AI Coding News - Code Generation, Copilot & Developer Tools

KernelEvolve: How Meta’s Ranking Engineer Agent Optimizes AI Infrastructure

This is the second post in the Ranking Engineer Agent blog series exploring the autonomous AI capabilities accelerating Meta’s Ads Ranking innovation. The previous post introduced Ranking Engineer Agent’s ML exploration capability, which autonomously designs, executes, and analyzes ranking model experiments. This post covers how to optimize the low-level infrastructure that makes those models run [...] Read More... The post KernelEvolve: How Meta’s Ranking Engineer Agent Optimizes AI Infrastructure appeared first on Engineering at Meta .

Google: Gemma 4 31B (google/gemma-4-31b-it)

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Control which domains your AI agents can access

In this post, we show you how to configure AWS Network Firewall to restrict AgentCore resources to an allowlist of approved internet domains. This post focuses on domain-level filtering using SNI inspection — the first layer of a defense-in-depth approach.

Persist session state with filesystem configuration and execute shell commands

In this post, we go through how to use managed session storage to persist your agent's filesystem state and how to execute shell commands directly in your agent's environment.

Qwen: Qwen3.6 Plus (free) (qwen/qwen3.6-plus)

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.

[AINews] A quiet April Fools

a quiet day

Automating competitive price intelligence with Amazon Nova Act

This post demonstrates how to build an automated competitive price intelligence system that streamlines manual workflows, supporting teams to make data-driven pricing decisions with real-time market insights.

Z.ai: GLM 5V Turbo (z-ai/glm-5v-turbo)

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.

Improve coding agents’ performance with Gemini API Docs MCP and Agent Skills.

Gemini API Skills

Anthropic releases part of AI tool source code in 'error'

Anthropic accidentally released part of the internal source code for its AI-powered coding assistant Claude Code due to human error, the company said Tuesday.

[AINews] The Claude Code Source Leak

The accidental "open sourcing" of Claude Code brings a ton of insights.

Building an AI powered system for compliance evidence collection

In this post, we show you how to build a similar system for your organization. You will learn the architecture decisions, implementation details, and deployment process that can help you automate your own compliance workflows.

AWS launches frontier agents for security testing and cloud operations

I'm excited to announce that AWS Security Agent on-demand penetration testing and AWS DevOps Agent are now generally available, representing a new class of AI capabilities we announced at re:Invent called frontier agents. These autonomous systems work independently to achieve goals, scale massively to tackle concurrent tasks, and run persistently for hours or days without constant human oversight. Together, these agents are changing the way we secure and operate software. In preview, customers and partners report that AWS Security Agent compresses penetration testing timelines from weeks to hours and the AWS DevOps Agent supports 3–5x faster incident resolution.

Build a solar flare detection system on SageMaker AI LSTM networks and ESA STIX data

In this post, we show you how to use Amazon SageMaker AI to build and deploy a deep learning model for detecting solar flares using data from the European Space Agency's STIX instrument.

Qodo raises $70M for code verification as AI coding scales

As AI floods software development with code, Qodo is betting the real challenge is making sure it actually works.

Import AI 451: Political superintelligence; Google's society of minds, and a robot drummer

Are there any genies that can be put back in the bottle?

[AINews] H100 prices are melting *UP*

a quiet day lets us report an important GPU trend

Kwaipilot: KAT-Coder-Pro V2 (kwaipilot/kat-coder-pro-v2)

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions, with a focus on large-scale production environments, multi-system coordination, and seamless integration across modern software stacks, while also supporting web aesthetics generation to produce production-grade landing pages and presentation decks.

Claude rate limit chaos

[AINews] Everything is CLI

a quiet day lets us reflect on the growing trend of CLIs for ~everything~ agents