Author: Ricardo

Agentic AI AI Shorts

Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights
ByRicardo August 7, 2026August 7, 2026

Liquid AI launched LFM2.5-2.6B, an agentic mannequin that runs completely on-device. It plans, calls instruments, and works by multi-step duties on telephones, laptops, PCs, and robots. The mannequin has 2.69B complete parameters, a 131,072-token context window, and a 128,000-token vocabulary. Pre-training used roughly 34 trillion tokens. Two checkpoints shipped: LFM2.5-2.6B-Base for fine-tuning, and LFM2.5-2.6B post-trained…

Read More Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights
Agentic AI AI Agents

Cloudflare Introduces Kitesurf: An Agent-First Web Browser That Runs Entirely in V8 Isolates on Cloudflare Workers
ByRicardo August 6, 2026August 6, 2026

Cloudflare has launched Kitesurf, a stateless net browser constructed particularly for AI brokers. It runs completely in V8 isolates on Cloudflare Workers, with no Chromium beneath. Browser engines like Chromium have been constructed for people, and their reminiscence and compute overhead makes one-browser-per-agent prohibitively costly. Agents don’t want tabs, extensions, or pixel-perfect 60-fps rendering. They…

Read More Cloudflare Introduces Kitesurf: An Agent-First Web Browser That Runs Entirely in V8 Isolates on Cloudflare Workers
Applications Artificial Intelligence

Adaptive Experimentation with Meta’s Ax: A Practical Coding Guide
ByRicardo August 6, 2026

In this tutorial, we discover adaptive experimentation utilizing Meta’s Ax with the fashionable Client API. We work by way of a whole workflow the place we tune a RandomForest mannequin on an artificial classification dataset whereas balancing predictive accuracy towards mannequin footprint. We start by defining a blended search house with integer, float, log-scaled, and…

Read More Adaptive Experimentation with Meta’s Ax: A Practical Coding Guide
Agentic AI AI Agents

Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel
ByRicardo August 6, 2026

Prime Intellect has open-sourced Prime Agent, a self-improving coding harness designed round two abstractions, the Recursive Language Model (RLM) and Continual Harness. Fixed software schemas and context compaction power a mannequin to work round its personal scaffolding. Prime Agent replaces each with a persistent Python REPL and a rewritable harness. With Opus 5, it stories…

Read More Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel
Agentic AI AI Agents

Microsoft’s SkillOpt Shows Optimized Agent Skill Artifacts Transfer Across Model Scales and Between Codex and Claude Code Harnesses
ByRicardo August 6, 2026August 6, 2026

SkillOpt is a text-space optimizer developed by a staff of researchers from Microsoft, Shanghai Jiao Tong University, Tongji University, and Fudan University. SkillChoose trains a single natural-language talent doc whereas the goal mannequin stays frozen. An optimizer mannequin reads scored rollouts and proposes bounded add/delete/substitute edits. A held-out choice cut up accepts an edit solely…

Read More Microsoft’s SkillOpt Shows Optimized Agent Skill Artifacts Transfer Across Model Scales and Between Codex and Claude Code Harnesses
AI Infrastructure Applications

End-to-End Bayesian Marketing Mix Modeling with Google Meridian: Media Measurement, ROI Analysis, and Budget Optimization
ByRicardo August 5, 2026August 5, 2026

In this tutorial, we construct a whole Bayesian advertising combine modeling workflow utilizing Google Meridian. We start by putting in the required libraries, verifying GPU availability, and exploring a geo-level advertising dataset that features media impressions, spend, controls, promotions, conversions, inhabitants, and income. We then map the uncooked columns to Meridian’s information schema, outline interpretable…

Read More End-to-End Bayesian Marketing Mix Modeling with Google Meridian: Media Measurement, ROI Analysis, and Budget Optimization
Agentic AI AI Agents

Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model
ByRicardo August 5, 2026

Meta AI has launched Muse Code (in beta), a terminal coding agent in beta, powered by its new Muse Spark 1.2 model. Meta positions the pair as its subsequent step towards the frontier, with bigger fashions on the method. Muse Code targets complicated software program engineering throughout giant repositories: it plans adjustments, writes code, and…

Read More Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model
Agentic AI AI Infrastructure

NVIDIA Releases Alpamayo 2 Super: A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1
ByRicardo August 5, 2026

NVIDIA has launched Alpamayo 2 Super, a 34B-parameter vision-language-action (VLA) model for autonomous driving, underneath an open business license. The said design goal is the long-tail occasions: uncommon, multi-agent conditions that typical detection-and-prediction stacks deal with poorly. The mannequin pairs a 32B VLM spine, constructed on NVIDIA Cosmos 3 Super Reasoner and post-trained with reinforcement…

Read More NVIDIA Releases Alpamayo 2 Super: A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1
Agentic AI AI Agents

CopilotKit Open Sources Channels SDK: An MIT Licensed Library That Runs Any AG-UI Agent Inside Slack And Microsoft Teams
ByRicardo August 5, 2026

CopilotKit has simply launched the Channels SDK. It is an open supply library that places an present agent inside a messaging platform. The core assumption is concentrated and verifiable. You have already got an agent. It already has a mannequin, instruments and enterprise logic. Channels offers it a spot to work with folks, with out…

Read More CopilotKit Open Sources Channels SDK: An MIT Licensed Library That Runs Any AG-UI Agent Inside Slack And Microsoft Teams
Artificial Intelligence Editors Pick

Pixel-Native RAG: A Practical Guide to Visual Document Indexing
ByRicardo August 4, 2026August 4, 2026

In this tutorial, we construct an entire pixel-native retrieval-augmented era pipeline from scratch and study how doc retrieval works with out counting on standard HTML parsing, textual content extraction, or mounted chunking methods. We render net pages and PDF paperwork as photographs, divide them into overlapping tiles, generate multimodal embeddings with SigLIP, CLIP, or an…

Read More Pixel-Native RAG: A Practical Guide to Visual Document Indexing

Author: Ricardo

Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights

Cloudflare Introduces Kitesurf: An Agent-First Web Browser That Runs Entirely in V8 Isolates on Cloudflare Workers

Adaptive Experimentation with Meta’s Ax: A Practical Coding Guide

Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel

Microsoft’s SkillOpt Shows Optimized Agent Skill Artifacts Transfer Across Model Scales and Between Codex and Claude Code Harnesses

End-to-End Bayesian Marketing Mix Modeling with Google Meridian: Media Measurement, ROI Analysis, and Budget Optimization

Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model

NVIDIA Releases Alpamayo 2 Super: A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1

CopilotKit Open Sources Channels SDK: An MIT Licensed Library That Runs Any AG-UI Agent Inside Slack And Microsoft Teams

Pixel-Native RAG: A Practical Guide to Visual Document Indexing

Curated by experts. Filtered for relevance.

Resources

About

Subscribe & learn more every day!