You have to be signed in to use this resource.
Advanced AI evaluations of LLM
Resource details
Akeypart of our work at the AISafety Institute (AISI) involves periodically evaluating advanced AI systems to assess the potential harm they could cause. In this post, we present results from our recent evaluations of five large language models (LLMs)thatarealready usedby the public.
This resource maps to capability ID 6.6.0.1.4.68of domain 6 of the Artificial Intelligence (AI) and Digital Healthcare Technologies Capability Framework
| Contributed by: | Artificial intelligence beyond the basics |
| Authored by: |
|
| Licence: | Creative commons: Attribution-NonCommercial 4.0 International More information on licences |
| First contributed: | 19 September 2024 |
| Audience access level: | Full user |
Share this resource
Report an issue with this resource
You may report a resource, for example, if there is an issue with copyright infringement, breach of personal data, factual inaccuracies, typing errors or safety concerns. The type of issue will determine whether the resource is immediately removed from the platform or if the contributor is asked to make amendments. You can report a resource from the resource information page or by contacting the Learning Hub support team.
You can contact the Learning Hub support team by completing the support form or if you have a general enquiry you can email enquiries@learninghub.nhs.uk.