291–300 of 367 posts
Pretty clearly it's beating Opus at [web dev]( https://www.gptbased.com/ ) - on price, on score.. I mean what else is there?
I hate to be that guy, but real privacy policy on training data/it being hosted somewhere where I'm not worried about secrets being stored/leaked.
Earlier quoted context omitted.
Take a look at Ollama Cloud: https://ollama.com/pricing You get access to a whole bunch of bleeding edge open models including GLM-5.2, Kimi K2.7, DeepSeek 4 Pro, etc. Inference is run on US/SG/EU cloud providers with zero data retention policies. The $20/mo tier is very generous, in my experience.
They don’t have a statement about where it is run or data retention on the GLM5.2 model. They do state that for others, like MiniMax.
> Where are models hosted?
> Ollama hosts models and compute resources primarily in the United States. To serve global demand, we may route to Europe and Singapore for additional capacity.
> Is my prompt or response data trained on?
> Prompt or response data is never logged or trained on.
> Who does Ollama partner with to host models?
> Ollama collaborates with NVIDIA Cloud Providers (NCPs) to host open models.
> When Ollama partners with providers, we require no logging, no training, and zero data retention policies in place.
I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…
> So we ran it head-to-head against Claude Opus 4.8: same one-shot prompt, build a 3D platformer in raw WebGL from scratch Running a single one-shot prompt is not a benchmark, not is it representative of any sort of real-world usage. Most agent usage is collaborative so you need to test things like reliability (when I delegate a task, does it complete it without making up test results for e.g.) and steerability (does…
At home I make a point of trying other models / tools on my side projects. So I've been using OpenCode and trying tons of models via OpenRouter. I tried Kimi, Deepseek, MiMo, etc.
GLM 5.2 is a _major_ step up from every other non-GPT/Claude/Gemini model I've tried. It's not as good as latest Claude Opus, but it feels every bit as good as Opus from ~4 months ago at a fraction of the price.
To me this model is the "it just works" moment for open weights models. We had this for closed weights models in late 2025 when Opus 4.5 landed. This is the same feeling I'm having with GLM 5.2. It's 90% as good as what I get from Anthropic for 1/5th of the cost and without any concern of lock-in.
I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…
What about: take top 3 feature requests, top 3 bug reports for 3 popular open source projects and ask to solve those based on the issue contents and access to the project repos.
Even if you stay in a single prompt scenario, you could make it more realistic.
> Through an API it costs a fraction of Opus, and you can run it yourself for free if you have the hardware. I haven't been keeping up on hardware costs for state of the art LLM inference, but this remark made me ask myself how many readers of the article would actually be able to run this model on hardware they own. How much would it cost to acquire such a setup?
This framing local LLMs as free is stupid. Basically pay 100+ months worth of API costs up front isn't free in the slightest. And it will be slower than non-local, your hardware will be outdated in 12 months and probably won't be able to run SOTA at anywhere near non-local speed in max 20 months
You're better off setting a budget and buying the best machine you can afford in that range, or picking a VRAM target and accepting the class of models you can run on it. Those models will almost certainly improve over time and your skills will adapt to the limitations. Hardware is so valuable right now that it's not even likely to be a significant loss if you had to sell.
Right now I think 24 GB is probably the best bang for your buck (used 3090), because you also get a high end gaming/gpgpu device which is nice anyway. 32 GB you can do with AMD or Intel, but NVIDIA is megabucks and at this point you're really paying for RAM. Unfortunately the ship has sailed on "reasonably" priced RTX 6000s, which at one point were about $7k and are being listed at $10k++.
I feel like another comparison worth looking at is purely cost. Capability per dollar is something I care about: Opus API $5/$25 Sonnet API $5/$15 Haiku API $1/$5 GLM 5.2 API $1.4/$4.4 So you're really getting near opus level capability for the price of haiku .
Not really, GLM uses more tokens to get work done.
Earlier quoted context omitted.
I don’t think we need them. I think the models we have are good enough. It’s the orchestration layer that makes the biggest difference at this point. The open source models we have are capable of calling tools and the work is getting them to be capable enough to know which tools to call and what to do in response. I think we are leaving the main frame era of AI and entering the PC era already. If there wasn’t a RAM s…
They are absolutely not good enough
I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…
IMHO, It's not the oneshotting. It's the "starting from empty slate" greenfield that's the real problem. We used to make fun of Engineers who follow a README on a framework, test it on an empty project, and say "this framework is the best for our 10 year running production app". Greenfield mentality is always the solution to all problems and problem to all solutions. One should still measure oneshotting, it's an impo…
That issue, and the issue of "aesthetics", are the biggest complaints I have today. I don't know exactly how to define aesthetics, but it's when AI is making decisions that no experienced developer or designer would. They may be functionally correct but "ugly" to another developer or and end user.
An example is an case I ran in to yesterday where parsing a config, and failing and logging on a configuration error. It logged a specific item where the config was invalid but not what group or any notion of where in the config this error was. Of course, specific item names could be duplicated in different parts of the config. It's small, but correcting these minor things take time and they are the types of decisions no one would have made who had any experience writing code and debugging a config problem. This was Opus 4.8/max too.