GCHQ spy chiefs warn Microsoft’s ChatGPT and other AI chatbots pose a security risk – as City law firm bans workers from using it in case client data is leaked
Spy organisation GCHQ says Artificial Intelligence powered chatbots like ChatGPT are emerging security threats.
In a blog post yesterday the National Cyber Security Centre says companies operating the technology – like Microsoft and Google – are able to read questions typed into the chatbots.
The centre admits that with any emerging technology, there is always concern around how secure it is.
And it advises users not to include sensitive information in queries or anything that could lead to issues if everyone saw them.
The blog points out: ‘The query be visible to the organisation providing the LLM (so in the case of ChatGPT, to OpenAI).
‘Those queries are stored and will almost certainly be used for developing the LLM service or model at some point.
The Telegraph reports City firm Mishcon de Reya has banned its lawyers from typing client data into ChatGPT over security fears, as has Accenture.
It was revealed on Monday that ChatGPT will soon be able to do much more than send human-like text messages.
In September, rival tech giant Meta unveiled its own AI system that generates videos from text prompts. ‘Make-A-Video’ was trained on images with captions to help it learn about the world and how it is described, and unlabeled videos to determine how the world moves
A Microsoft executive has revealed that the next version – set to be released this week – will be able to turn text prompts into unique videos.
The tech giant has invested heavily in ChatGPT, and has already unveiled a host of new products which incorporate it as an AI assistant, like search engine Bing.
But this updated version, dubbed GPT-4 and tipped to launch on Thursday, will have ‘multimodal models’, according to Microsoft Germany CTO Andreas Braun.
This means that it will be able to generate content in multiple formats, like audio clips, images and video clips, from a text prompt.
ChatGPT is a large language model that has been trained on a massive amount of text data, allowing it to generate human-like text responses to a given prompt.