I left Claude for months. Opus 5.5 is why I'm back

<p>I’ve been off Claude for months. Not because it got dumb, but because it got annoying. The rambling, the hedging, the preachy little disclaimers on tasks that didn’t need them. I moved most of my daily work to Codex and I didn’t miss it. Then Anthropic shipped Opus 5.5: 40% cheaper than Opus 5, faster, and with what they’re calling a fundamentally different alignment approach. I ran it for a week across real work, including four long-running agentic tasks, a full ChatPRD homepage redesign, an SVG benchmark, and one very firm refusal, and I’m ready to give you the honest verdict. There’s a lot to like. There are still two things that drive me a little crazy. And there’s one capability I genuinely wasn’t expecting.</p><p><br></p><p><strong>What you’ll learn:</strong></p><ol><li>Why I walked away from Claude entirely, and what it took for me to come back</li><li>The real cost math on Opus 5.5 and why pricing matters more for agentic work than single prompts</li><li>What happened when I ran four long-running agentic tasks, including one that tried to manipulate Claude mid-run</li><li>Why Opus 5.5 is now my go-to for frontend prototyping, and where it still lets me down</li><li>The one capability I genuinely didn’t see coming, and no other model in my stack can match it</li><li>The moment Opus 5.5 told me flat-out no, and what that says about where Anthropic’s safety posture actually lands in practice</li><li>Where Codex still wins, and how I’m splitting my model stack after a full week of testing</li></ol><p>—</p><p><strong>In this episode:</strong></p><p>(00:00) Why I stopped using Claude</p><p>(01:02) What Anthropic says Opus 5.5 is</p><p>(01:54) Cost, speed, and benchmark overview</p><p>(03:20) Safety, alignment, and the cybersecurity limits</p><p>(05:02) How I AI bench</p><p>(05:39) Voice test: is it actually not annoying?</p><p>(07:54) Long-running agentic task results</p><p>(10:50) Frontend prototyping</p><p>(17:23) Writing voice and email</p><p>(19:41) SVG illustrations</p><p>(20:46) Video editing</p><p>(21:42) My verdict: what it’s good at, what it still isn’t</p><p>—</p><p><strong>Tools referenced:</strong></p><p>• Claude Opus 5.5: <a href="https://www.anthropic.com/claude-opus-5-5">https://www.anthropic.com/claude-opus-5-5</a></p><p>• ElevenLabs MCP connector: <a href="https://elevenlabs.io/mcp">https://elevenlabs.io/mcp</a></p><p>• Codex (OpenAI): <a href="https://openai.com/codex">https://openai.com/codex</a></p><p>—</p><p><strong>Where to find Claire Vo:</strong></p><p>ChatPRD: <a href="https://www.chatprd.ai/">https://www.chatprd.ai/</a></p><p>Website: <a href="https://clairevo.com/">https://clairevo.com/</a></p><p>LinkedIn: <a href="https://www.linkedin.com/in/clairevo/">https://www.linkedin.com/in/clairevo/</a></p><p>X: <a href="https://x.com/clairevo">https://x.com/clairevo</a></p><p>—</p><p>Production and marketing by <a href="https://penname.co/">https://penname.co/</a>. For inquiries about sponsoring the podcast, email jordan@penname.co.</p>