ML4Good UK August 2024

How will the days be spent? 

• Peer-coding sessions following a technical curriculum with mentors.
• Presentations by experts in the field.
• Review and discussion of AI Safety literature.
• Personal career advice and mentorship.
• Discussion groups

We update our program between each camp, to stay up to date with the rapid development of the field of AI.

The program of the last camp was composed of technical content including:

• Implement SGD and other local optimisation algorithms, run remote hyper-parameter searches on a simple architecture
• Implement GPT-2 from scratch
• Implement and run RLHF
• Look at various interpretability techniques on GPT models and the ResNet
• Implement DQN and A2C, two important reinforcement learning algorithms
• Implement adversarial attacks and defences
• Implement an LLM agent

Alongside talks, workshops and group discussions on:

• model evaluations
• AI trends
• forecasting and timelines
• risk models, risk scenarios and classifications
• landscape of solutions
• corporate governance
• international governance

There is also the opportunity to dive more into the topic of your choice during the literature review afternoon and the 2.5-day project at the end of the camp.

These are simply guidelines - anyone is welcome to apply.
‍
This program is aimed at people in the UK and nearby countries.

Despite our focus on machine learning and technical alignment in this course we think that ML4Good is suitable for people who do not plan to do this kind of research long term, but who intend to work on other things where being knowledgeable about ML techniques and AI safety conceptual concepts is useful. If you are someone working in AI Governance and could do with a more technical foundation on which to act for example, this bootcamp may prove useful.

We welcome applications from those who fit a majority of the following criteria. We are looking for people with diverse skillsets; there are many roles in AI safety that could benefit from people with the knowledge provided by this camp, such as roles in communications, governance and policy. If you have some combination of these skills, such as advanced mathematics skills but less programming experience, or lots of experience in communication and less in programming and mathematics, we would like to encourage you to apply.

• You are motivated to work on addressing the societal risks posed by advanced AI systems - ideally, motivated enough to consider making significant career decisions such as transitioning to technical alignment work, setting up a university AI safety group, or founding a project
• You have a programming background and want to learn how to contribute your skills to the field of AI Safety
• You have relatively strong maths skills (e.g. Mathematics level equivalent to at least one year of university education).
• You are skilled at communicating technical concepts to both technical and non-technical audiences and collaborating with people with varying levels of expertise
• You have a high level of proficiency in English
• You can commit to completing our prerequisite material before the bootcamp (we will send this to you upon acceptance). We expect this material to take 10-20 hours. It will include AI safety conceptual readings and may include programming or mathematics preparation depending on your strengths.

Will there be any spare time? There will be periods of leisure and rest during the camp. However, the course is intensive and full-time - don’t plan to do anything else during the camp and we would recommend giving yourself a day off afterwards before returning to full-time work!

What language will the camp be in? All courses, instruction, resources, and conversations will be in English.

What do you mean by AI Safety? By “AI Safety” we mean ensuring that AI doesn’t lead to negative outcomes for sentient beings or the premature disempowerment of humanity. In a recent open letter signed by many deep learning pioneers, it is stated that “mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war.” Avoiding these bad outcomes is a challenge that has to be tackled on a societal level. In this camp, we will focus on technical approaches to building safer AI systems, for example by making their internal processes more interpretable.

I am not sure my level of technical knowledge is sufficient. Please see the prerequisite section above to see what level of technical knowledge we are looking for. If you are unsure, please err on the side of applying and feel free to contact us with any questions. Additionally, before the camp begins we will provide some preparation work.

How much do I need to know about AI Safety to apply? We expect participants to have a solid grasp of why and how an AI could become existentially unsafe for sentient beings and a general overview of proposed solutions. When it comes to theoretical AI Safety topics, we don’t expect an advanced level of knowledge. You will get more value out of the event if you have more familiarity with AI Safety beforehand. We will provide some reading before the camp for those less familiar.

What might an ideal candidate look like? We have particular interest in those who we can support in planning concrete actions towards working on the reduction of AI risks. Examples of promising candidates include:

• You are an undergraduate in a technical subject with an active github account and you would consider setting up an AI Safety Reading Group at your university.
• You are early in your career or are a masters student in a technical field and you are interested in exploring a future career in alignment to reduce risk from advanced AI.
• You are a professional in the field of software engineering or data science and are looking for a way to alter the trajectory of your career towards work on AI Safety. You would be happy contributing engineering talent to open source tooling or helping found a new project.
• You already have prior machine learning experience and are keen to apply your skills to reduce risk from AI and plan to act on this by e.g. changing jobs, or planning your career, or would be willing to join early stage projects.
• You have experience communicating technical topics clearly through writing posts for technical and non-technical audiences distilling problems and their solutions. You would be interested in working with technical people to communicate their ideas or on developing government policy.