The US, EU, UK, Israel, and six other nations have signed the first-ever legally binding international AI treaty during a Council of Europe (COE) summit in Vilnius on Thursday.
The document was initially passed in May, having been negotiated between the Council of Europe's 46 members (including all EU countries) and eleven external nations.
Having witnessed a series voluntary agreements in the UK and South Korea, the shift to legally binding commitments is a welcome step forward in the bid to appease growing concerns over the dangers AI may pose upon humanity. Whilst tech regulation is not without its critics, and questions remain over ensuring effective implementation, the treaty is nonetheless a landmark milestone.
Following pressure from countries such as the US, the COE's public sector-focused convention is unfortunately filled with caveats and exemptions. With private companies mostly excluded and the use of ambiguous language likely to hinder enforcement, the AI treaty is far from what many had hoped and expected.
AI hysteria has led to a demand for regulation far too early in the technology's development. Whilst AI's capabilities may certainly one day reach a level of sophistication or danger that requires intervention, evidence from Europe shows that for now this will likely only stifle research and innovation out of fear of an unlikely existential crisis.