Anthropic really pissed me off with their harness crap. They're well within their rights but their communication over it was enough to get me to swap. I don't need extra hurdles when there's a perfectly valid alternative right there. They don't have the advantage they think they do.
But if you’re stuck with no better model, it’s better than local models and no models.
I have to say, OpenCode’s OpenUI has taught me what modern TUIs can be like. Claude’s TUI feels more like it’s been grown than designed. I’m playing around with TUI widgets trying to recreate and improve that experience
Claude's TUI is not a TUI. It's the most WTF thing ever: the TUI is actually a GUI. A headless browser shipped the TUI that, in real-time, renders the entire screen, scrolls to the bottom, and converts that to text mode. There are several serious issues and I'll mention two that do utterly piss me off...
1. Insane "jumping" around where the text "scrolls back" then scrolls back down to your prompt: at this point, seen the crazy hack that TUI is, if you tell me the text jumping around in the TUI is because they're simulating mouse clicks on the scrollbar I would't be surprised. If I'm not mistaken we've seen people "fixing" this by patching other programs (tmux ?).
2. What you see in the TUI is not the output of the model. That is, to me, the most insane of it all. They're literally changing characters between their headlessly rendered GUI and the TUI.
> Claude’s TUI feels more like it’s been grown than designed.
"grown" or "hacked" are way too nice words for the monstrosity that Claude's TUI is.
Codex is described as a: "Lightweight coding agent that runs in your terminal". It's 95%+ Rust code. I wonder if the "lightweight" is a stab at the monstrosity that Claude's TUI is.
it goes into detail about llama-server args; quants to try; and layer/kv cache splits. I plan to try the techniques there.
Remember the old saying about boiling a frog? LLM corporations need to make most of their users pay hundreds per month, asap. This is Anthropic increasing temperature regulator under the pot just a tiny little bit. Not the first and not the last time.
> LLM corporations need to make most of their users pay hundreds per month, asap.
I think they need to at least have a 1 month introductory rate for the max plan at $20, or devs that decide to try out agentic coding just won't go to Anthropic.
That leads to downstream impacts, like when a company is deciding which AI coding tools to provide and the feedback management hears everyone is already used to (e.x.) Codex, then Anthropic starts losing the enterprise side of things.
I suspect a lot of people are like me. They got into this at the $20/month level individually to check things out. I'm not stressing things out, so I haven't moved up, but the moment I bump into a limit, I'll pull the trigger by default. Until then, I'm the sleeping dog, and you should let me lie.
Well, Anthropic decided to kick me. Now, I'm investing the time to figure out how to use the "open" and "Chinese" models assuming that Anthropic is about to screw me. Once I switch, Anthropic is going to have to demonstrate significant improvements over what I'm now using to get me to even consider them again.
Not according to their webpage: "Claude Code is included in your Pro plan. Perfect for short coding sprints in small codebases with access to both Sonnet 4.6 and Opus 4.7." [1]
> I'm a career engineer
I'm trying really hard here to be nice, but what the hell are you doing? Are you vibe coding multiple apps in parallel and calling it engineering?
Is it like those people who eat 2-3x the amount of meat to ensure they offset the positive impact 1-2 vegans are having? :D
I'm not challenging your opinion, but this is an outlier in the general current public opinion about it.
EDIT: it is also surprising to me that everyone seems to believe the people at Anthropic are simply incompetent and recklessly risking their good reputation, while very few consider the possible good reasons they might have for taking such drastic measures. And I don't think it's because of financial pressures in their case
When I threw it at a difficult issue in an iOS app, it like GPT came up with wrongly guessed explanations. It only found the issue after I had it instrument the app and add extensive logs. Usually GPT 5.4 is the same.
Only that with GPT 5.4 it’s at least included in my subscription, while sending 3-4 messages to Opus 4.7 for this blew through my $20 plan limits and consumed $10 of extra usage on top. At that point I can’t help but bring up how much more expensive it is.
Rest assured OpenAI won’t want to leave that kind of money on the table…
With that much competition and ongoing improvements, I don’t have such a pessimistic view on future usage limits and cost.
At the speed everything is advancing I don’t think it’s such an advantage. They all catch each other up pretty fast. That’s why I prefer to pay Cursors and have access to all of them instead of being lock to a single one (even if that means to lose some discounted credits). If they opened Mythos today at a good price that would be something but that’s not the case and it won’t happen.
That's not how you keep your customers. None of these agents have a moat, I moved away from Cursor when they started doing what Anthropic is doing now, and never went back even when I was a paying customer since the start.
Anthropic bleeds money per user. No matter if it's the $20 or $200 plan, every Claude Code user is unprofitable.
The only way to not bleed money is to eventually move everyone to API pricing. Hiring a personal senior engineer will likely be cheaper.
Yes, confirmed directly from Anthropic's website. Claude Code is included in the Pro plan, described as perfect for short coding sprints in small codebases with access to both Sonnet 4.6 and Opus 4.7. Claude
You said: Is claude code included with the pro subscription Is claude code included with the pro subscription
3:11 PM Claude responded: Yes, Claude Code is included with the Pro plan ($20/month). Yes, Claude Code is included with the Pro plan ($20/month). You can use it in the terminal, desktop app, VS Code, JetBrains, and on the web.
The main caveat is that Claude Code draws from the same usage limits as your regular Claude chat — so heavy coding sessions can eat into your quota faster. If you find yourself hitting limits often, the Max plans ($100–$200/month) offer significantly more headroom.
Thats a head scratcher:)
>$17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly.