Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Apple is paying Google approximately $1 billion annually to use a custom Gemini model for Siri's planning and summarization features, according to Bloomberg's Mark Gurman. The partnership, confirmed in January 2026, foll…
Cline launched ClinePass, a low-cost monthly subscription pairing its agent harness with curated open-weight models and higher API rate limits, as the performance gap between frontier and open-weight models narrows. The …
AI agents rely on external systems to manage memory because large language models are stateless and process only the text in their context window per call. Developers must engineer memory by inserting relevant context in…
OpenAI released GPT-5.6 on June 26, 2026, introducing three models including the flagship Sol, marking a new generation in AI language models with real benchmark improvements.
The Trump administration's export controls on Anthropic and OpenAI's frontier AI models are driving developers toward open-source alternatives, potentially benefiting foreign competitors. Commerce Department restrictions…
An engineer discovered that MCP server schemas consumed 42,000 tokens on a single server, causing a 37% token bill increase. After instrumenting a production agent, they found that schema overhead accounted for up to 80%…
A developer replaced Claude with a local Ollama model for generating git commit messages after hitting Claude's usage limit, which resulted in a commit message reading 'You've hit your session limit'. The developer chose…
U.S. developers and startups are increasingly adopting low-cost Chinese AI models like DeepSeek, which offer comparable performance at a fraction of the price of American rivals. Despite political scrutiny, Chinese firms…
The newsletter discusses the challenges of measuring developer productivity and predicting timelines, drawing parallels between Fred Brooks' 'The Mythical Man-Month' and modern AI agentic software development. It highlig…
AI researcher and LessWrong community member argues that the concept of 'P(doom)'—the probability of catastrophic AI outcomes—is poorly defined and counterproductive. The post highlights ambiguity in what counts as 'doom…
OpenAI's preview release of the GPT-5.6 series introduces three distinct tiers—Sol, Terra, and Luna—signaling the end of single-model API integration. Developers must now build intelligent routing layers to dynamically c…
A developer working on a locked-down enterprise Windows machine built a Python bridge using pywin32 to let Claude Code read and draft Outlook emails without MCP servers or Azure app registration. The single-file tool exp…
The official Anthropic Ruby SDK now supports building AI agents in Rails with tool design, MCP servers, human approval gating, testing, and cost control. The SDK includes streaming, connection pooling, and a tool runner …
Claire tests GLM-5.2, an open-weight model from Z.ai, in her ChatPRD codebase, finding it production-grade and capable of replacing Opus for some coding workflows. The model benchmarks near Claude Opus 4.8 and above GPT-…
FamNest engineer discovered that AI agents fail to call APIs correctly when documentation is written for humans, not machines. The coach agent in FamNest's agent graph repeatedly constructed malformed calls to a retrieva…
The New York Times escalated its copyright lawsuit against OpenAI and Microsoft, accusing Microsoft of building a supercomputer specifically to help OpenAI steal copyrighted articles. The Times seeks to amend its complai…
AI is transforming software development by automating repetitive tasks like code generation, debugging, and documentation, but it is not replacing developers. Developers remain essential for understanding business goals,…
OpenAI is investigating Codex quota depletion after Pro plan users exhausted weekly limits in one to two days, revealing that AI coding agent adoption is outpacing capacity forecasts. Engineering lead Thibault Sottiaux c…
As recursive self-improvement accelerates, humans risk losing the ability to interpret and guide autonomous research agents, which could lead to safety failures. A new research agenda proposes studying how to keep humans…
A second-year computer science student at the University of Debrecen built RepoLens, an AI system that scans GitHub repositories for developer onboarding, screens technical candidates by analyzing commit history, and ope…