Research / Sources
Discussion and research on AI alignment. alignmentforum.org
Argues that high-reliability engineering practices like detailed specs and staged testing cannot straightforwardly transfer to AGI, since AGI behaviour is open-ended and out-of-distribution, so alignment needs deeper understanding.
A podcast interview with DeepMind's Samuel Albanie on the company's technical AGI safety paper, covering its core assumptions, misuse and misalignment threats, and planned mitigations such as amplified oversight.
Sketches a structured safety case arguing an internally deployed LLM agent won't exfiltrate data, based on a red-team control evaluation of monitoring protocols and extrapolation to deployment.
Argues frontier AI companies are unlikely to produce high-assurance safety cases for existentially dangerous AI within short timelines, due to security, scheming-detection, and acceleration difficulties, and unlikely to pause unilaterally.