| ▲ | operatingthetan 4 days ago |
| 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. |
|
| ▲ | robertkarl 4 days ago | parent | next [-] |
| 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. |
| |
| ▲ | operatingthetan 4 days ago | parent | next [-] | | 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. | | |
| ▲ | jorjon 4 days ago | parent [-] | | 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. | | |
| |
| ▲ | someuser54541 4 days ago | parent | prev | next [-] | | Please report back, would be very interested in your findings. | | |
| ▲ | sshine 4 days ago | parent | next [-] | | 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 | | |
| ▲ | TacticalCoder 4 days ago | parent | next [-] | | > 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. | |
| ▲ | taikon 4 days ago | parent | prev [-] | | To be clear, was OpenCode a better in your opinion compared to ClaudeCode? | | |
| ▲ | sshine 3 days ago | parent [-] | | Better UI, worse model (GLM), probably slightly worse agentic runtime. In spite of how glitchy Claude feels, it makes decisions fast. |
|
| |
| ▲ | robertkarl 4 days ago | parent | prev [-] | | 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. |
| |
| ▲ | hank2000 4 days ago | parent | prev [-] | | how was it? I'm doing this today | | |
|
|
| ▲ | try-working 4 days ago | parent | prev | next [-] |
| Kimi K3 in July-September is the big one. |
|
| ▲ | muyuu 4 days ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | toasty228 4 days ago | parent [-] | | 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. | | |
|
|
| ▲ | maxnevermind 4 days ago | parent | prev | next [-] |
| Anthropic will kick and scream as those are often distilled from their latest models and is cutting into their margin. Though it is not like their hands are clean neither, it is just a different type of stealing, an approved one :-) |
|
| ▲ | kzisme 4 days ago | parent | prev | next [-] |
| How challenging are these to setup locally and have them running? |
| |
| ▲ | operatingthetan 4 days ago | parent [-] | | 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. | | |
| ▲ | kzisme 4 days ago | parent [-] | | The min req is probably crazy I assume but I'll take a peek :) |
|
|
|
| ▲ | AussieWog93 3 days ago | parent | prev [-] |
| 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. |
