Anthropic

Latest AI news, models and releases from Anthropic. ['anthropic-ai', 'Anthropic AI Models', 'Claude', 'Claude 2', 'Claude 2.1', 'Claude 3', 'Claude 3.5 Sonnet', 'Claude-3.5-Sonnet', 'Claude 3.5 Sonnet v2', 'Claude 3.7 Sonnet', 'Claude 3 Haiku', 'Claude 3 Opus', 'Claude3 Opus', 'Claude 3 Sonnet', 'Claude 4', 'Claude 4.6', 'Claude 4 Opus', 'Claude 4 Sonnet', 'Claude 5', 'Claude Agent SDK', 'Claude.ai', 'Claude AI', 'ClaudeBot', 'Claude Code', 'Claude Code (Opus 4.7)', 'Claude Code Sonnet 5', 'Claude Cowork', 'Claude Design', 'Claude Desktop', 'Claude Fable', 'Claude Fable 5', 'Claude Fable5', 'Claude Fable 5 Max', 'Claude Haiku', 'Claude Haiku 4.5', 'Claude Instant', 'Claude (language model)', 'Claude Max', 'Claude Mythos', 'Claude Mythos 5']

Official site ↗

Agents 🇷🇺

LLM Schizophrenia: A Vibe Coder's Cookbook

An experienced developer shares a workflow for using AI agents to write large production code. By creating specialized subagents with distinct roles, clean contexts, and restricted tools, the author prevents context degradation and improves code quality. The approach includes skills (process files), planning, rules, and automated checks.

Anthropic

Habr — хаб ИИ02.08 · 11:01

Business & Market 🇷🇺

AI at 300 Hours? The Estimate Is Below the Industry Floor: A Three-Method Cross-Check

An IT specialist's estimate of 300 hours for a business accounting system upgrade was challenged by the client, who claimed AI could do it in an evening. The specialist recalculated the scope using three independent methods, revealing his own estimate was below the lowest industry benchmarks. The 412 function points would actually take between ~990 (low-code 90th percentile) and ~12,400 hours (COCOMO II nominal), according to ISBSG data.

Anthropic

Google/DeepMind

Habr — хаб ИИ02.08 · 10:01

Show more ↓