News for hackers. Stuff that matters.
Re:Claude Code removed from Anthropic's Pro plan by operatingthetan on Tuesday April 21, 2026 @06:07PM (#47855221)
I think we are inevitably heading to using the cheap Chinese models like Kimi, GLM, and Minimax for the bulk of engineering tasks. Within 3-6 months they will be at Opus 4.6 level.
Re:Claude Code removed from Anthropic's Pro plan by maxnevermind on Tuesday April 21, 2026 @08:16PM (#47856792)
Anthropic will kick and scream as those are often distilled from their latest models. Though it is not like their hands are clean neither, it is just a different type of stealing, an approved one :-)
Re:Claude Code removed from Anthropic's Pro plan by robertkarl on Tuesday April 21, 2026 @06:11PM (#47855269)
This was literally my task today, to try out Qwen 9B locally on my, albeit a bit memory-constrained at 18GB, macbook with pi or opencode. Before reading this update.
Re:Claude Code removed from Anthropic's Pro plan by operatingthetan on Tuesday April 21, 2026 @06:14PM (#47855302)
Minimax coding plan is $10 a month for roughly 3x the $20 Claude Pro CLI usage allowed. That would be good place to start. 200k context though.
Re:Claude Code removed from Anthropic's Pro plan by jorjon on Tuesday April 21, 2026 @06:26PM (#47855439)
MiniMax has its own issues. Server overloads, API errors, and failure to adhere to even the system prompt. It can happily work for hours and get no job done.
Re:Claude Code removed from Anthropic's Pro plan by sincerely on Wednesday April 22, 2026 @04:41AM (#47860800)
Just like me :)
Re:Claude Code removed from Anthropic's Pro plan by someuser54541 on Tuesday April 21, 2026 @06:22PM (#47855376)
Please report back, would be very interested in your findings.
Re:Claude Code removed from Anthropic's Pro plan by robertkarl on Tuesday April 21, 2026 @07:23PM (#47856197)
For what it's worth: here's my experience in the first 10 minutes of using Qwen locally to write some code. https://github.com/robertkarl/local-qwen-first-10-minutes it includes some token generation numbers and steps to repro.
Re:Claude Code removed from Anthropic's Pro plan by sshine on Tuesday April 21, 2026 @07:09PM (#47856019)
I ran OpenCode + GLM-5.1 for three weeks during my vacation. It’s okay. It thinks a lot more to get to a similar result as Claude. So it’s slower. It’s congested during peak hours. It has quirks as the context gets close to full.

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

Re:Claude Code removed from Anthropic's Pro plan by taikon on Tuesday April 21, 2026 @07:23PM (#47856193)
To be clear, was OpenCode a better in your opinion compared to ClaudeCode?
Re:Claude Code removed from Anthropic's Pro plan by sshine on Wednesday April 22, 2026 @05:24PM (#47869468)
Better UI, worse model (GLM), probably slightly worse agentic runtime.

In spite of how glitchy Claude feels, it makes decisions fast.

Re:Claude Code removed from Anthropic's Pro plan by TacticalCoder on Tuesday April 21, 2026 @07:25PM (#47856220)
> 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.

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.

Re:Claude Code removed from Anthropic's Pro plan by hank2000 on Tuesday April 21, 2026 @06:14PM (#47855309)
how was it? I'm doing this today
Re:Claude Code removed from Anthropic's Pro plan by robertkarl on Tuesday April 21, 2026 @06:27PM (#47855452)
I will report back... but I have to recommend this comment on a post about Qwen 3.6 https://news.ycombinator.com/item?id=47843466 by daemonologist

it goes into detail about llama-server args; quants to try; and layer/kv cache splits. I plan to try the techniques there.

Re:Claude Code removed from Anthropic's Pro plan by try-working on Tuesday April 21, 2026 @06:26PM (#47855445)
Kimi K3 in July-September is the big one.
Re:Claude Code removed from Anthropic's Pro plan by kzisme on Tuesday April 21, 2026 @07:20PM (#47856153)
How challenging are these to setup locally and have them running?
Re:Claude Code removed from Anthropic's Pro plan by operatingthetan on Tuesday April 21, 2026 @08:18PM (#47856820)
Getting them running is easy (check out LMstudio or ask one for some recommendations). The real question is whether you have the hardware to make them run fast enough to be useful.
Re:Claude Code removed from Anthropic's Pro plan by kzisme on Wednesday April 22, 2026 @12:13AM (#47858917)
The min req is probably crazy I assume but I'll take a peek :)
Re:Claude Code removed from Anthropic's Pro plan by muyuu on Tuesday April 21, 2026 @08:43PM (#47857117)
Kimi 2.6 works roughly like Opus 4.6, when it used to work. Depending on the task, a bit better or a bit worse. And it's MUCH cheaper.
Re:Claude Code removed from Anthropic's Pro plan by toasty228 on Wednesday April 22, 2026 @08:21AM (#47862556)
From this morning: I had a single go file with like 100 loc, I asked it to add debug prints, it thought for 5+ minutes, generating ~1m output token and did not actually update my file.
Re:Claude Code removed from Anthropic's Pro plan by slopinthebag on Wednesday April 22, 2026 @12:32PM (#47865903)
Which harness? Did you use OpenRouter?
Re:Claude Code removed from Anthropic's Pro plan by AussieWog93 on Wednesday April 22, 2026 @06:07PM (#47869915)
This is possibly a hot take but recently I've been having about as much luck with Composer 2 in Cursor as I have with Opus 4.6 in Claude Code.

Opus is obviously the better model, but Cursor's "harness" is doing so much heavy lifting in terms of just magically supplying the broader context the model needs to understand the ramifications of its edits.