ANTHROPIC
151 items
143 posts, 7 tools, 1 guide
Anthropic is cutting its vulnerability disclosure window from 90 days to 30 for high and critical bugs, effective January 1, 2027. What changes, what does not, and a Monday checklist for maintainers.
Self-hosted Claude Managed Agents runs the service, its PostgreSQL store and sandboxes on your infra, with Bedrock, Vertex, Foundry or a gateway for model calls.
Claude Fable 5.2 costs $8/$40 per MTok, down from $10/$50, but enforces the prefix check on every account. The four breaking changes and how to migrate.
Claude Console now has an IP allowlist in beta: up to 1,000 IPv4 or IPv6 ranges per org, enforced on the Messages, Batches, Files and Admin APIs. Setup and lockout traps.
Weekly Claude Code limits are draining faster for many users since mid-October. What the GitHub measurements show, the headless claude -p metering gap, and what to check first.
Claude Code on Opus 5.5 now refuses to recreate specific existing games, even renamed. What the two-sentence rule says, what it blocks, and what builders do next.
Anthropic renamed Max 20x to Ultra and dropped the five-hour limit for verified accounts. What the 10x weekly label means, how to check yours, and Max vs Ultra.
Claude API message threads (beta, Nov 2) keep a conversation on the server for 5 minutes, so each turn sends only new messages. Setup, SDK helper, errors, limits.
Since Claude Code 2.1.314, one setting makes Write, Edit and NotebookEdit refuse paths outside your working directories in every mode, including bypassPermissions.
Claude Code deprecated Opus 4.8 fast mode on Oct 30 and removes it Nov 30, 2026. Requests then error. Opus 5.5 fast costs $8/$40 per MTok - here is the fix.
Anthropic published how the Claude Code team reviews code at agent volume: layered checks, human approval scaled by risk, a round cap, and incidents as evals. What to copy.
The Claude Usage and Cost Analytics API beta reports token usage and cost by model, workspace, API key and user. How it works, the limits, and how to migrate.
Since Claude Code 2.1.311, typing ultrathink runs that turn at xhigh effort on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1. When it works, when it does not, and caps.
Anthropic filed its S-1 for a Nasdaq listing under ANT. The revenue and loss figures, the risk factors that touch API users, and what to change in your stack on Monday.
The Claude Tag API beta lets Enterprise admins turn Claude on per Slack channel, set instructions, models and guest policy, and attach Access bundles from code.
Claude Code 2.1.310 brings the Monitor tool and plugin monitors to Bedrock, Vertex and Foundry. How Monitor works, its limits and 30-minute cap, and the setup.
Claude vs Claude Code: one app for chat, docs and general work, one agent for your codebase. Same model family and shared plan limits, different jobs.
Anthropic used Claude to prove no-crash properties for 123 OSS-Fuzz libraries. What the proofs cover, where they stop, and the fuzz-target habits worth copying on Monday.
Claude Security now rescans repos as commits land, marks findings fixed when the fix ships, and adds an API, MCP connector and webhooks. Setup, limits and cost.
Claude Models on Google Cloud (Anthropic managed) is the full Claude API behind Google Cloud IAM and billing. Setup, the 2 services, IAM roles and SDK code.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.