» Tag
anthropic
22 postsCutting Claude API Costs 84% by Separating Vision and Reasoning
An OCR pipeline routed page images to Haiku and reasoning to Sonnet instead of Opus, cutting Claude API costs by 84%. Includes the model-routing math and a real JSON parsing bug.
The Future of Software Development at Anthropic
Discover how AI tools are reshaping software development at Anthropic.
Anthropic subsidizes AI coding costs at 13x. How long will it last?
Insights on Anthropic's AI coding subsidies and engineering cost implications.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comGetting JSON Out of Claude: Prefills Are Dead, Here's What Works
Assistant-turn prefills now throw 400 errors on newer Claude models. Here's how structured outputs and tool use replace the old JSON-forcing trick.
PromptFiction Flaw: Auto-Submitted Hidden Prompts in Claude Desktop
Oasis Security's research uncovered the PromptFiction flaw in Claude Desktop, enabling commands to be executed without user approval.
Add Claude Sonnet 5 Behind a Provider Contract
Claude Sonnet 5 should be integrated with a provider contract for optimal design.
Anthropic Scores AI Jailbreaks Like CVEs With New CJS Scale
Anthropic unveiled the CJS scale for grading AI jailbreak severity like CVEs, launching Claude Fable 5 alongside this new framework for the industry.
GPT-5.6 Arrives, Fable 5 Goes Metered: Cost Control Still Missing
OpenAI's GPT-5.6 rollout and Anthropic's newly metered Fable 5 expose a deeper gap in AI coding tools: no reliable way to track, reserve, or explain agent spending.
Claude Cowork: Tasks Keep Running After You Close the Laptop
Anthropic's Claude Cowork runs multi-step tasks on remote servers and keeps working even after you close your laptop, marking a shift toward asynchronous AI agents.
Subtext Visualizes an LLM's Internal Reasoning in Real Time
Subtext is an open-source tool that applies Anthropic's Jacobian lens to visualize a local LLM's internal representations live during conversation.