Google Uses Interactions API as Default for Gemini Models
Google has made the Interactions API the default interface for Gemini models and agents, replacing the generateContent API as of June 2026.
ARTICLES BY THEO ALMEIDA
LATEST NEWS
-
-
AWS Uses Multimodal AI to Enable Searchable Aerial Imagery
AWS and Vexcel developed a system to make aerial imagery searchable using natural language, achieving high F1 scores with Amazon Nova Multimodal Embeddings.
-
Ampersend Uses Amazon Bedrock AgentCore Payments for AI Agent Billing
Ampersend integrated Amazon Bedrock AgentCore Payments to enable AI agents to pay for services in under two weeks, cutting development time by months.
-
Nvidia Launches AI for Science Software Tools
Nvidia announced new AI software tools at ISC 2026, accelerating scientific research with performance gains up to 14,900x.
-
X.ai Introduces /goal for Autonomous Task Execution in Grok Build
X.ai launched /goal in Grok Build on June 22, 2026, enabling long-running, autonomous task execution for developers.
-
Data2Story Uses Seven AI Agents to Turn CSV Files Into Verifiable News Articles
Oxford and Stanford researchers developed Data2Story, an AI tool that transforms CSV files into interactive news articles with verifiable sources, using seven specialized agents.
-
ChatGPT Tips for Better Prompts and Results
ChatGPT users can enhance their interactions by using specific prompts, such as asking for 80-20 insights or requesting personalized feedback, according to a Wired guide.
-
Apple Weaves AI Into iPhone Apps With iOS 27
Apple is embedding AI into its software to solve everyday problems, with features like bill splitting and password updates coming in iOS 27, set for release later this fall.
-
Hugging Face Enables 3D Figurine Creation Without Creative Software
A Hugging Face Space transforms a single photo into a 3D collectible without using Photoshop or Blender. The process relies on two model endpoints, each handling a distinct step in the pipeline.
-
AWS Launches Two Services to Address AI Agent Security and Context Gaps
AWS announced two new services to tackle security and business context issues in AI agents, with AWS Continuum offering automated code vulnerability fixes and AWS Context providing knowledge graphs for better decision-making.
-
Google Colab CLI Enables Free Model Fine-Tuning with Hugging Face
A developer fine-tuned a model in minutes using Google's new Colab CLI, Hugging Face tools, and a free GPU, with no coding required.
-
AMD Radeon GPUs Enable Local LLM Deployment
AMD announced a guide for running large language models on Radeon GPUs, with support for GGUF and ONNX formats.