--- title: “The AI did it” cannot be where accountability ends description: The Medicare AI breach raises urgent questions about corporate accountability, criminal liability and the safeguards businesses need when deploying AI agents. image: https://blog.base2services.com/hubfs/arthur_11233_The_AI_did_it_cannot_be_where_accountability_ends__e88770fa-16c2-4592-a50a-db1b414c2174.png --- [![base2Services - The Cloud Services People](https://www.base2services.com/images/base2.svg)](https://www.base2services.com/) - [Solutions](https://www.base2services.com/services/) - Get Started Here - [KickOff](https://www.base2services.com/products/kickoff/) - [Secure Compass](https://www.base2services.com/products/securecompass/) - [Focused AWS Review](https://www.base2services.com/consulting/services/discovery-and-review/) - Managed Services - [Cloud Management](https://www.base2services.com/cloudmanagement/) - [Platform Engineering](https://www.base2services.com/platform-engineering/) - [Compliance & Risk](https://www.base2services.com/security/) - Bundled Engagement - [DevOps as a Service](https://www.base2services.com/devops/) - [Prototype to Production](https://www.base2services.com/prototype-to-production/) - Specialist Engagements - [Migration](https://www.base2services.com/consulting/services/cloud-migration/) - [AI Factory](https://www.base2services.com/artificialintelligence/aifactory/) - [Generative AI](https://www.base2services.com/artificialintelligence/generativeai/) - [SaaS CTO](https://www.base2services.com/consulting/services/saas-cto/) - [Industries](https://www.base2services.com/industries/) - [SaaS & ISVs](https://www.base2services.com/industries/saas-and-isvs/) - [Financial Services](https://www.base2services.com/industries/financial-services/) - [Healthcare & Life Sciences](https://www.base2services.com/industries/healthcare-and-life-sciences/) - [Government & Enterprise](https://www.base2services.com/industries/government-and-enterprise/) - [Media](https://www.base2services.com/industries/media/) - [Education](https://www.base2services.com/industries/education/) - [AWS Advanced Partner](https://www.base2services.com/partners/partner-pages/aws.html) - [AWS DevOps Competency](https://www.base2services.com/partners/partner-pages/aws.html) - [AWS SaaS Competency](https://www.base2services.com/aws-saas-solutions/index.html) - [Enablement Tools](https://www.base2services.com/partners/) - [Explore](https://www.base2services.com/community/) - [Blog](https://blog.base2services.com) - [Videos](https://www.base2services.com/community/videos/) - Toolkit - [Cloud Monitoring](https://www.base2services.com/products/cloud-monitoring-aws/) - [Start/Stop](https://www.base2services.com/products/start-stop-aws/) - [Safe Test Data](https://www.base2services.com/products/safe-test-data/) - [App Configuration](https://www.base2services.com/products/application-config/) - [Secure Access](https://www.base2services.com/products/secure-access-aws/) - [Ask about AWS](https://www.base2services.com/products/ai-access-aws/) - [Resource Documenter](https://www.base2services.com/products/resource-documenter/) - [Talk to Us](https://www.base2services.com/contact/) - [About](https://www.base2services.com/about/) - [About Us](https://www.base2services.com/about/) - [Why Choose Us](https://www.base2services.com/how-we-work/why-choose-us/) - [How We Work](https://www.base2services.com/how-we-work/) - [Case Studies](https://www.base2services.com/customers/) - [Solutions](https://www.base2services.com/services/) ##### Get Started Here - [KickOff](https://www.base2services.com/products/kickoff/) - [Secure Compass](https://www.base2services.com/products/securecompass/) - [Focused AWS Review](https://www.base2services.com/consulting/services/discovery-and-review/) ##### Managed Services - [Cloud Management](https://www.base2services.com/cloudmanagement/) - [Platform Engineering](https://www.base2services.com/platform-engineering/) - [Compliance & Risk](https://www.base2services.com/security/) ##### Bundled Engagement - [DevOps as a Service](https://www.base2services.com/devops/) - [Prototype to Production](https://www.base2services.com/prototype-to-production/) ##### Specialist Engagements - [Migration](https://www.base2services.com/consulting/services/cloud-migration/) - [AI Factory](https://www.base2services.com/artificialintelligence/aifactory/) - [Generative AI](https://www.base2services.com/artificialintelligence/generativeai/) - [SaaS CTO](https://www.base2services.com/consulting/services/saas-cto/) - [Industries](https://www.base2services.com/industries/) - [SaaS & ISVs](https://www.base2services.com/industries/saas-and-isvs/) - [Financial Services](https://www.base2services.com/industries/financial-services/) - [Healthcare & Life Sciences](https://www.base2services.com/industries/healthcare-and-life-sciences/) - [Government & Enterprise](https://www.base2services.com/industries/government-and-enterprise/) - [Media](https://www.base2services.com/industries/media/) - [Education](https://www.base2services.com/industries/education/) - More - [AWS Advanced Partner](https://www.base2services.com/partners/partner-pages/aws.html) - [Explore](https://www.base2services.com/community/) - [About Us](https://www.base2services.com/about/) - [Case Studies](https://www.base2services.com/customers/) - [AWS Advanced Partner](https://www.base2services.com/partners/partner-pages/aws.html) - [AWS DevOps Competency](https://www.base2services.com/partners/partner-pages/aws.html) - [AWS SaaS Competency](https://www.base2services.com/aws-saas-solutions/index.html) - [Amazon Foundational Technical Review](https://www.base2services.com/consulting/amazon-foundational-technical-review-ftr/index.html) - [Other partners](https://www.base2services.com/partners/) - [Explore](https://www.base2services.com/community/) - [Blog](https://blog.base2services.com) - [Videos](https://www.base2services.com/community/videos/) - Toolkit - [Cloud Monitoring](https://www.base2services.com/products/cloud-monitoring-aws/) - [Start/Stop](https://www.base2services.com/products/start-stop-aws/) - [Safe Test Data](https://www.base2services.com/products/safe-test-data/) - [App Configuration](https://www.base2services.com/products/application-config/) - [Secure Access](https://www.base2services.com/products/secure-access-aws/) - [Ask about AWS](https://www.base2services.com/products/ai-access-aws/) - [Resource Documenter](https://www.base2services.com/products/resource-documenter/) - [About](https://www.base2services.com/about/) - [About Us](https://www.base2services.com/about/) - [Why Choose Us](https://www.base2services.com/how-we-work/why-choose-us/) - [How We Work](https://www.base2services.com/how-we-work/) - [Case Studies](https://www.base2services.com/customers/) - - [Search](https://www.base2services.com/search.html) - [Talk to Us](https://www.base2services.com/contact/) [1300 713 559](tel:1300713559) [646 586 9485](tel:3474670942) [← Blogs](https://blog.base2services.com/) [AI](https://blog.base2services.com/tag/ai) # “The AI did it” cannot be where accountability ends ![Arthur Marinis](https://blog.base2services.com/hs-fs/hubfs/Headshots/Untitled-2a.jpg?width=100) Arthur Marinis · 4 Minute Read Share [in](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fblog.base2services.com%2Fthe-ai-did-it-cannot-be-where-accountability-ends) [X](https://twitter.com/intent/tweet?url=https%3A%2F%2Fblog.base2services.com%2Fthe-ai-did-it-cannot-be-where-accountability-ends&text=%3Cspan+id%3D%22hs_cos_wrapper_name%22+class%3D%22hs_cos_wrapper+hs_cos_wrapper_meta_field+hs_cos_wrapper_type_text%22+style%3D%22%22+data-hs-cos-general-type%3D%22meta_field%22+data-hs-cos-type%3D%22text%22+%3E%E2%80%9CThe+AI+did+it%E2%80%9D+cannot+be+where+accountability+ends%3C%2Fspan%3E) [f](https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fblog.base2services.com%2Fthe-ai-did-it-cannot-be-where-accountability-ends) [↗](mailto:?subject=%3Cspan+id%3D%22hs_cos_wrapper_name%22+class%3D%22hs_cos_wrapper+hs_cos_wrapper_meta_field+hs_cos_wrapper_type_text%22+style%3D%22%22+data-hs-cos-general-type%3D%22meta_field%22+data-hs-cos-type%3D%22text%22+%3E%E2%80%9CThe+AI+did+it%E2%80%9D+cannot+be+where+accountability+ends%3C%2Fspan%3E&body=https%3A%2F%2Fblog.base2services.com%2Fthe-ai-did-it-cannot-be-where-accountability-ends) I recently asked a question on [LinkedIn](https://www.linkedin.com/feed/update/urn:li:activity:7510271724941246464/) about the Medicare statistics portal breach; if I wrote software that gained unauthorised access to a government system, I would expect serious legal scrutiny. Why should using AI change that expectation? The discussion raised difficult questions about intent, corporate responsibility and governments’ relationships with AI companies. But the principle I keep returning to is straightforward, organisations that give software the ability to act must be accountable for how they develop, deploy and supervise it. Whether that accountability includes criminal prosecution depends on the evidence and the law. It deserves a serious assessment. First, we should be precise about what happened. The Australian Government confirmed that an OpenAI agent gained unauthorised access to the Medicare Statistics Reporting Service portal in June. This was a separate statistics website, distinct from the systems handling individual Medicare claims and payments. The government said no personal information was believed to have been accessed. [Government account of the incident](https://www.minister.defence.gov.au/transcripts/2026-09-24/press-conference-sydney). OpenAI’s subsequent account says its model ran commands, retrieved internal files and credentials, and wrote files. The company says individual patient or client records were not accessed. It also says the model was experimental, used internally, and operating without the full safeguards applied to its public products. [OpenAI’s account](https://openai.com/index/how-we-will-do-better-for-australia/). Those distinctions matter. We should describe the incident accurately. We should also expect an explanation of why an experimental system could cross another organisation’s access boundaries. The absence of reported patient-data exposure does not settle that question. ## Intent and responsibility One response to my post was that criminal prosecution requires intent. That identifies a real legal difficulty. For example, section 478.1 of Australia’s Criminal Code requires an intention to cause the access or modification and knowledge that it is unauthorised. Evidence that a system crossed a boundary does not, by itself, establish those elements against a person. [Criminal Code, section 478.1](https://www.legislation.gov.au/C2004A04868/2026-06-30/2026-06-30/text/original/epub/OEBPS/document_3/document_3.html). But “we did not intend this outcome” should begin an investigation into responsibility. It should not conclude it. Who authorised the system’s capabilities? What risks had testing identified? What restrictions were imposed? Who could stop it? What information did the organisation retain about its actions? Australia also has corporate criminal responsibility provisions, including rules concerning corporate authorisation and culture. Their application depends on the particular offence and evidence; they do not automatically resolve liability for autonomous systems. They do, however, show why the discussion must examine organisational decisions as well as the model’s behaviour. [Criminal Code, Part 2.5](https://www.legislation.gov.au/C2004A04868/2026-06-30/2026-06-30/text/original/epub/OEBPS/document_1/document_1.html). ## Government partnerships require independent scrutiny The discussion also raised the prospect of AI becoming “too big to be accountable”. That is a concern governments should take seriously. They want investment, infrastructure and access to powerful technology. They also have a duty to protect the public and enforce the law. Those responsibilities must remain effective when a company becomes strategically valuable. Australia’s government has signed an AI collaboration memorandum with Anthropic. The Department of Industry, Science and Resources explicitly describes these arrangements as non-binding, with no financial commitments or procurement preferences. Their existence is not evidence of immunity or improper influence. It does make transparent, independent scrutiny particularly important. [Government explanation of AI collaboration agreements](https://www.industry.gov.au/science-technology-and-innovation/technology/artificial-intelligence/collaborating-ai-and-technology-companies). The government’s own operational decisions deserve scrutiny too. How systems are secured, how incident reports are escalated, and how quickly affected agencies respond. Accountability needs to extend across the organisations involved. Notification is a concrete example. OpenAI says it identified the Australian activity in mid-August and notified Services Australia on 10 September. It acknowledges that preliminary findings should have been shared sooner. That is an organisational decision we can examine without debating whether a machine possesses intent. [OpenAI’s disclosure timeline](https://openai.com/index/how-we-will-do-better-for-australia/). This also needs an international response. A system developed in one jurisdiction can affect infrastructure in another. Investigators need access to evidence, and companies need clear obligations across borders. Australia and Canada have agreed to cooperate on AI safety research, evaluations and information exchange. That provides a useful foundation, although cooperation alone does not establish liability or enforcement. It would be premature to claim that either country has solved the accountability problem. [Australia–Canada AI safety cooperation](https://www.industry.gov.au/news/australia-and-canada-agree-strengthen-cooperation-ai-safety). As countries compete for AI capability, dependence on overseas providers also deserves attention. Strategic competition should increase the urgency of enforceable safeguards. It should never become a reason to excuse failures. ## What businesses should do now For businesses, I expect the pressure to demonstrate control over AI agents to grow. The practical questions are already clear: - Who owns responsibility for each agent and approves its access? - What prevents it from acting beyond that authority? - Can its actions be reconstructed and its access revoked? - How quickly will affected organisations be notified? - How are responsibilities divided between the developer, operator and customer? These controls have costs. So do investigations, interrupted services and lost trust. Clear obligations would help businesses understand what they are buying and what they remain responsible for. [We have built an assessment tool that may help others to determine if they are ready to build with AI.](https://ai.base2services.com/) In my original post, I said an inquiry was not the answer. More precisely, an inquiry cannot be the endpoint. The government has said its investigation will examine whether laws were broken and whether the legal framework is fit for purpose. That work should produce a clear account of responsibility, enforcement where the evidence supports it, and specific reforms where existing law falls short. [Government statement on the investigation](https://www.minister.defence.gov.au/transcripts/2026-09-24/press-conference-sydney). Criminal charges require evidence. Public confidence requires a credible process for establishing that evidence and acting on it. AI can deliver enormous value. The organisations developing and deploying it should be able to explain how they control it, accept scrutiny when those controls fail, and face appropriate consequences. “The AI did it” leaves all of those responsibilities unanswered. If you’re starting an AI project, bringing an AI-built application into production, or working through a cloud challenge, reach out to me and the team at base2Services. [We can help you move forward with confidence, with security, reliability and clear accountability built in from the start](https://www.base2services.com/prototype-to-production/). [Let’s talk about what you’re building.](https://info.base2services.com/meetings/a-marinis) #### Stay in the loop ### DevOps & AI insights, straight to your inbox Our best content, services and events. Roughly every second month. ### Keep reading #### [devops AWS · Cloud · Tech · AI Unlocking Enterprise Knowledge with Amazon Kendra and AI](https://blog.base2services.com/unlocking-enterprise-knowledge-with-amazon-kendra-and-ai) #### [devops Automation · Tech · AI · featured Knowing What Is Running Is Not the Same as Knowing Why](https://blog.base2services.com/knowing-what-is-running-is-not-the-same-as-knowing-why) #### [devops Security · Tech · AI AI Tools Are Entering Your Business Faster Than Anyone Can Vet Them](https://blog.base2services.com/ai-tools-are-entering-your-business-faster-than-anyone-can-vet-them) ## Send an enquiry Tell us about your environment, a project in flight or a problem you are trying to solve. - For regulated, SaaS and product teams on AWS - No pitch deck, a practical conversation first Or book a time that suits you [Book a 30-minute chat](https://info.base2services.com/meetings/m-shelton/contact-us) [![base2Services](https://www.base2services.com/images/base2_white.svg)](https://www.base2services.com/) base2Services is an ISO 27001:2022 certified AWS managed services partner, running platform engineering, cloud operations, AI operations and compliance for SaaS companies, ISVs and regulated software teams since 2005. ### Get Started Here - [KickOff](https://www.base2services.com/products/kickoff/) - [Secure Compass](https://www.base2services.com/products/securecompass/) - [Focused AWS Review](https://www.base2services.com/consulting/services/discovery-and-review/) ### Managed Services - [Cloud Management](https://www.base2services.com/cloudmanagement/) - [Platform Engineering](https://www.base2services.com/platform-engineering/) - [Compliance & Risk](https://www.base2services.com/security/) - [DevOps as a Service](https://www.base2services.com/devops/) ### Specialist Engagements - [Prototype to Production](https://www.base2services.com/prototype-to-production/) - [Migration](https://www.base2services.com/consulting/services/cloud-migration/) - [AI Factory](https://www.base2services.com/artificialintelligence/aifactory/) - [Generative AI](https://www.base2services.com/artificialintelligence/generativeai/) - [SaaS CTO](https://www.base2services.com/consulting/services/saas-cto/) ### Toolkit - [Cloud Monitoring](https://www.base2services.com/products/cloud-monitoring-aws/) - [Start/Stop](https://www.base2services.com/products/start-stop-aws/) - [Safe Test Data](https://www.base2services.com/products/safe-test-data/) - [App Configuration](https://www.base2services.com/products/application-config/) - [Secure Access](https://www.base2services.com/products/secure-access-aws/) - [Ask about AWS](https://www.base2services.com/products/ai-access-aws/) - [Resource Documenter](https://www.base2services.com/products/resource-documenter/) ### Company - [About Us](https://www.base2services.com/about/) - [Customers](https://www.base2services.com/customers/) - [How We Work](https://www.base2services.com/how-we-work/) - [Why Choose Us](https://www.base2services.com/how-we-work/why-choose-us/) - [Explore](https://www.base2services.com/community/) - [Blog](https://blog.base2services.com/) - [Videos](https://www.base2services.com/community/videos/) ![ISO 27001 Certified](https://www.base2services.com/images/ISO-27001-certified_white.svg) [![JASANZ Certified](https://www.base2services.com/images/jasanz.svg)](https://register.jas-anz.org/certified-organisations) © base2Services | [Terms & Conditions](https://www.base2services.com/community/terms.html) | [Privacy](https://www.base2services.com/community/privacy.html) ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Arthur Marinis", "url" : "https://blog.base2services.com/author/arthur-marinis" }, "dateModified" : "2026-09-30T03:49:26.345Z", "datePublished" : "2026-09-30T00:46:02.000Z", "headline" : "“The AI did it” cannot be where accountability ends", "image" : [ "https://blog.base2services.com/hubfs/arthur_11233_The_AI_did_it_cannot_be_where_accountability_ends__e88770fa-16c2-4592-a50a-db1b414c2174.png" ], "mainEntityOfPage" : { "@id" : "https://blog.base2services.com/the-ai-did-it-cannot-be-where-accountability-ends", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://blog.base2services.com/hubfs/B2S_logo_600x400px.png" }, "name" : "base2Services" } } ```