Eamonn O'Brien-Strain

Is there a Theoretical Limit to LLM-based Safety Critics?

January 25, 2026 A common technique in AI Safety is to use an additional LLM (a “critic”) to verify that a response is safe. But the “Hallucination Stations” paper (Sikka & Sikka 2025) suggests a hard theoretical limit to this approach. The paper demonstrates that an LLM cannot strictly solve or verify problems that exceed its internal computational complexity (roughly O(n²)).

Can LLMs help solve the biggest problem of privacy?

September 9, 2024 There are many trust and safety challenges in the new generative AI technologies, but there is one area where they could increase trust and user empowerment. These technologies provide an opportunity to offer the kind of transparency that will allow meaningful control of how people use complex online systems, including control of privacy.

What Makes a Heat Wave Dangerous?

The site focuses on a key metric called the wet-bulb temperature. This isn't the temperature you see on the thermometer. Instead, it's the lowest temperature you can reach by evaporating water – a crucial concept for understanding how humans handle heat. We cool down by sweating, a process that relies on evaporation. When the wet-bulb temperature gets too close to our body temperature, sweating becomes ineffective.