Archive - BlueDot Impact

Is the Frontier AI Governance course right for you?

3 questions to help you decide.

Apr 5 • Joshua Landes

March 2026

Quitting FinTech for AI Safety — Milos Borenovic

Milos is the Chief Product Officer and Parternships Lead at Lucid Computing

Mar 25 • Harrison Wood

High-Stakes Activation Probes on Indonesian

This project was submitted by Ivan Wiryadi. It was an Outstanding Submmission for the Technical AI Safety Project Sprint (Jan 2026). Participants worked…

Mar 25 • Ivan

Interpreting Latent Reasoning in the Depth-Recurrent Transformer

This project was submitted by Tristan von Busch. It was a Top Submission for the “Technical AI Safety Project” prize (Jan 2026). Participants worked on…

Mar 24

Rapid Small Grants for the BlueDot Technical AI Safety Project Sprint

Small grants for BlueDot participants to build their portfolio

Mar 17 • Sam Dower

Why you should vibe-code your AI safety research sprint project

Your research hours are limited. Don't spend them coding.

Mar 13 • Sam Dower

aegish: Using LLMs To Block Malicious Shell Commands Before Execution [>] Email

This project was submitted by Guido Bergman. It was an Outstanding Submmission for the Technical AI Safety Project Sprint (Jan 2026). Participants…

Mar 11 • Guido Bergman

Measuring Moral Sycophancy Is Harder Than It Looks: Auditing and Extending the ELEPHANT Benchmark

This project was submitted by Alexis Wang. It was an Outstanding Submmission for the Technical AI Safety Project Sprint (Jan 2026). Participants worked…

Mar 11 • Alexis

Quaver | Lovable for Evals and Benchmarks

What I Learned Building 2 AI Benchmarks From Scratch (And Why I Automated the Third)

Mar 11 • Faw

Reproducing FAR.AI's Study on LLMs' Persuasion Attempts at Harmful Topics

This project was submitted by Mutalib Begmuratov. It was an Outstanding Submmission for the Technical AI Safety Project Sprint (Jan 2026). Participants…

Mar 11 • Mutalib Begmuratov

MANTA: Evaluating Nonhuman Welfare Reasoning in AI Models

Evaluating Nonhuman Welfare Reasoning in Frontier AI Models

Mar 11 • Allen Lu

Multilingual Safety Alignment Is Not “Just Translate the Prompt”

For people fine-tuning reasoning LLMs for non-English users

Mar 11 • Zahraa Al Sahili

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts