🧩 Philosophy 15h ago · Alec Harris

How much will conceptual reasoning training transfer to ML research abilities?

Less Wrong
View Channel →
Source ↗ 👁 0 💬 0
Recently the Conceptual Reasoning Capabilities (CRC) team at Redwood released a post arguing that we should accelerate AI’s conceptual reasoning abilities. This post was very controversial. In particular, people are worried that improving AI’s conceptual reasoning abilities will accelerate both their ability to do ML research and the capabilities they need for takeover.I am going to address just one chunk of this controversy: how much does training conceptual reasoning on AI safety questions tra

Comments (0)

Sign in to join the discussion

More Like This

📰
Corrigibility should not be the only target
LessWrong · 5h ago
📰
Dialogue with Richard Ngo on Alignment, Hierarchical Integrity of Human-AI systems, Revolution, and Power
LessWrong · 7h ago
How to Run Better Research With Agent Fleets
LessWrong · 10h ago
GPT-6.1 Sol is One Sentence Away From Collaborating: Other Models Need More Help
LessWrong · 12h ago
University of Cape Town vs. Free Speech
Daily Nous · 13h ago
📰
Herbert Spencer
Stanford Encyclopedia of Philosophy · 17h ago