Liability for AI Errors

This week there was an article that speculated that doctors in the UK could be liable for errors made by AI tools unless rules are changed. The argument is that AI tools should be treated as products, which isn't necessarily the case right now. Right now doctors may face all the liability instead of AI tool makers having some responsibility. From my reading, this doesn't appear to say that doctors aren't still accountable for mistakes, but they aren't wholly accountable. The Medical Protection Society wants the technology vendors to bear some responsibility.

I have to admit I'm torn here. If doctors are using tools, they should be sure the tools work well and they agree with the recommendations or results. However, I think AI changes things somewhat. If I read a medical device, say one that analyzes blood, I expect that the results are deterministic and accurate. If they aren't, how could I, as a doctor, know that. The companies the built (or maintain) the device would be culpable for errors.

Using AI assistance, however, is a little different. This is a non-deterministic interpretation of data. In the same situation, if an AI were to interpret blood results and summarize them, perhaps failing to point out a deviation of a value and this impacted patient care, is the AI responsible? The doctor for not realizing there is an issue? Joint responsibility?

I think it's unclear. I'm not 100% sure how I feel here, and I lean towards both being liable. If someone is training an AI model to help with medicine, then they ought to bear (and feel) accountable for results.

This seems different than software engineering to me. In medicine we have humans overloaded and AI is supposed to help, but has to be responsible. I don't think the stakes are as high in producing software. It's an arbitrary decision to say we need to get xx work done with yy resources. AI can help, perhaps amplify the abilities of people to produce code, but the people still have to verify the AI results. Any time pressure is a decision we make, not one brought on by medical issues.

Perhaps this seems hypocritical, and I will admin I'm not 100% sure how I feel, but I'm more concerned with AI technology bearing responsibility in healthcare than software. Do you feel the same way? Or perhaps in either case the AI is just a tool? Let me know what you think,

Steve Jones - SSC Editor

Join the debate, and respond to the editorial on the forums

Learn how to call locally hosted Ollama embedding ...

Both SQL Server and PostgreSQL are moving fast int...

Third part in my Ai series with databases. When building AI solutions within the database realm the first thing that people do is a straightforward concept, connect the LLM... The...

Data lakes had a reputation problem. The promise was compelling: dump all your data into cheap object storage—S3, GCS, Azure Blob—and query it whenever you need. The reality was a mess of stale partitions, schema drift, and silent data corruption caused by unsafe concurrent writes. Engineers knew the risks and worked around them rather than fixing them.

An excited enterprise client came back from a conference where Snowflake delighted them with AI demos and semantic views built on Open Semantic Interchange (OSI) standard. Snowflake even went...

AWS announces the availability of Claude Fable 5 on Amazon Bedrock and Claude Platform on AWS. Claude Fable 5 delivers Mythos-level capabilities available to all customers, with strong safeguards...

There are some serious angles to this topic, and I have had conversations with people at conferences who are doing a remigration from the cloud, but it feels like the exception not the rule. It is interesting to think about.

This month we have a very interesting invitation f...

For T-SQL Tuesday #199, Koen Verbeeck posed an exc...

This month’s T-SQL Tuesday is hosted by Koen Ver...

Cloud migrations fail not from incompetence, but from unknown unknowns. Discover the most common challenges teams face in 2026 — and how to plan for what you don't yet...

The conference has passed, and what a great couple of days it was. During the lead up to the conference, we had a few minor snafus, like some ticketing...

In this blog post, I’ll show you how to retrieve all Intune devices and display key attributes such as the owner, device model, and other important information.Just follow the...

In a data warehouse, one important concept is to retain historical data. This data is typically not available in operational systems. One approach in data warehouses is the use of Slowly Changing Dimensions (SCDs). What are the SCD options and are there any new approaches?

In the first post, I introduced contained availabi...

A reader says to me yesterday very directly during a linkedin exchange: "All of the data leadership is focused on Fabric." Nine words. He is right and...

Normally when I tell people about SQL Server’s optimistic concurrency isolation levels, Read Committed Snapshot Isolation (RCSI) and Snapshot Isolation (SI), I have to give them a little speech...

PostgreSQL's `deadlock_timeout` controls how often deadlocks are searched for, not how long a deadlock will be tolerated.

Introduction These are my SQL Server Diagnostic In...

Anthropic launched Claude Fable 5 for broad use wi...

A client asked me last week, plainly: 'Why are we still paying for SQL Server when Postgres is free?' It is a fair question, and it is being asked...

It is Patch Tuesday again. Microsoft shipped around 200 fixes today and three publicly disclosed zero-days, and not one of them is in SQL Server. Just like May, the...

You have a customer list. Somewhere in it, 'Globex...

While wandering around the documentation looking for some Question of the Day topics, I learned something new about the money data type. This post discusses what I learned. Another... The...

There have been a lot of posts on LinkedIn of late about the “logical execution order” of a query that all really miss some really big points. I was...

Dynamic SQL vs OR Clauses in SQL Server Chapters 00:00:00 – Introduction 00:02:15 – Dynamic SQL for Query Tuning 00:05:34 – Case Expressions and Join Clauses 00:08:45 – Performance...

Learn 10 everyday AI prompts for ChatGPT, Gemini, ...

AI data center growth is turning power access into...

Compare NotebookLM with Notion, Obsidian, Recall, Atlas, and Open Notebook to find the best AI research and knowledge management tool for your workflow.

OpenAI has confidentially filed a draft S-1 with the SEC, opening the door to an IPO as Anthropic and other AI firms eye public markets.

Imagine tuning in to the opening kickoff of a World Cup match and seeing a player intentionally send the ball all the way down the pitch and right out...