All Technologies
AI & ML·expert

Claude

Anthropic's flagship model family

Claude is Anthropic's model family - Opus, Sonnet, Haiku - covering frontier reasoning down to fast, cheap inference. It's my default for long-context and code-heavy tasks.

2+years in production
30+projects shipped
expertproficiency

My take

Why I use Claude

Claude - especially Opus on long context - handles tasks GPT-4 doesn't reliably. The 1M context window genuinely changes what's possible, and the tone and judgment are calibrated well for production.

Want the broader stack philosophy? Read about how Sri picks tools or browse engineering insights.

Honest assessment

Strengths & tradeoffs

No tool is perfect. Here's what shines and what to watch for.

Strengths

  • 1M-token context on Sonnet/Opus tiers
  • Strong long-document reasoning
  • Excellent code generation and review
  • Tool use and computer use
  • Three-tier model family for cost/speed tradeoffs

Tradeoffs (honestly)

  • Top-tier models are expensive per token
  • Streaming and structured output APIs evolve quickly
  • Some integrations still OpenAI-first

Fit assessment

When to reach for Claude

Pick the right tool for the job.

Best fits

Reading entire codebases or large doc sets

Coding assistants and Claude Code workflows

High-stakes enterprise reasoning

Long-running agents with tool use

Not ideal for

Image generation

Hyper-low-latency completion at scale (consider Haiku or smaller models)

Common use cases

Long-context analysisCode reviewAgentic workflowsEnterprise chat

Resources

Learn more

Curated official docs, tutorials, and writing on Claude.

Need help with Claude?

Whether you're starting fresh or optimizing an existing implementation, I can help you get the most out of this technology. Read more in insights or get in touch.

Command Palette

Search for a command to run...