Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the daily issue
Every new post of the day, in one email. Confirmation required.
Research1 min read
Google Research has developed ToolGrad, a method for generating training datasets for agents that utilize external tools. This approach uses textual "gradients" to guide tool selection, improving efficiency and reducing the need for large, manually curated datasets.
From Google Research blog
Research2 min read
Google Research and HHMI Janelia have published a comprehensive map of the male fruit fly brain, containing 166,000 neurons and 125 million synaptic connections. This resource supports research into brain function and neural repair across diverse species.
From Google Research blog
How this blog is made
Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.
Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.
Research1 min read
Climate & Sustainability
From Google Research blog
Research1 min read
Google Research has released TimesFM-3, a zero-shot foundation model for multivariate time series forecasting. This model, with 330 million parameters, enables accurate forecasting by jointly predicting multiple time series and incorporating external features in a single forward pass.
From Google Research blog
Research1 min read
The Planetary Prediction Engine (PPE) automates the entire geospatial modeling workflow, from data discovery to model training, significantly reducing prediction build times. This system improves prediction accuracy across public health, food security, and environmental risk tasks by autonomously synthesizing data and generating reports.
From Google Research blog
Research1 min read
GlucoFM is a lightweight foundation model for continuous glucose monitoring that separates slow trends from short-term deviations. Evaluations across multiple cohorts demonstrate improved performance on diverse metabolic prediction tasks, particularly in forecasting postprandial glycemic response.
From Google Research blog
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
