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

September 22, 2026

AI Summary

5 min read

The host of How I AI opens with a confession: they abandoned Claude for months. Not because the models lacked intelligence, but because interacting with Claude became genuinely frustrating. The host describes "Claude Slop"—rambling, unnatural responses that made simple conversations feel like pulling teeth. After switching to other tools, they had all but written off the platform. Then Anthropic released Claude Opus 5.5, and the host got early access. The central question they set out to answer is not about benchmarks or pricing, but something more visceral: "Is it annoying?" The answer, they report, is a qualified no. Opus 5.5 is back in their workflow.

What Opus 5.5 actually is

Anthropic positions Opus 5.5 as delivering "Fable-level performance" at roughly 40% less cost than Opus 5, and about 30% faster. The pricing is $4 per million input tokens and $20 per million output tokens, with a fast mode at $8 and $40. It beats Opus 5 on Anthropic's own benchmarks, matches GPT-6 Astra (the host's previous favorite), and undercuts Sonnet at a third of the cost. But the host is clear: benchmarks are not the story. The story is whether the model feels better to use.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **Why I Abandoned Claude** - The host explains they stopped using Claude for months due to "Claude slop"—annoying, rambling, unnatural responses that made their "blood boil."
2 (01:02) **Opus 5.5 Pitch: Back, Baby** - Anthropic's new model is cheaper (40% less than Opus 5), faster, and claims near-Fable-level performance—but the host only cares about one question.
3 (03:18) **The Annoying Test: Is It Still a Scold?** - Opus 5.5 is "minimally annoying"—a huge improvement—but Claude remains "square" and safety-conscious, which shapes its personality.
4 (05:40) **Voice Test: Not Annoying, But Quiet** - In voice interaction, Opus 5.5 is straightforward and GPT-like, but it sometimes goes silent for minutes during long tasks, creating perceived latency.
5 (07:55) **Long-Running Agentic Tasks: All Succeeded** - The model completed all four long-running agentic tasks (inbox triage, backend feature, research, computer use) without failure, using 25–82 steps per task.
6 (10:26) **Adversarial PR Reviewer** - The host now uses Opus 5.5 as an adversarial reviewer for PRs and work from GPT, and vice versa, enabling parallelization.
7 (10:51) **Front-End Prototyping: Where Claude Shines** - Opus 5.5 crushed a homepage redesign, producing a much bolder, more visual layout that the host plans to ship.

+ Full timestamped outline available in the app

Show Notes

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.

What you’ll learn:

Why I walked away from Claude entirely, and what it took for me to come back
The real cost math on Opus 5.5 and why pricing matters more for agentic work than single prompts
What happened when I ran four long-running agentic tasks, including one that tried to manipulate Claude mid-run
Why Opus 5.5 is now my go-to for frontend prototyping, and where it still lets me down
The one capability I genuinely didn’t see coming, and no other model in my stack can match it
The moment Opus 5.5 told me flat-out no, and what that says about where Anthropic’s safety posture actually lands in practice
Where Codex still wins, and how I’m splitting my model stack after a full week of testing

—

In this episode:

(00:00) Why I stopped using Claude

(01:02) What Anthropic says Opus 5.5 is

(01:54) Cost, speed, and benchmark overview

(03:20) Safety, alignment, and the cybersecurity limits

(05:02) How I AI bench

(05:39) Voice test: is it actually not annoying?

(07:54) Long-running agentic task results

(10:50) Frontend prototyping

(17:23) Writing voice and email

(19:41) SVG illustrations