Skip to main content

Documentation Index

Fetch the complete documentation index at: https://plantis.ai/llms.txt

Use this file to discover all available pages before exploring further.

Original: Lenny Rachitsky · 28/05/2026

Summary

Lenny Rachitsky reviews Anthropics’ Claude Opus 4.8, highlighting its strengths in prototyping and weaknesses in edge cases and hallucinations.

Key Insights

“Where Opus 4.8 excels: greenfield prototypes, one-shot features, and fast execution” — Summary of the strengths of Opus 4.8.
“Where it struggles: the last 10%, edge cases in existing codebases, and hallucinations” — Summary of the weaknesses of Opus 4.8.
“Why I’m still reaching for Opus 4.7 on data-heavy strategy and roadmap work” — Comparison of Opus 4.8 with its predecessor in specific tasks.

Topics


Full Article

I got a few hours of early-access testing with Anthropics newly released model Opus 4.8. I walk through real coding, design, and strategy tasks across Claude Code and Claude Cowork, and give you my unfiltered view on what impressed me and what didnt.Listen or watch on YouTube, Spotify, or Apple PodcastsWhat youll learn:Where Opus 4.8 excels: greenfield prototypes, one-shot features, and fast executionWhere it struggles: the last 10%, edge cases in existing codebases, and hallucinationsHow Opus 4.8 compares to Opus 4.7 on business strategy workWhy Im still reaching for Opus 4.7 on data-heavy strategy and roadmap workThe new features shipping alongside the model: dynamic workflows with parallel subagents and effort control in Claude.ai and CoworkThe prompting and harness strategy Id use to get the most out of itIn this episode, we cover:(00:00) Introduction to Opus 4.8(00:44) Benchmark performance and pricing(01:53) First coding test: Building a prototyping tool(03:00) Where it failed: The last 10% problem(03:27) The hallucination problem(04:23) Testing Opus 4.8 on existing codebases(05:24) The ambition test: Building games for a 9-year-old(07:03) Business strategy test: 4.7 vs 4.8(08:23) The roadmap test(09:17) Final verdictReferences: System Card: Claude Opus 4.8: https://cdn.sanity.io/files/4zrzovbb/website/c886650a2e96fc0925c805a1a7ca77314ccbf4a6.pdf Introducing Claude Opus 4.8 on X: Where to find Claire Vo:ChatPRD: https://www.chatprd.ai/Website: https://clairevo.com/LinkedIn: https://www.linkedin.com/in/clairevo/X: https://x.com/clairevoProduction and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Claude Opus 4.8: “a modest but tangible improvement”

Simon Willison · explanation · 78% similar

How the engineer behind Claude Cowork actually uses Claude | Felix Rieseberg (Anthropic)

Lenny Rachitsky · how-to · 77% similar

Claude Opus 4.6 vs. GPT-5.3 Codex: How I shipped 93,000 lines of code in 5 days

Lenny Rachitsky · explanation · 76% similar