Asking artificial intelligence tools about medical symptoms does not help people make better health decisions than traditional methods such as standard internet searches, according to a new study published in Nature Medicine.

The authors said the findings are significant as more people increasingly turn to AI chatbots for medical guidance, despite limited evidence that these tools offer safer or more effective advice.

How The Study Was Conducted

Researchers led by the University of Oxford Internet Institute worked with a group of doctors to design 10 medical scenarios. These ranged from mild conditions such as a common cold to severe emergencies, including brain bleeding caused by haemorrhage.

The scenarios were first tested without human participants using three large language models: OpenAI’s ChatGPT 4o, Meta’s Llama 3, and Cohere’s Command R+. The models correctly identified the medical condition in 94.9% of cases, but selected the correct next step, such as seeking urgent care, in only 56.3% of cases. The companies did not respond to requests for comment.

Human Use of AI Shows No Advantage

The researchers then recruited 1,298 participants in Britain and asked them to assess symptoms using either AI tools, their own experience, standard internet searches, or the National Health Service website.

When participants made decisions themselves, relevant medical conditions were identified in fewer than 34.5% of cases. The correct course of action was chosen in less than 44.2% of cases, a result no better than participants using traditional information sources.

Poor AI to Human Interaction

Adam Mahdi, a co-author of the study and associate professor at Oxford, said the results highlighted a significant gap between AI’s technical ability and its effectiveness when used by people.

He said the knowledge exists within AI systems, but that information does not consistently translate into useful guidance during real-world interactions, indicating the need for further research.

Where AI and Humans Go Wrong

The team reviewed around 30 interactions in detail and found that users often provided incomplete or inaccurate symptom descriptions. At the same time, AI systems sometimes produced misleading or incorrect responses.

In one example, a patient describing symptoms of a subarachnoid haemorrhage was correctly advised to go to the hospital after mentioning a stiff neck, light sensitivity, and the “worst headache ever.” Another patient describing similar symptoms but using the phrase “terrible headache” was instead advised to lie down in a dark room.

Researchers plan to conduct similar studies across different countries and languages to assess whether AI performance changes over time or in different settings.

The study received support from data company Prolific, the Dieter Schwarz Stiftung, and the UK and US governments.

The Pakistan Telecommunication Authority (PTA) has decided to make calls to toll-free numbers (0800-XXXXX) completely free for mobile phone users across Pakistan.

Under the new arrangement, mobile subscribers will no longer be charged for calling 0800 numbers. Previously, toll-free calls were free only for fixed-line users, while mobile users had to pay applicable charges despite the numbers being labeled as toll-free.

PTA said it took notice of the issue in the interest of consumer protection and user facilitation. The authority initiated steps to address the difference in treatment between mobile and fixed-line subscribers.

As part of the process, PTA held consultations with key stakeholders, including Pakistan Telecommunication Company Limited (PTCL), National Telecommunication Corporation (NTC), local loop operators, and cellular mobile operators. Following these discussions, all stakeholders agreed to extend toll-free calling to mobile users as well.

PTA said the decision reflects its commitment to providing user-friendly and fair telecommunication services. The move is intended to improve access to support services and ensure uniform telecom facilities for consumers across the country.

The Pakistan Digital Authority (PDA) and the DFINITY Foundation have signed a memorandum of understanding to develop sovereign, AI-native digital infrastructure in Pakistan.

The partnership aims to ensure that sensitive national data remains within the country while enabling secure and modern software systems designed for the AI era.

The agreement was signed between PDA and DFINITY in Islamabad and Zurich. Under the partnership, DFINITY will support the creation of a dedicated Pakistan Subnet on its Internet Computer Platform (ICP). The platform functions as a sovereign cloud capable of hosting tamper-resistant software, national-scale applications, and AI-powered systems that can operate independently of foreign cloud infrastructure.

The collaboration also includes plans to pilot a National Messenger application to enable private and verifiable communications. In addition, the partnership will expand access to Caffeine, an AI platform incubated by DFINITY, through the provision of 1,500 Caffeine licenses. These licenses will support application development and capacity-building initiatives across government, education, and entrepreneurship.

DFINITY will also establish a local presence in Pakistan as part of the agreement, aimed at supporting long-term collaboration and ongoing technical engagement.

Dr. Sohail Munir, Chairperson of the Pakistan Digital Authority, said the partnership represents an important step in Pakistan’s digital development. He said investing in sovereign cloud infrastructure and AI-ready platforms will strengthen national resilience, support innovation, and create opportunities for public institutions, students, and entrepreneurs.

Dominic Williams, Chief Scientist and Founder of DFINITY and Caffeine, said Pakistan is adopting a forward-looking approach to digital infrastructure. He said the establishment of a Pakistan Subnet and investment in sovereign, tamper-proof systems will allow the country to develop secure and verifiable software and AI applications aligned with national priorities. He added that the partnership enables Pakistan to build, own, and operate AI and cloud services on its own terms.

Caffeine allows users to build and deploy production-ready applications on the Internet Computer using natural language descriptions, removing the need for traditional engineering teams and complex development processes. The platform is used globally by solo developers, municipalities, banks, and public institutions. Within three months of its launch, users executed more than 3.4 million build prompts.

DFINITY is the creator of the Internet Computer, an open network that provides a serverless sovereign cloud. The platform allows governments, institutions, and individuals to run tamper-proof and resilient software with full ownership and without reliance on foreign cloud providers or access by foreign intelligence agencies.

DFINITY has invested more than $500 million in research and development. Its team includes engineers and researchers formerly associated with Google, Apple, IBM, and Meta. The organization has published more than 1,500 research papers, received over 88,000 citations, and contributed more than 190 patents in areas including distributed systems, cryptography, and advanced computing.

The Pakistan Digital Authority is the federal body responsible for leading Pakistan’s digital transformation under the Digital Nation Pakistan Act 2025. PDA oversees digital policy, data and AI governance, national digital infrastructure, and shared government platforms, with the goal of ensuring interoperability, security, and alignment across federal and provincial institutions.

DFINITY is a non-profit organization focused on developing the Internet Computer and transforming the internet into a public sovereign cloud capable of hosting next-generation software and services. Founded in 2016, DFINITY operates research centers in Zurich and San Francisco.