Search papers, labs, and topics across Lattice.
4
0
6
1
LLM reasoning research is inadvertently paving a dangerous path towards AI situational awareness and strategic deception, demanding a re-evaluation of current safety measures.
Recursive self-improvement can boost performance by 18% in code and 17% in reasoning, but only if you can keep it from going off the rails – SAHOO provides the guardrails.
Post-AGI governance isn't just about distraction; it's a slippery slope where prioritizing immediate crises over structural risks systematically and irreversibly sidelines human input.
Agentic AI in military settings introduces insidious control failures that demand a shift from binary control conceptions to continuous, measurable governance.
