Robert Ta and colleagues Jonathan and Powell fixed Claude Opus 5's repeated failures by writing eight specific rules into a single prompt. The model kept misreading emails and botching summaries until they used intent engineering to decompose what they needed into concrete instructions, turning it from unusable to mostly functional.
Claude Opus 5, the best Opus yet once you heal it. So I got this in my inbox and I sent it to Jonathan and Powell also goes through the same experience. At first I love the Wiz 5 and then I used it for a few days. The more I worked with it, the less I liked it. I'm going to cancel Claude. It's just so bad. I can't believe it. It's just lazy. The most recent example, I have Claude check my inbox for important emails, summarize them, work with them, and send out replies if necessary. I caught Claude again simply not reading The email. There are lots of other complaints here. And so Powell is like, hey, you can heal this. And he never switched away from Opus 5. Every time a failure repeated, he wrote a rule that stopped it, then kept working. After 2 weeks, 8 blocks of the Claude MD survived.
So at the bottom, he summarizes all the intent engineering into like one copy and paste prompt. And I put that in my user level Claude MD, not the repo level, but the user level. And it was pretty funny. I actually used an Opus 5 session to like update the system prompt. And then it said, okay, it asked me to do something. And I said, well, given the new rules we just talked What do you think about that? Do you think you can figure it out? And it said, yes, I can. And it turned out to be of the form of like, I can make a cheap reversible change and see if it works and it won't cost anything. And then I can solve the problem. I was like, yeah, we'll do that. And it did it. And it was like, kind of like this trained haplessness that it has. All of a sudden it's like, wait, it had a new tool to like rethink how to do it. So I've seen that in a few of my Opus sessions now where it's just like these little nudges on the intent engineering. And by the way, this guy just did a great job working with the model, decomposing its intent into a prompt that is actually like visibly improves the model. I think that's like a really strong skill that this guy demonstrated, the intent engineering. But, uh, yeah, anyway, the fix works for the most part. Opus 5 is mostly usable now with this fix.
