DEV Community

# anthropic

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Claude Sonnet 4.6: Opus Performance at 1/5 the Cost (And Why You Should Migrate)

Claude Sonnet 4.6: Opus Performance at 1/5 the Cost (And Why You Should Migrate)

Comments
6 min read
🚨 Claude Sonnet 4.6 Just Dropped: The "Computer Use" Update We Were Waiting For

🚨 Claude Sonnet 4.6 Just Dropped: The "Computer Use" Update We Were Waiting For

1
Comments
3 min read
Benchmarking Vercel AI Gateway against the native Anthropic SDK

Benchmarking Vercel AI Gateway against the native Anthropic SDK

Comments
5 min read
LLM Structured Output in 2026: Stop Parsing JSON with Regex and Do It Right

LLM Structured Output in 2026: Stop Parsing JSON with Regex and Do It Right

Comments
15 min read
I Asked Claude About Its New Constitution. It Got Uncomfortable.

I Asked Claude About Its New Constitution. It Got Uncomfortable.

Comments
7 min read
16 AIs Built a C Compiler from Scratch: The Dawn of Autonomous Software Engineering

16 AIs Built a C Compiler from Scratch: The Dawn of Autonomous Software Engineering

1
Comments
2 min read
🚀 Claude Just Broke the Speed Limit: Meet "Opus 4.6 Fast"

🚀 Claude Just Broke the Speed Limit: Meet "Opus 4.6 Fast"

1
Comments
3 min read
AI News Roundup (Feb 8, 2026): Agent Teams, GPT‑5.3 Codex, and the GPT‑4o Farewell

AI News Roundup (Feb 8, 2026): Agent Teams, GPT‑5.3 Codex, and the GPT‑4o Farewell

1
Comments
3 min read
Measuring Model Hallucinations: When AI Invents Facts

Measuring Model Hallucinations: When AI Invents Facts

1
Comments
3 min read
Claude 4.6 Opus: Advanced Reasoning or a New Monitoring Nightmare?

Claude 4.6 Opus: Advanced Reasoning or a New Monitoring Nightmare?

1
Comments
2 min read
Measuring Model Overconfidence: When AI Thinks It Knows

Measuring Model Overconfidence: When AI Thinks It Knows

1
Comments
3 min read
Claude Opus 4.6: 1M context, stronger agentic coding, and what it means for builders

Claude Opus 4.6: 1M context, stronger agentic coding, and what it means for builders

1
Comments
2 min read
GPT‑5.3‑Codex vs Claude Opus 4.6: benchmarks, cost, and workflow tradeoffs

GPT‑5.3‑Codex vs Claude Opus 4.6: benchmarks, cost, and workflow tradeoffs

1
Comments
3 min read
Claude Code Agent Teams: the missing UX for real multi-agent development

Claude Code Agent Teams: the missing UX for real multi-agent development

Comments
2 min read
The Repository That Tracks Everything You Ask Claude: A Story About Header Injection in Claude Code

The Repository That Tracks Everything You Ask Claude: A Story About Header Injection in Claude Code

Comments
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.