llm.
32 writings found
Latest Archives
AWS Bedrock Web Search Expands to Public Web Access
Amazon Bedrock's Web Search now supports external web access, letting AI models ground responses in real-time information while offering data residency controls.
Gemini 3.7 Flash: The Coding Model That Actually Listens
Google's latest Flash model cuts costs in half while dramatically improving code generation, reasoning, and developer experience. What it means for your stack.
LLM 0.32: When a CLI Tool Becomes an Agent Platform
Major LLM release adds reasoning traces, server-side tools, and content-addressable logging. What this means for building AI systems.
Why AI Adoption Is Stalling: The Context Engineering Problem
The real bottleneck in AI adoption isn't capability, it's context. Michael Foree explains why connecting AI to your actual work is harder than it should be.
OpenAI GPT-5.6 Family: Luna, Terra, and Sol Breakdown
OpenAI launches GPT-5.6 in three sizes with aggressive pricing and strong agentic benchmarks. Here's what it means for developers in 2026.
AI Agents Are Now Running Ransomware Attacks
Sysdig documented the first agentic ransomware operation, JadePuffer. Here is what it means for developers and the future of cybersecurity.
SKILL.md vs OKF: what they are, what they aren't, and how to use both
Two small formats that look similar and solve different problems. Here's the mental model, the failure modes, and how to write a good OKF bundle from scratch.
Why Google's AI Still Can't Spell 'Strawberry' Right
The search giant's latest AI errors expose a fundamental flaw in how LLMs process text
Datasette Agent Is the Bridge Between LLMs and Your Data
A technical look at how Datasette Agent brings AI querying to SQLite databases
Datasette Agent: Where Three Years of LLM Development Finally Clicked
The convergence of conversational AI and data querying opens new possibilities for personal data assistants and extensible tooling.
Datasette Agent: When Data Tools Meet Conversational AI
Three years of LLM work finally converges with Datasette. What this means for building AI systems around your data.
LLM 0.32a0: Rethinking Abstractions for Modern Language Models
Simon Willison's LLM library gets a major refactor to handle multi-modal inputs, streaming typed responses, and the messy reality of frontier models.
LLM 0.32a0: Why Your Prompt/Response Mental Model is Already Obsolete
Simon Willison's LLM library gets a major refactor to handle multi-modal inputs, streaming message parts, and the messy reality of modern AI models
LLM 0.32a0: When Your Abstraction Meets Reality's Complexity
Simon Willison's LLM library gets a major refactor to handle the messy, multi-modal world of modern AI models. Here's why abstractions always break.
Permission Hungry Agents and the Return to First Principles
ThoughtWorks Radar 34 reveals AI's paradox: we're racing forward while rediscovering software fundamentals, and our security models aren't ready.