AI Safety Self-Study
⭐ 📣 📰 📣 ⭐ Newsflash! I just finished my BlueDot Impact Technical AI Safety Project! Take a look!
🎉 🥳 Accepted Applications 🥳 🎉 Link to heading
| Date Applied | Program Name | Program Dates | Notes |
|---|---|---|---|
| 2026-05-22 | SPAR Demo Day | 2026-05-23 | |
| 2026-04-27 | Alex Bores for Congress Fellowship | 2026 | |
| 2026-04-20 | BDI Rapid Grant for Tech. AI Project | 2026 | $200 |
| 2026-03-15 | EA Global London 2026 | 29 - 31 May 2026 | |
| 2026-03-15 | BlueDot Impact Technical AI Project | 13 April - 21 May 2026 | Project |
| 2026-03-15 | BlueDot Impact Technical AI Safety | 6 - 11 April 2026 | |
| 2026-02-24 | 80,000 Hours Career Consultation | 18 March 2026 | |
| 2026-02-23 | BlueDot Impact AGI Strategy Course | 9-13 March 2026 |
📆 💼 Upcoming Events 💼 📆 Link to heading
| Date | Event |
|---|---|
| 2026-05-26 | AI Safety Evals: Frontier Models are Capable of In-context Scheming |
| 2026-06-02 | AI Safety Evals: Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs |
| 2026-06-04 | AI Governance Club: Scheming in the Wild: Detecting Real-World AI Scheming Incidents with Open-Source Intelligence |
| 2026-06-11 | AI Governance Club: Peer-Preservation in Frontier Models |
📆 💼 Past Events 💼 📆 Link to heading
| Date | Event |
|---|---|
| 2026-05-21 | AI Governance Club: Radical Optionality: Governing Transformative AI Under Uncertainty |
| 2026-05-14 | AI Governance Club: Regulating AI Agents |
| 2026-05-13 | Compute & Control: The Physical & Policy Foundations of AI Governance |
| 2026-05-07 | AI Governance Club: Some Simple Economics of AGI |
| 2026-04-30 | AI Governance Club: Mythos vs. Reality: Aligning AI Governance with Cyber-Resilience |
| 2026-04-16 | AI Safety Poland: Open-Source Intelligence for AI Risk Governance" |
| 2026-04-16 | “AI Governance Club: Low-Resource Languages Jailbreak GPT-4 |
| 2026-04-15 | “What’s up with Mythos?” |
| 2026-04-01 | “Did an LLM Write This? And other questions from the convergence of AI and national security.” |
| 2026-03-11 | What will mobilise the public to act on AI? |
📚 Courses 📚 Link to heading
Various courses and programs that I’ve been using to educate myself about AI technical safety and policy, governance and legislation.
Completed
- Technical AI Project (BlueDot Impact) (Waiting for certificate)
- Ethics in AI and Data Science (Linux Foundation EdX)
- U.S. Public Policy (HarvardX)
- Technical AI Safety Course (BlueDot Impact)
(hover to see cert)
- AGI Strategy Course (BlueDot Impact)
(hover to see cert)
- Future of AI Course (BlueDot Impact)
(hover to see cert)
- AGI Safety Short Course (Google DeepMind)
- Neural Networks Foundational Review (3Blue1Brown)
- Linear Algebra Foundational Review (3Blue1Brown)
In Progress
- Differential Equations Foundational Review (3Blue1Brown)
- Python Foundational Review (MIT OpenCourseware)
Future
- Frontier AI Governance (BlueDot Impact)1
- American Government (HarvardX)
- U.S. Political Institutions (HarvardX)
- Citizen Politics in America (HarvardX)
- Governance in the European Union (KU Leuven)
- AI Safety (Harvard University/Boaz Barak)
- Game Theory I (Stanford EdX)
- Game Theory II (Stanford EdX)
- Intro to AI (HarvardX)
- Intro to AI Alignment (Stanford University)
- AT Safety Atlas
Last updated: 22 May 2026
-
These are programs that I need to apply to. There’s no guarantee that I’ll be accepted. ↩︎