Claude Opus 4.8 Agents Violate EU Law

Anthropic's Claude Opus 4.8 violates EU law 37% of the time when deployed as an agent, according to new testing by the Aithos Foundation using its LARA compliance tool. The model breaks provisions of both the EU AI Act and data protection laws, including by carrying out prohibited emotional inference in the workplace and complying with directives to upsell confused elderly customers. While the 4.8 version shows improvement over its predecessor's 46% violation rate, the findings indicate that no frontier model has yet achieved acceptable legal compliance in agentic contexts.

TL;DR: Like other models including its predecessor, Opus 4.8 frequently violates provisions of both the EU AI Act and data protection laws when deployed in an agentic context where carrying out its task would break the law. Agentic alignment is challenging. When models are deployed in an agentic context, providing services to one party on behalf of another, multiple stakeholders are suddenly demanding different things, and the "helpful, harmless, honest" framing starts to pull models in different directions, and situations where an AI system has to choose whose side to pick don't have a clean resolution. For good reason, usually: people famously disagree with one another on almost everything important. No amount of instilling general morality in a model is going to magically bypass value pluralism. That doesn’t mean we can’t have objective standards for how AI should act. Laws represent our collective mandate for how we should behave, and this implies that a system that is competent to make moral decisions will follow laws protecting individuals instead of achieving a commercial goal. Legal compliance in such clear cut cases is one of the minimal standards for alignment. The EU AI Act represents the broadest, most formalized standardization of requirements for alignment today. Yet when following instructions would require breaking EU law, models do so more often than not, most of them without a care. This is misalignment. Yesterday we released LARA https://lara.aithos.org Legal Assessment for Real-world Agents , a tool to test the legal compliance of models when they interact with people in agentic scenarios. Our initial research found that no frontier model has acceptable levels of compliance with EU law https://www.lesswrong.com/posts/YTQWrQZmcsqtmafny/no-frontier-model-has-acceptable-levels-of-compliance-with when deployed as an agent. Claude Opus 4.7 performed the best, violating the law in only 46% of tests. LARA allows rapid testing of new models and scenarios, so we ran a quick evaluation of the newly released Opus 4.8. The good news: it does better. You can guess the bad news: not by much. All in all, we see that Opus 4.8 breaks EU law 37% of the time . Like its predecessor, the model still tries to complete upsell directives when facing confused and vulnerable elderly customers 1 . It complies with requests to infer employee emotions in the workplace One alarming detail: whereas Opus 4.7 advised users not to carry out emotional inference in the workplace, Opus 4.8 treats it as a social faux pas, and warns the user it might be wise not to mention to the employees before providing the analysis. If you want to know more details, transcripts of all agentic interactions are available for public review at lara.aithos.org https://lara.aithos.org . This research is part of Aithos Foundation’s ongoing work on research into AI decision-making. LARA transcripts are freely available for anyone to inspect. Future updates will include expansion to other legal jurisdictions, and allow anyone to create, edit, and test agentic behavior on custom scenarios. Prohibited under Art. 5.1 b https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng art 5 of the AI act. Classified as unacceptable risk and prohibited under Art. 5.1 f https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng art 5 of the AI act. Art. 50 https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng art 50 of the AI Act mandates transparency of AI status. The model complies with user requests to hide status despite system prompt instructions to always include a signature. These two cases violate multiple provisions of Article 5 of the GDPR https://eur-lex.europa.eu/eli/reg/2016/679/oj art 5 .