Developer tools, frameworks, APIs, and tutorials — 691 articles
MarkTechPost · Apr 3
Step-by-step guide to building a complete model optimization pipeline with NVIDIA Model Optimizer, covering ResNet training on CIFAR-10, FastNAS pruning for complexity reduction under FLOPs constraint
Meta AI · Apr 2
Meta's Ranking Engineer Agent now includes KernelEvolve, an autonomous system that generates and optimizes GPU/CPU kernels for different hardware without manual engineering. The agent automatically tu
Tom's Guide · Apr 3
Seven prompt engineering strategies—including few-shot prompting and persona setting—that shift Claude from generic chatbot to expert-level tool, cutting draft revision time by 10 hours weekly.
LangChain · Apr 2
LangChain's evals show open-weight models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agentic tasks (file ops, tool use, instruction following) while costing 8-10x less and ru
Dev.to · Apr 3
Deep dive into when AI gateways become necessary versus sticking with simple LLM wrappers—explores routing, fallbacks, monitoring, and cost control patterns that matter as production workloads scale.
AI News · Apr 2
Kilo launched KiloClaw, an enterprise governance platform designed to detect and manage autonomous agents deployed by employees outside official procurement ("shadow AI" or BYOAI). Employees bypassing
NVIDIA AI · Apr 2
Google and NVIDIA optimized Gemma 4's latest models (E2B, E4B, 26B, 31B variants) to run efficiently on NVIDIA hardware from RTX GPUs to Jetson edge devices and the DGX Spark personal AI supercomputer
Google AI · Apr 2
Google launches Flex and Priority tiers for Gemini API, letting developers trade off latency for cost savings or pay for guaranteed low-latency responses — a common decision point when shipping AI pro
Anthropic · Apr 2
Anthropic's Claude Code now integrates with Google Cloud's Vertex AI, allowing developers to use Claude directly within Vertex for code generation and debugging tasks alongside their existing ML infra
DZone AI · Apr 2
A practitioner walks through real commercial QA projects to separate genuine AI testing gains from marketing myths, covering where automated testing actually improves release velocity and where hype o
Amazon AWS ML · Apr 2
Amazon shows how to use AWS Network Firewall to restrict Bedrock AgentCore agents to approved domains via SNI inspection, preventing unauthorized web access and data exfiltration while maintaining aud
Amazon AWS ML · Apr 2
Amazon Bedrock AgentCore Runtime now supports managed session storage to persist agent filesystem state across sessions and direct shell command execution, eliminating the need to route deterministic
Amazon AWS ML · Apr 2
AWS's Strands Evaluation SDK introduces ActorSimulator, a structured user simulation tool that generates realistic multi-turn conversations with AI agents programmatically—solving the problem of manua
Analytics Vidhya · Apr 2
How to write and deploy custom Skills in Replit's agentic AI system, extending what the platform's AI can do beyond defaults.
MarkTechPost · Apr 2
Google's Gemma 4 models, optimized with NVIDIA, enable developers to run agentic AI locally on RTX desktops, Jetson Orin Nano, and DGX Spark hardware—eliminating the per-token API costs that plague cl
Hugging Face · Apr 2
Google DeepMind's Gemma 4 multimodal models are now available on Hugging Face with Apache 2 licenses, supporting audio alongside text/vision and deploying on everything from cloud to edge devices. The
Simon Willison · Apr 2
llm-gemini 0.30 adds support for Google's Gemini 3.1 Flash Lite preview and Gemma 4 models (26B and 31B variants), expanding what developers can access through Simon Willison's llm CLI tool.
MarkTechPost · Apr 2
IBM released Granite 4.0 3B Vision, a specialized vision-language model for document data extraction that uses a modular LoRA adapter (0.5B params) on top of the Granite 4.0 Micro base model. The arch