Resolution has formed an Agent Foundations research team.
The team will develop theory to understand minds and improve AI reasoning.
Members include veteran AI safety researchers from MIRI.
What happened
Resolution, an AI research organization, has announced a new Agent Foundations team. The initial members are Jeremy Gillen, Abram Demski, Sam Eisenstat, Scott Garrabrant, and Kaarel Hänni.
Why it matters
The team will pursue foundational theory for understanding minds, aiming to address a lack of precise reasoning about AI behavior. This work is seen as necessary before building superintelligent systems that enhance human agency rather than pose risks.
What to watch
Resolution plans to recruit additional experienced researchers soon, and later intends to hire interns and junior researchers to expand the team.
Ask the AI about this article →
The new team at Resolution continues a line of research that MIRI's Agent Foundations team pioneered, focusing on the theoretical underpinnings of AI behavior. This effort is motivated by a perceived gap: while most engineering fields can reason about unseen scenarios, AI lacks that capability. The team aims to fill that gap by developing theory that allows for more precise questions about how advanced AI might behave after learning and self-modification. The hiring plans suggest an intention to grow this research area significantly. As they expand, the team's work could provide the groundwork for designing AI systems that align with human goals, a goal that some view as increasingly important as AI capabilities advance.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Infosys, a founding partner of CrowdStrike's Project QuiltWorks, is bringing enterprise context to CrowdStrike…
Cisco has announced a target to have zero engineers writing code by the end of October
OpenAI's latest model, Astra, can do more thinking off the scratchpad, according to Transformer
Cecilia Ziniti, former general counsel at Replit, left the company in November 2023 and founded GC AI, an AI s…
Governments and companies outside the US and China are building local AI models to avoid relying on foreign sy…
Users report Instagram's "AI Content" label is wrongly appearing on images they edited with tools like Canva's…
