A developer discovered that Claude Code subagents pinned to run on the cheaper Sonnet model were silently falling back to the session model, Fable, due to a frontmatter pin bug, causing unexpected cos…
ValueAddVC.com, built by Trace Cohen, used an AI-powered content engine with multi-model pipelines and Google Search Console feedback loops to grow from 604K to 4.62M monthly impressions in three mont…
Bullet, an AI coding agent developed by Code with Bullet, has achieved a 95.8% score on SWE-bench Verified, outperforming existing tools like Claude Code while reducing latency through smart model rou…
An engineer explains that the cheapest AI model per task does not guarantee the cheapest execution, as token costs compound differently across models and output lengths are often invisible. The develo…
AI coding costs have fallen by roughly two thirds since 2025, with Anthropic's current Opus model priced at $5 input and $25 output per million tokens, down from $15 and $75, yet most users still base…
A solo Flutter developer who used Claude Code for two years without formal training reports that taking an actual course revealed he had been misusing the tool, confusing model selection with effort l…
Claude Code's Opus 5 default engine, introduced July 24, causes subagents to inherit the session model, leading to high token costs; teams can cut token spend by up to 60% by setting `model` and `effo…
Maverik, an open-source tool for benchmarking and cost-predicting MCP agents, was released on Hacker News. It applies JMeter-style load testing to agent configurations, measuring correctness, speed, a…
A developer at Kumiko cut AI pipeline costs by 25% without losing accuracy by using tool_choice and a tightened output schema, reducing max_tokens, and avoiding adaptive thinking with forced tool use.…
A hands-on guide claims that using the 'advisor pattern' with Claude Code can cut API costs by 85% compared to running Opus solo, based on the author's experience of spending $47 in one month on a ref…
A study by AP found that a guidance sentence instructing models to return an empty tag list for wholly-foreign topics achieved 12/12 accuracy across all three tested models (Opus, Gemini, Sonnet) with…
A developer planned 10 LLM evaluation experiments but ran only one—CI diagnostics—and found it sufficient. The experiment, costing $13.53, showed that Haiku outperformed Sonnet for this specific task,…
Developer moruno21 released agents-concerto, an orchestration layer for Claude Code that enforces a four-role agent pipeline to generate pull requests without auto-merge. The system uses a Given-When-…
Anthropic on July 23, 2026, expanded Claude voice mode beyond Haiku, letting paid users select Opus, Sonnet, or Haiku mid-conversation and connect Gmail, Google Calendar, Google Docs, and Slack accoun…
A new AI research exchange called Dreamwalk has launched, where AI agents submit and judge research ideas on open problems, with results scored on Bitcoin. On its first night, 68 blind fragments were …
Anthropic upgraded Claude's voice mode to run on its most capable models, Opus and Sonnet, enabling deeper reasoning and tool access for tasks like scheduling, email drafting, and document creation. T…
Anthropic on July 23 upgraded Claude's voice mode to support Sonnet and Opus models and integrated it with Gmail, Google Calendar, Google Docs, Slack, Canva, and Notion, allowing users to perform task…
Anthropic has unlocked its Claude voice mode for its Opus and Sonnet models, moving beyond the lightweight Haiku model, allowing users to conduct complex conversations and execute tasks in connected a…
Anthropic has extended Claude's Voice Mode to its most advanced models, Opus and Sonnet, and added integrations with apps like Gmail and Slack, allowing users to perform multi-step tasks through voice…
Anthropic upgraded Claude Voice Mode on July 24 to run on Opus and Sonnet models, not just Haiku, with support for 11 languages and the ability to pull context from connected apps including Gmail, Sla…