ANTHROPIC
151 items
143 posts, 7 tools, 1 guide
Claude API version 2026-10-21 removes temperature, top_p and top_k, and new major SDKs (TypeScript 1.0, Python 2.0) send it by default. What breaks and how to migrate.
Claude Code Review now has three review levels. How Quick, Standard and Deep trade depth for cost, how to set them per repo, and how to budget before rollout.
Claude Inference hooks left beta for Enterprise on Oct 20. How the prompt and tool call frames work, how to verify signatures, and a TypeScript verdict server.
Every scheduled AI model API shutdown through mid 2027 by month: GPT-4o on Jan 14, whisper-1 on Feb 26, Claude Sonnet 4.5 on Nov 30, plus how to migrate.
Amazon Bedrock ends Claude 3 Haiku, 3 Sonnet, 3.5 Sonnet, 3.5 Sonnet v2 and 3.7 Sonnet in seven Regions on November 13, 2026. The dates, the new model ids, the prices and the code change.
Prompt caching across OpenAI, Anthropic, Gemini, DeepSeek, Mistral, xAI and Qwen: prices, TTLs, setup code. A reused 100K prefix costs 71-93% less.
Anthropic Python SDK 1.0 swaps httpx for httpx2, requires Python 3.10+, and drops temperature and Text Completions. Verified steps to upgrade safely.
Claude API inline tools beta: define, reshape or upgrade a tool mid-conversation with one system message and keep the prompt cache. Code included.
The Claude API exports OpenTelemetry traces in beta. Set up SDK spans in TypeScript or Python, add a Console destination for API spans, and count tokens once.
Claude Code v2.1.257 points /model fable at Fable 5.1: 1M context, $10/$50 per MTok, $0.25 cache reads. Setup, gotchas, and when Opus 5.5 wins.
Claude Code 2.1.299 compacts sessions over 200K tokens after about 54 idle minutes. How the cache math works, the setting to turn it off, and when to keep it.
Claude Code now reports prompt cache hit ratio and miss causes in /usage. How to read it, script a status line, and set 5m or 1h TTLs.
Claude computer use is GA as computer_toolset_20260801: no beta header, batched actions, zoom on. How to call it, migrate, and write an SDK driver.
Claude Fable 5.1 keeps $10/$50 pricing but cuts cache reads to $0.25/MTok. The three breaking API changes, new betas, and when Opus 5.5 is enough.
Claude Managed Agents can now write workflows that fan out up to 1,000 agents server-side. How to enable workflow runs, follow events and cap spend.
Anthropic's Frontier Red Team says small open models may be months from self-replicating across cheap IoT devices. What it measured and where the claim is thin.
Anthropic Scion replaced git after merges grew to over 30,000 a day. What Anthropic's post says, what HN pushed back on and what to apply to your own repo.
Claude Code Projects is open to waitlisted Pro and Max users. How the coordinator and cloud threads work, what they cost in plan limits and where it breaks.
Claude for Startups paused its free Claude Team year and $1,000 API credit offer at capacity. What the program page says now and how to cover the gap.
ai-newtab runs a Claude Managed Agents session from a Chrome extension to build a daily homepage. How the loop works, the cost claim, and the security gaps.

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