Claude's In-Context Learning — The End of Fine-Tuning
··1593 words·8 mins
Anthropic’s latest Claude breakthrough lets developers inject task-specific knowledge directly into prompts without fine-tuning, fundamentally shifting how we
- Osmond van Hemert — Senior Software Engineer & Applied AI/
- Blog Tags: Software Development, AI, Security & Infrastructure/
- AI Across Software, Security & Infrastructure/
AI Across Software, Security & Infrastructure
AI turns up in more than model announcements. This tag collects posts about AI wherever it intersects with software development, security, infrastructure, and the industry that builds those tools. Use the list below to follow those connections across categories.
For coverage focused on models, agents, and AI policy, start with the AI category. For narrower reading paths, explore AI Models & Releases or Developer Tooling.
AI Regulation & Compliance — Building Responsible AI Systems
··778 words·4 mins
Navigate AI regulation frameworks: EU AI Act, GPAI compliance, supply chain security, and building AI systems with governance by design.
AI-Assisted Testing — From Unit Tests to Behavior Validation
··1539 words·8 mins
AI models can now generate tests, find edge cases, and validate behavior at scale. But blindly using AI for testing creates false confidence.
The Rise of Agent-Based Systems in Software Development
··1060 words·5 mins
AI agents are moving from research labs into production systems, fundamentally changing how we architect software for autonomous decision-making and execution.
Anthropic's SpaceX Deal — How Compute Became the Real AI Moat
··1207 words·6 mins
Anthropic just bought all 300+ MW of SpaceX’s Colossus 1 data centre.
Supply Chain Malware in PyTorch Lightning — AI's Attack Surface
··1190 words·6 mins
A Dune-themed malware campaign targeting the PyTorch Lightning library highlights how AI/ML supply chains are becoming prime targets for sophisticated attacks.
Agent Systems Architecture Patterns — Building Autonomous Systems
··681 words·4 mins
Explore architecture patterns for building agent-based systems, from reasoning loops to tool integration and operational governance.
GitHub Copilot Agent Mode Goes GA — What It Means for Developers
··908 words·5 mins
GitHub Copilot’s agent mode is now generally available, promising autonomous multi-step coding.
AI/LLM Models & Capabilities — In-Context Learning to Reasoning
··668 words·4 mins
Tracking the rapid evolution of AI model capabilities, from in-context learning and extended thinking to reasoning models reshaping development workflows.
GTC 2026 Preview — What NVIDIA's Next Move Means for AI
··1097 words·6 mins
With NVIDIA’s GTC 2026 around the corner, here’s what developers and infrastructure teams should be watching for in the next generation of AI compute.
EU AI Act GPAI Rules — Six Months In, Compliance Clock Ticking
··1084 words·6 mins
The EU AI Act’s general-purpose AI provisions have been in force for six months.
AI Agent Frameworks — The Wild West of Autonomous Systems
··980 words·5 mins
The AI agent framework landscape has exploded, with LangGraph, CrewAI, AutoGen, and dozens more competing for developer mindshare. Here’s what matters.