Full-text search across 62841 articles. Combine with topic and date filters; results sorted by relevance.
Dex Horthy, CEO and cofounder of HumanLayer, coined the term 'context engineering' and shared lessons from building AI agents, including that shipping unread code leads to disaster within months after a July 2025 experim…
A new analysis reveals that AI model pricing pages misrepresent real costs because tokenizers—the components that split text into billable units—vary widely between models, turning the same TypeScript file into 681 token…
A developer argues that AI-generated code cannot replace human judgment, domain understanding, and system thinking, warning that overreliance on AI tools leads to skill atrophy and shallow solutions. The piece emphasizes…
Google released ADK 2.0, a hybrid agent framework combining deterministic code with selective LLM reasoning, achieving ~50% token savings and improved security. Meta CEO Mark Zuckerberg admitted AI agent progress has lag…
Anthropic launched Live Artifacts for Claude Code on June 18, 2026, enabling real-time, shareable web pages from coding sessions. OpenAI's GPT-5.6 is nearing a June launch, with its chief scientist calling it a meaningfu…
Synaxi-predict, a new tool from Synaxi, predicts the token cost, turn count, and pass rate of a Claude Code task before execution, enabling users to select the optimal model and avoid wasted tokens. The tool uses an MLP …
At CodeRabbit's app.js conference booth, developers played a speed code review game where bugs were missed under time pressure. Conversations revealed many rely on pre-installed review bots or coding agents for review, o…
A debate is emerging in engineering circles that AI has killed Agile and brought back Waterfall, but the reality is more nuanced: the high cost of writing code that made Agile necessary is gone, replaced by a rapid spec-…
Anthropic released Claude Opus 4.8 on May 22, making the model available simultaneously in Claude Code, the API, and major cloud providers without a waitlist or staged rollout. The new model is roughly four times less li…
Modular released AI agent skills for its Mojo language that enable coding assistants to translate existing GPU kernels from CUDA and Triton into Mojo code, addressing the challenge that large language models lack trainin…
OpenAI's GPT-5.5 Codex model was tested at four reasoning effort levels — low, medium, high, and xhigh — on 26 real-world coding tasks from the open-source GraphQL-go-tools repository. Low and medium tied on test pass ra…
The author describes rebuilding their personal blog using a complex technology stack including Next.js, React, and MDX, despite acknowledging it may seem like overkill for a blog. They chose MDX for content management be…
A September 23, 2026 blog post outlines a manual workflow for converting accepted, recurring PR review comments into coding-agent rules stored in files such as AGENTS.md, .claude/rules/ and .cursor/rules/, citing a study…
A product-focused practitioner, newly relocated to Austin, describes a spec-driven development operating model for enterprise agentic AI rollouts, in which a locked specification file serves as the contract that coding a…
AI agents in September 2026 remain poorly defined, with the term applied to everything from simple API-calling chatbots to sixteen agents that built a working C compiler from scratch over two weeks for $20,000 in API cos…
Bluebox, an AI agent that monitors OpenTelemetry data and files GitHub issues with evidence, launched its setup process, enabling coding agents to automatically investigate production issues and provide root-cause fixes.…
Anthropic reported on July 24, 2026 that it removed over 80% of Claude Code's system prompt for its newest models with no measurable loss on its coding evaluations, but an independent re-measurement by Pawel Huryn on Jul…
Software engineering is fundamentally about managing complexity and making architectural tradeoffs, not just writing code, according to a new essay. The piece argues that while AI excels at generating code, it cannot rep…
Xenition, an AI-native app builder, aims to let developers create mobile apps by describing their intent in natural language rather than writing code. The project's approach focuses on generating visual previews and shor…
SemiAnalysis announced AgentX 1.0, the world's first fully open source multi-turn agentic coding inference benchmark at 1 million context, released under Apache 2.0, after spending more than $3M building the dataset. The…