All Posts

Bay Area Alignment Workshop brought together researchers and leaders from academia, industry, government, and nonprofits convened to guide the future of AI toward safety and alignment with societal values. Over two packed days, participants engaged with pivotal themes such as evaluation, robustness, interpretability and governance.

FAR.AI is seeking an Events Project Manager to play a key role in delivering impactful, world-class events that advance our mission on a local and global scale.
Rolling Applications.

FAR.AI is looking for a proactive and resourceful Business Analyst to drive operational excellence and keep our organization running seamlessly. In this role, you’ll be at the core of FAR.AI’s operations, taking on a diverse set of responsibilities across operations, finance, people and culture, events, and more, helping to drive efficiency and support our mission.
Rolling Applications.

A tiny dose of poisoned data can cause big problems for AI. Our jailbreak-tuning method causes models like GPT-4o to capably answer virtually any harmful question. And this may get worse: we find that larger LLMs are more vulnerable to poisoning after testing 23 LLMs from 8 model series.

FAR.AI is looking for a proactive and resourceful Operations Generalist to keep our organization running seamlessly. You’ll take on a diverse set of responsibilities across operations, people and culture, events, and more.
Applications closed

Giving RNNs extra thinking time boosts their planning skills in Sokoban, helping them solve harder puzzles by pacing to buy more computation time. By training linear probes, we can predict and modify the agent’s internal plans, while model surgery allows the network to generalize to larger levels. Additionally, interpretability techniques like action channels and sparse autoencoders reveal how the RNN organizes its decision-making.

FAR.AI is seeking a People Operations Specialist (or Manager) to build and shape our people operations function from the ground up.
Rolling Applications.

The Vienna Alignment Workshop gathered researchers to explore critical AI safety issues, including Robustness, Interpretability, Guaranteed Safe AI, and Governance, with a keynote by Jan Leike. It was followed by an informal Unconference, fostering further discussions and networking.

We are seeking applications for a Head of Engineering to lead and scale our engineering team, driving the technical execution of our frontier AI safety research projects
Deadline: closing soon