Research
Google's AMIE AI Shows Real-Time Video Consultation
Google AI Bloghigh confidence
Why it matters
- →AMIE demonstrates the potential for AI to enhance real-time clinical consultations.
- →The system's ability to interpret visual and auditory cues could improve diagnostic accuracy.
- →This research highlights the future role of AI in transforming healthcare delivery.
Google's research medical AI system, AMIE, has showcased its ability to perform real-time clinical video consultations. Developed by Google Research and Google DeepMind, AMIE uses a multi-agent architecture to interpret visual and auditory cues during consultations. In a study involving simulated consultations, AMIE was evaluated positively for its diagnostic accuracy and communication skills. Although still a research system, AMIE's capabilities suggest a promising future for AI in healthcare.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1AI Outperforms Doctors in ER Diagnosis Study
TechCrunch AI · May 3, 2026 · Related
- 2AI Outperforms ER Doctors in Harvard Study
The Rundown AI · May 4, 2026 · Related
- 3Google DeepMind Introduces AI Co-Clinician
Lev Selector · May 8, 2026 · Related
- 4Google I/O 2026: AI Agents and Gemini Updates
WIRED AI · May 19, 2026 · Related
- 5Agentic AI Transforming Global Health Care
MIT Technology Review AI · June 2, 2026 · Background
- 6Google Research Explores AI in Dermatology Assistance
Google Research Blog · June 12, 2026 · Related
- 7Google's AMIE AI Advances Disease Management
Google AI Blog · June 17, 2026 · Same story
- 8Google's SymptomAI Enhances Symptom Assessment
Google Research Blog · July 22, 2026 · Related
What happened next
- 9Samsung unveils AI models for wearable health data
AI News · August 14, 2026 · Background
- 10AI May Surpass Doctors in Key Medical Tasks
WIRED AI · August 28, 2026 · Background
- 11ChatGPT Integrates with Healthcare Data Systems
OpenAI · September 1, 2026 · Background
- 12Google DeepMind Launches Agentic Video Understanding
Google DeepMind · September 1, 2026 · Background
- 13Google's August AI Innovations: Gemini and Beyond
Google AI Blog · September 1, 2026 · Background
Follow this story
Open the full story →Google's AMIE AI Shows Real-Time Video Consultation
2 developments
- Aug 11 · Google AI Blog
Google's AMIE AI Shows Real-Time Video Consultation (This article) - Aug 12 · AI News
Google tests AMIE for clinical video consultations
More in Research
© WIRED AIResearchagents
Researchers Drive Car with GPT-6 Astra
Three engineers at Axiom proved that general-purpose language models can control physical hardware without task-specific training. By linking OpenAI’s GPT-6 Astra to a Toyota Corolla’s steering system, they navigated the vehicle through an In-N-Out drive-thru using only prompt engineering and camera input. While the car moved slowly and required a safety driver, the experiment reveals that multimodal models are developing emergent spatial reasoning capabilities previously thought to require dedicated robotics stacks. This blurs the line between digital assistants and physical agents, suggesting that scaling text-and-image training yields unexpected real-world utility.
WIRED AI
© Hugging Face BlogResearchresearch
Nemotron Fine-Tuning Hits Gold at IOI and IMO
NVIDIA’s Nemotron models just crossed the gold-medal threshold in both the International Olympiad in Informatics and Mathematics. This isn't a new foundation model; it’s proof that specialized fine-tuning combined with iterative generate-verify-refine inference loops can push existing architectures to world-class levels. The Ultra-CC variant scored 535.4/600 on IOI, while the IMO system solved complex proofs without external tools or formal provers. By releasing the datasets and pipelines, NVIDIA is shifting the narrative from raw parameter count to reproducible specialization recipes.
Hugging Face Blog
© The Verge AIResearchresearch
OpenAI releases 722 math manuscripts from frontier model
OpenAI has published 722 manuscripts covering 372 result families, marking a significant escalation in AI-driven mathematical discovery. This release, guided by the AGMAI advisory group's ethical guidelines, includes solutions to hundreds of open questions and details on compute usage, such as an average of three hours of ChatGPT Pro thinking per result. The move shifts the conversation from speculative claims to verifiable data, forcing the academic community to confront the reality of AI-generated proofs. It underscores a growing tension between rapid corporate output and traditional peer review standards. Mathematicians now have concrete artifacts to audit rather than vague promises. The transparency around compute costs sets a precedent for future frontier model releases in scientific domains.
The Verge AI