[_345]

If you're okay with sonnet level performance, this sounds like a straight upgrade. But I find that sonnet messes up too much, that it ends up not being worth cost optimizing down to using it or another sonnet-level model. Glad to have this as an option though

[2ndorderthought]

A lot of people are having good experiences doing things like using opus for designing and using locally hosted qwen3.6 for implementation.

I could see a serious cost reduction story by using opus for design and deepseek for implementation.

Personally I would avoid anthropic entirely. But I get why people don't.

[girvo]

Like me: that’s what I do. Either Opus 4.7 or GLM 5.1 for planning, write it out to a markdown file, then farm it out to Qwen 3.6 27B on my DGX Spark-alike using Pi. Works amusingly well all things considered.

[brianjking]

How are you interacting with GLM 5.1? Via the Claude Code harness? I really wish they'd release a fully multimodal model already.

[girvo]

Through Pi, mostly! Also my own for-fun agent I wrote

Yeah so would I, I do miss having vision tools sadly.

[2ndorderthought]

How is glm 5.1? I have t tried it yet but have been meaning too

[girvo]

It's surprisingly good. Beats MiniMax 2.7 and Qwen 3.5 Plus in my testing (I haven't tested 3.6 plus though), quite handily. It's far better than Sonnet, and often equivalent to Opus for the web development and OCaml tasks I'm using it for. It definitely isn't Opus 4.7, but its far good enough to earn it's keep and is substantially cheaper.

[sshine]

I agree with this. And also: it uses more thinking time to reach this. So while you get a lot of tokens on their plan, the peak 3x token usage multiplier + the extra thinking means you run into the rate limit anyways.

[girvo]

True, though the $20 equivalent used for planning only I don’t hit those limits often, vs Claude where the Pro can literally hit limits with a single prompt haha

[amunozo]

Did you compare it with Kimi K2.6 and DeepSeek V4 Pro? I feel they're similar but as GLM is more expensive, I am not using it much.

[Alifatisk]

I second this, glm-5.1 is incredible.

[aftbit]

What hardware are you using to power this?

[girvo]

> DGX Spark-alike

Probably wasn't clear enough if you don't know what that is already, apologies

It's an Asus Ascent GX10, which is a little mini PC with 128GB of LPDDR5X as shared memory for an Nvidia GB10 "Blackwell" (kind of, it's a long story) GPU and a MediaTek ARM CPU

[aftbit]

Ah yeah I saw that, I was just curious which particular mini-PC you were using. I was considering picking up one of the various AI Max 395 boxes before the RAMpocalypse but didn't take the plunge. Thanks for the response!

[girvo]

I heavily considered one of the AMD Strix Halo boxes, but part of the reason I wanted this was to learn CUDA :)

[sterlind]

pulls up chair

could you tell me the long story?

edit: or wait, is it quasi-Blackwell the way all DGX Sparks are quasi-Blackwell? like the actual silicon is different but it's sorta Blackwell-shaped?

[girvo]

Yeah exactly. Shader model 121 is different to SM 120 (consumer Blackwell) and is different again to data centre Blackwell SM100.

The promise of this chip was “write your code locally, then deploy to the same architecture in the data centre!”

Which is nonsense, because the GB10 is better described as “Hopper with Blackwell characteristics” IMO.

Still great hardware, especially for the price and learning. But we are only just starting to get the kernels written to take advantage of it, and mma.sync is sad compared to tcgen05

[chrsw]

I keep re-learning this lesson: I chug along with a lesser model then throw a problem at it that's too complex. Then I try different models until I give up and bring in Opus 4.6 to clean up.

[energy123]

It's not even that much cheaper, GPT 5.5 is about 2x more expensive per task than Deepseek v4 Pro when you adjust for less token usage, according to Artificial Analysis. Doesn't seem worth it to me.

[cpursley]

Are we talking pay as you go API or vs plans?

[energy123]

Pay as you go API rates.

[brianwawok]

And I keep using Opus to like, make git commits. Really just need a smart router that is actually smart, vs having to micromanage model

[sterlind]

the problem is managing the contexts. your session might fit in Opus, but will that smaller model you dispatch the git commit to fit? even so, will it eat too much on prefill? do you keep compactions around for this, or RAG before dispatch or something? how do you button back up the response?

all doable but all vaguely squishy and nuanced problems operationally. kinda like harness design in general.

[maxdo]

This is the problem: you need the best model, not just a good one, for: - Good architecture, which requires reading specs, code, etc. reads like: lots of tokens in/out - Bug fixing — same, plus logs, e.g. datadog

Once you've found the path, patches are trivial and the savings are tiny unless you're doing refactoring/cleanup.

testing gets more and more complicated. Take a look at opencode go, and you see this:

>Includes GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2-Pro, MiMo-V2-Omni, MiMo->V2.5-Pro, MiMo-V2.5, Qwen3.5 Plus, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, >DeepSeek V4 Pro, and DeepSeek V4 Flash

and now on your own with bugs, all of these models can produce at scale. Am i missing anything in this picture. What is the real use of cheaper models?

[JSR_FDED]

I'd argue that you need the model that's good enough, not the best.

[maxdo]

any missed bug, any wrong architecture decision, is a huge loss, sure , if you run it as autocomplete on steroids you can get any Chinese model. If you try to move faster, and that is a conscious choice, any hiccup is a productivity loss and tons of tokens burned.

[Culonavirus]

We're not yet at a point of saturation when all the frontier models would be of somewhat comparable "intelligence" and we could decide which to use based on other factors (speed, effective context window etc.), so I honestly don't see why would you (as a company or an employee) not use the best available model with the highest (or at least second highest) thinking effort. The fees are not exactly cheap, but not that expensive either.

[nyssos]

Agreed that we're not at saturation, but we don't have a canonical "best" either. For example ChatGPT 5.5 + Codex is, in my experience, vastly superior to Opus 4.7 + Claude Code at sufficiently well-specified Haskell, but equally vastly inferior at correctly inferring my intent. Deepseek may well have its own niche, though I haven't used it enough to guess what it might be.

[willio58]

I don’t find this with sonnet at all. As long as I have a solid Claude.md and periodically review the output and enforce good code practices via basic CI gates I’ve rarely ever found myself having to switch to opus

[2ndorderthought]

You might be surprised then at how good cheaper models solve your problems

[mohsen1]

This has been my experience working on tsz.dev. Only Opus 4.7 and GPT 5.5 can really be productive for the remaining test cases.