In this monologue, Robert Ta delivers a pointed criticism of Anthropic’s Opus 5 model, describing it as increasingly frustrating the more it is used. He notes that Opus 5 frequently goes off‑track, generates unsolicited or random content, forgets prior context, and is hampered by overly aggressive guardrails. Ta contrasts it unfavorably with GPT‑5.6, calling the latter “worlds better,” and cites broader community complaints that Opus 5 is overly verbose, low‑agency, and seems designed to inflate token usage ahead of Anthropic’s IPO. He references tweets from users and Claude developers highlighting these issues. Ta then shifts to practical advice for AI builders: enabling Claude Code’s new “concise” output style via configuration (output‑style = concise in settings.json) to curb verbosity, and adding a “Technical Simplified English” setting to improve readability. He shares his personal workflow of keeping some sessions on Opus 4.8 because it remains more usable than the newer release. The overall message is a call to adapt default settings to mitigate Opus 5’s shortcomings rather than abandoning the model entirely.
Chapters
This is a tweet from Chubby. I thought it was just me. Opus 5 is the first model that the more I use it, the worse I like it. That's a very strong statement. It goes off track, does random things I didn't ask for, forgets other things, and constantly has those annoying guardrails, et cetera. Sorry, but GPT-5.6 is worlds better. I really don't understand it anymore. What's going on at Anthropic? Sonic 5 was already a bad release, and since Opus 4.6, I feel like the subsequent Opus models have simply declined significantly in quality. My enthusiasm for Opus 5 definitely evaporated. And just following on that, Opus 5 is actually worse than any model Anthropic has released thus far. Nothing comes close to how much this shit model constantly wants your approval, how it goes off and do random things instead of the thing you ask to do, how it just assumed things will take months. Hug. And somebody here, Prototype, says, same experience. It seems to work better as a subagent of Fable. Using it as a main orchestrator has been terrible for me, even on simplish tasks. Also close to impossible to discuss technical work with it as it compresses concepts into compound nouns at a ridiculously high level, barely intelligible at times. Yes. It creates new words, new combinations of words all the time. There's so many new Claude-isms that have come out with this, and it's really interesting to see the CEO, Dario, smelling his own farts, believing that he hasn't been negative about Any of his AI takes and how the public's perception is like, oh yeah, people are negative about AI. It's not my fault. That is exactly what Opus 5 is like. It's like, hey dude, go look at what you did. And it's like, no, no, it was fine. I think the key things here are there's a lot of sustained user complaints about Opus 5's durability. It's kind of low agency. It's very verbose. It makes me as a user feel like, okay, did they make this thing more verbose just to stack tokens? On their side, to look like their books are better than they are in for their incoming impending IPO. I don't know. Here's another tweet from Claude Devs. You can now set Claude Code's output style to concise. The whole of AI Twitter blew up about the Opus Five release, saying that it was such a bad model. We agree. So Claude now has a config. So go try it out. If you're an AI builder, please go try this out in Opus Five. If you're using it for any sort of development and you want to minimize your token spend as well as maximize your understanding because Claude kind of be a damn. In Opus 5 and very verbose and kind of low agency. I find this makes it easier for me to understand. It lowers the amount of prose and verbosity. So turn it on in /config/output-style or set output-style to concise in settings.json. And this is what it's going to look like. So if you're an AI builder, check this out. Let us know what you think of it. I also would recommend adding technical simplified English to your Claude MD personal harness in your global settings. That's really helped my sessions with Cloud Code with Opus 5 go a lot better, though I do still have some sessions with Opus 4.8 that I'm liking a lot more, which is funny. I'm like not upgrading those sessions. I'm like, stay here, don't restart to update, stay with Opus 4.8.
