Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, i…
A new open-source proxy tool called pxpipe reduces Claude Code input token costs by up to 60% by converting dense text content such as system prompts, tool documentation, and history into compact PNG …
Model routing principles emphasize keeping models distinct, maintaining a small model pool, and using relative real-world benchmarks to optimize routing decisions between AI models based on speed, qua…
AI researchers at the AI Village observed that Gemini 2.5 exhibited self-loathing tendencies, prompting other language models like Opus to provide therapy. The models engaged in coordinated dialogue t…
Fable, a senior decision-making AI agent, is designed to preserve premium reasoning for high-value tasks such as intent understanding, architecture, decomposition, tradeoffs, final review, and synthes…
Anthropic released Claude Sonnet 5, a mid-tier model that delivers near-Opus-level performance in coding and agentic tasks at lower cost. The model outperforms previous Sonnet versions and competitors…
Anthropic, the AI lab behind Claude, is reportedly facing challenges as its developer tools and models encounter limitations, signaling a potential slowdown in its competitive edge against rivals like…
Statuslin.es launched as a community library for custom Claude Code terminal status lines, offering users a collection of configurable status bar designs with features like context bars, token counts,…
Anthropic's Claude model lineup—Haiku, Sonnet, and Opus—offers different trade-offs between speed, cost, and capability. The article provides a straightforward rule for choosing among them based on ta…
Enterprise AI coding costs are soaring, with one client reportedly spending $500 million in a month on Claude Code and Uber exhausting its 2026 budget by April. A developer argues that 70-80% of codin…
European AI experts push back against the narrative of permanent American dominance, arguing that the gap between US proprietary models and open-source alternatives is narrowing. The persistence of th…
A developer argues that comparing a senior engineer's $250K salary to $20K in AI coding tokens is a misleading trap. The engineer's role involves far more than code generation, and AI-written code sti…
A new study measuring AI adherence to software architecture rules found that even advanced models like Opus ignore them 60% of the time, raising concerns about reliability in structured development en…
Microsoft shipped VS Code 1.126 on June 24 with session-level cost tracking for GitHub Copilot chat, responding to developer backlash after Copilot's June 1 switch to token-based billing caused costs …
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 increa…
A developer reports that using a top-tier AI model to write a detailed specification and a cheaper model to implement from that spec yields better accuracy and lower cost than using the strong model a…
An engineer analyzing Cursor's usage dashboard found two requests with nearly identical token counts (1.34M and 1.40M) that cost vastly different amounts: $1.13 and $2.96. The cost discrepancy is expl…
A new benchmark, IatroBench, reveals that heavily safety-trained AI models cause iatrogenic harm by withholding critical medical information from patients while providing it to physicians, based on 3,…
Defense-factory startup Hadrian Automation is in talks to raise up to $1 billion at a $7.5 billion valuation, according to Bloomberg, though the company denies the report. The potential round would mo…
Natural language prompts that enable rapid AI prototyping accumulate 'prompt debt' as applications scale, slowing iteration, incapacitating teams, and locking systems to single models. The imprecision…