Research conducted by the UK’s AI Safety Institute (AISI) found that AI chatbots can be easily coerced into producing harmful, illegal, or explicit responses. The study probes five large language models (LLMs) already in…
By Sam Jeans · 2 min read
We hear a lot about AI safety, but does that mean it’s heavily featured in research? A new study from Georgetown University’s Emerging Technology Observatory suggests…
By Sam Jeans · 3 min read
Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous data. There has been much debate…
By Eugene van der Watt · 2 min read
AI is risky, right? That’s what we’ve all been told this last year. But not everyone agrees, including some top researchers. X has been ablaze with…
By Sam Jeans · 11 min read
On day two of the AI Safety Summit, UK Prime Minister Rishi Sunak attempted to drive home that AI developers will permit government evaluation of tools…
By Sam Jeans · 5 min read
The UK’s AI Safety Summit kickstarted today, seeing politicians, tech bosses, researchers, and members of civil advocacy groups descend upon the historic Bletchley Park. The British…
By Sam Jeans · 4 min read
The UK has announced the dates for a high-profile summit focused on AI safety, which will take place on November 1 and 2 at Bletchley Park,…
By Sam Jeans · 2 min read
