Full-text search across 35378 articles. Combine with topic and date filters; results sorted by relevance.
Base44, acquired by Wix for $80 million in 2025, launched its own AI model Base 1 on June 29 to reduce reliance on third-party models and improve margins. The move comes as Base44 reaches $150 million in annual recurring…
Base44, the vibe coding platform acquired by Wix for $80 million a year ago, has launched its own AI model, Base1, to improve latency, cost, and efficiency. The move addresses concerns about defensibility for startups re…
A developer introduced AGENTS.md, a single Markdown file placed at the root of a repository to provide AI coding agents with essential context, setup commands, and conventions. The file, pioneered by OpenAI's Codex and n…
A developer created 'orchestrate-plan', a Claude Code skill that executes a locked PLAN.md by delegating implementation to cmux worker panes one phase at a time, clearing context between phases. The skill supports parall…
Google launches Zero Frontend Code, enabling deployment of interactive A2UI agents directly to Gemini Enterprise. The technology uses generative UI to create dynamic interfaces at runtime, allowing AI agents to assemble …
A developer observed that AI-generated code is often correct but slowly erodes software architecture, leading to 'architecture debt' that goes unnoticed until it becomes costly. To address this, they built ArchPilot, a t…
METR and Epoch AI released MirrorCode, a benchmark testing AI agents' ability to reimplement entire software programs from source code. Claude Opus 4.6 rebuilt a 16,000-line bioinformatics toolkit in Rust, passing 99.95%…
An engineer at Anthropic analyzed the hidden costs of switching models in Claude Code sessions, finding that model switches invalidate prompt caches, leading to duplicated cache writes that can increase costs by up to 85…
Gartner predicts that by 2028, AI coding costs will exceed the average global developer salary of around $2,000 per month due to rising token consumption and consumption-based billing. The research firm warns that withou…
Z.AI's open-weight GLM-5.2 (Max) model climbed to second place on the Code Arena frontend leaderboard by June 16, scoring up to 1,595 points and beating Claude Opus 4.7 (Thinking) by 29 points. The 744B+ parameter Mixtur…
Anthropic's Claude Code dynamic workflows enabled Jarred Sumner to port 750,000 lines of Zig to Rust with 99.8% of Bun's test suite passing in eleven days by codifying orchestration in JavaScript scripts rather than rely…
A developer documented workarounds for breaking changes in Anthropic's Claude Code CLI tool, including pinning version 1.0.17, disabling auto-updates, and patching the `exit_plan_mode` popup to prevent focus disruption. …
Gartner predicts that enterprise AI coding token costs will rival or exceed average developer salaries by 2028 due to rising token consumption and consumption-based pricing models. Senior principal analyst Nitish Tyagi w…
A developer reports that AI coding costs can be slashed by 70% through task-level model routing instead of using a single frontier model for all tasks. After profiling usage, the developer found that 60% of prompts to ex…
A developer identifies five common ways AI coding agents waste tokens, including prompt caching inefficiencies, long-context bloat, oversized tool schemas from MCP servers, and repeated context. The post offers specific …
Developer Gary Sheng used Claude Code to redesign his iPhone app Simple Meds, which he originally built with GPT-4o and Cursor a year ago. The redesign leverages Claude Opus 4.7 and newer AI agents to improve the app's v…
A backend systems engineer compared building GenAI data pipelines with LangChain's orchestration framework versus pure native Python code. The analysis found that while frameworks like LangChain accelerate prototyping, t…
Vercel CEO Guillermo Rauch expressed shock at the coding abilities of Z.AI's open-weight GLM-5.2 model, which trails the best closed model by just 1% on key benchmarks. Vercel integrated the model into its AI Gateway wit…
A developer argues that 'vibe coding' autonomy levels (L0-L5) are incomplete without a second axis: operator discipline, which measures how much work survives session boundaries as inspectable state. The developer claims…
A developer explains that CLAUDE.md is a markdown file read by Claude Code at the start of every conversation, serving as a project's constitution for stack, conventions, and commands. The file can be generated via the /…