LLM safeguards are easily bypassed, UK government study finds
Research conducted by the UK’s AI Safety Institute (AISI) found that AI chatbots can be easily coerced into producing harmful,…
Just 2% of AI research is looking at safety, says Georgetown University study
We hear a lot about AI safety, but does that mean it’s heavily featured in research? A new study from…
WMDP measures and reduces LLM malicious use with unlearning
Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous…
The battle of the ‘AI godfathers’ – is AI risky or not?!
AI is risky, right? That’s what we’ve all been told this last year. But not everyone agrees, including some top…
Round up of day two of the UK’s AI Safety Summit
On day two of the AI Safety Summit, UK Prime Minister Rishi Sunak attempted to drive home that AI developers…
Rounding up day one of the UK’s AI Safety Summit
The UK’s AI Safety Summit kickstarted today, seeing politicians, tech bosses, researchers, and members of civil advocacy groups descend upon…
China to attend the UK’s AI Summit at Bletchley Park
Despite recent controversies surrounding espionage allegations, China is set to participate in the upcoming UK AI Safety Summit at Bletchley…
Bletchley Park set to host the UK’s Global AI Safety Summit in November
The UK has announced the dates for a high-profile summit focused on AI safety, which will take place on November…