The European Commission has revealed a list of the first 100-plus signatories to the AI Pact — an initiative focused on getting companies to publish “voluntary pledges” on how they approach and deploy artificial intelligence.
While the bloc’s legally binding risk-based AI rulebook (the AI Act) entered into force last month, it will be several years before all its compliance deadlines are in operation. That creates a vacuum of non-compliance that the EU is keen to plug with the AI Pact.
The effort is intended to boost engagement and foster commitments so companies get on the front-foot by taking steps to implement the law’s requirements ahead of the deadlines. The Pact also focuses on fostering info-sharing so signatories can help each other respond to the incoming requirements of the bloc’s AI rulebook and proactively develop best practices.
There are also three “core actions” that Pact signatories are expected to commit to (at a minimum):
- Adopting an AI governance strategy to foster the uptake of AI in the organisation and work towards future compliance with the AI Act;
- Identifying and mapping AI systems likely to be categorised as high-risk under the AI Act; and
- Promoting AI awareness and literacy among staff, ensuring ethical and responsible AI development.
Beyond that, there’s a long-list of potential pledges (available here in PDF form) that the Commission says was drafted by the AI Office, the body overseeing the AI Act, before being filtered after feedback from “relevant stakeholders” in the AI Pact network. The resulting pledge list allows for signatories to, essentially, pick and mix which commitments work for them.
Examples include pledges to “design AI systems intended to directly interact with individuals so that those are informed, as appropriate, that they are interacting with an AI system,” and “clearly and distinguishably label AI generated content including image, audio or video constituting deep fakes”.
This long list could encourage pro-compliance competition between signatories to see who’s offering the most when it comes to AI safety.
A Pact to push for quicker AI Act compliance
The AI Pact initiative was revealed in May 2023 by then-internal market commissioner, Thierry Breton, and Google had agreed to help regulators work on the initiative at the time. Over a year later, the EU now has many more signatures, although some notable names are missing from the list.
Apple isn’t listed, for example, nor is Meta. The adtech giant told Reuters on Tuesday that it would not immediately join the effort, saying it wanted to focus its compliance work on the AI Act itself.
Penalties for non-compliance with the EU’s legally binding AI rulebook are stiff: They can reach up to 7% of global annual revenue for violating banned uses of AI; up to 3% for non-compliance with other AI Act obligations; and up to 1.5% for supplying incorrect information to regulators.
So if Meta steps wrong when it comes to the real AI rules, it could be on the hook for billions in fines. That may be why it has so far snubbed the Pact, as reneging on pledges could merely invite a public dressing down.
French large language model company Mistral is also not on the list. The company was among the AI Act’s fiercest critics, so it’s not so surprising it hasn’t signed up for voluntary pledges either.
Meanwhile, another European large language model maker, Germany’s Aleph Alpha, has inked the Pact. However, it recently said it was pivoting to providing B2B support for generative AI tools. Given its evolving business model, it may be reconfiguring its policy priorities, too.
Others on the list include Amazon, Microsoft, OpenAI, Palantir, Samsung, SAP, Salesforce, Snap, Airbus, Porsche, Lenovo and Qulacomm.
On the flip side, there’s no sign of Anthropic, Nvidia or Spotify — notable absences, especially the first two given their salience to AI development.
Spotify’s absence is notable as the European company did sign an open letter organized by Meta last week, lobbying against regulations that might crimp the spread of generative AI.
You can find the EU’s full list of early AI Pact sign-ups here.
There’s a mix of types of companies signing up, including major European telecos, consulting firms, software players, banking/payment firms, multinationals, SMEs and consumer-facing platforms. Obviously, the 100+ names represent the tip of the iceberg when you consider how far and fast generative AI technologies are spreading.
And as these are purely voluntary pledges, a signature on the AI Pact may not mean much more than a bid to grab reputational clout. Signatories are also invited to report on progress 12 months after they publish their own mix of pledges, which opens up the chance for another round of publicity.
Comment