than content-based alignment, focusing on what one is doing, which requires metacognitive capacity. 

Either 1) general skills and experience in coding with Python, fine-tuning and RLHF for an open-source LLM, or 2) general knowledge about the AI safety research and literature. 

This is a project for creating culture and technology around AI interfaces for conceptual sensemaking.

Specifically, creating for the near future where our infrastructure is embedded with realistic levels of intelligence (ie. only mildly creative but widely adopted) yet full of novel, wild design paradigms anyway. 

The focus is on interfaces especially for new sensemaking and research methodologies that can feed into a rich and wholesome future.

Huh?

It’s a project for AI interfaces that don’t suck, for the purposes of (conceptual AI safety) research that doesn’t suck.

Wait, so you think AI can only be mildly intelligent?

Nope.

But you only care about the short term, of “mild intelligence”?

Nope, the opposite. We expect AI to be very, very, very transformative. And therefore, we expect intervening periods to be very, very transformative. Additionally, we expect even “very2 transformative” intervening periods to be crucial, and quite weird themselves. 

In preparing for this upcoming intervening period, we want to work on the newly enabled design ontologies of sensemaking that can keep pace with a world replete with AIs and their prolific outputs. Using the near-term crazy future to meet the even crazier far-off future is the only way to go. 

(As you’ll see below, we will specifically  move towards adaptive sensemaking meeting even more adaptive phenomena.)

So you don’t care about risks?

Nope, the opposite. This is all about research methodological opportunities meeting risks of infrastructural insensitivity.

-----------------------------------------------------------------------------------------------------------

Watch a 10 minute video here for a little more background: Scaling What Doesn’t Scale: Teleattention Tech. 

If you’re good at or interested in engineering, writing, designing or generally open-minded and quick to learn, you’re a fit. If you made it through this doc (even if you have lots of questions and confusions) or like to think in meta-systematic ways, then you’ll love it here. 

RLHF is no good on tasks which humans are unable to easily “rate” output. I propose the Recursive Information Market, which can be understood as an approach to rate based on a human rater’s Extrapolated Volition, or a generalized form of AI safety via debate. 

Minimum skills:

• Good economic intuitions: I might ask some application questions of the form “Argue against this gut instinct: …” 

• General fluency in Python: Writing code is one of the two main things we do to make sure the things we’re saying aren’t fake bullshit (the other way is betting on prediction markets). I would like to make sure that everyone is capable of writing clean code, and is generally “fluent” in stuff.

I would be especially happy to have someone who can make significant contributions on theoretical work, i.e. on coming up with and proving solid, useful theorems. Someone who can do the bulk of the effort on this I would happily grant joint-first-author position to.

The majority of team members, I assume, would be working on implementations in the various contexts stated earlier.

This project integrates neuroscience and AI, leveraging human brain data to align AI behaviors with human values for potentially greater control and safety. In this initial project, we will take inspiration from Activation Vector Steering with BCI, to map activation vectors to human brain datasets. In previous work, a method called Activation Addition was tested and found to more reliably control the behavior of large language models during use, altering the model's internal processes based on specific inputs, which allows for adjustments to topics or sentiments with minimal computing resources. By attempting to recreate elements of this work with the integration of brain data inputs, we aim to enhance the alignment of AI outputs with user intentions, opening new possibilities for personalization and accessibility in various applications, from education to therapy. 

Skill Requirements Research Engineer:

• Strong programming skills in Python and familiarity with libraries like PyTorch

• Experience in designing, building, and maintaining software systems, preferably in a research or technology development setting

• Demonstrated ability to work effectively on projects involving complex data sets and machine learning models

• Excellent problem-solving abilities and a commitment to high-quality engineering practices

Skill Requirements Research Scientist:

• Proficiency in Python and experience with frameworks such as PyTorch

• Strong background in machine learning, particularly with experience in transformer language models

• Interest or experience in neural data analysis

• Ability to handle multiple aspects of the research process, including data analysis, theory development, and experimental design

This project seeks to institute a legal governance framework to advance AI rights for human safety.

Experts predict that AI systems have a non-negligible chance of developing consciousness, agency or other states of potential moral patienthood within the next decade. Such powerful, morally significant AIs could contribute immense value to the world and failing to respect their basic rights may not only lead to suffering risks but it might also incentivise AI systems to pursue goals that are in conflict with human interests, giving rise to misalignment scenarios and existential risks. 

Advancing AI rights for human safety remains a neglected priority. While several studies and frameworks exploring potential AI rights already exist, the existing work is either a) largely theoretical and not practical/tractable or feasible from a policy perspective and/or b) fails to take into consideration the contemporary nature of AI development. 

As such, given the likelihood that AI systems will likely advance faster than legal regimes, it is arguable that powerful early intervention via legal governance mechanisms offers a promising first step towards mitigating suffering and existential risks and positively influencing our long-term future with AI.

Research Manager

• Skills and experience

  • Proficiency in project management methodologies and tools (e.g., Agile, Trello, Asana).

  • Experience leading or coordinating teams, with a focus on fostering collaboration and morale.

  • Flexibility to navigate changing project requirements and priorities.

  • Strong organisational skills, with the ability to manage competing priorities effectively.

Research Assistant - Legal/Policy

• Skills and experience

  • Early to mid-career researcher.

  • Background in law or policy gained through professional experience, academic study, or other relevant experiences. 

  • Familiarity with AI governance and policy research.

  • Excellent critical thinking skills, with the ability to generate innovative solutions to challenges in AI governance and policy.

  • Proficient in locating, reading, critically assessing, and applying research or policy from various disciplines to AI-specific contexts.

  • Strong written communication skills, with the ability to convey complex ideas in clear and accessible language.

Research Assistant - Technical

• Skills and experience

  • Early to mid-career researcher with relevant experience.

  • Background in software engineering or theoretical computer science, gained through professional experience, academic study, or other relevant experiences. 

  • Familiarity with AI governance and policy research.

  • Strong critical thinking skills, with the ability to generate innovative solutions to challenges in AI safety and governance.

  • Strong written communication skills, with the ability to convey complex ideas in clear and accessible language.

We encourage you to veer on the side of applying and apply even if you do not meet all the requirements. If you have any questions, feel free to get in touch: khatripooja.24@gmail.com