Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ox-Alpha Is GLM?

dejan.ai

Post reply on HN
Print view View original

61–70 of 75 posts

Re: Ox-Alpha Is GLM?

#61

Post by SyneRyder »

gvkhna wrote: post #40
mogili wrote: post #18

It's not a good model tbh, got a bunch of things wrong that Opus corrected in my codebase.

The harness is making a big difference, lackluster performance with pi but somehow very good performance with opencode. There’s some rl there for sure, for a smaller model it’s likely going to perform much better in a harness it understands the best.

I've been using a harness that I made myself, and making improvements to the harness has vastly improved its performance. It's actually been a useful model to identify flaws in the harness.

I think something also went wrong with the Ox provider last night (at least on OpenRouter), for a few hours it wouldn't accept tools. Zero change to the harness while I slept and it was back working again the next morning.

Re: Ox-Alpha Is GLM?

#62

Post by dejanseo »

jerrythegerbil wrote: post #16

As someone who uses NCD nearly every day, I have concerns about how it’s been used here. But while we’re “guessing”: Xiaomi MiMO

Author here. Tell me more. How do you use NCD and what is your concern about its application here? Should I have use da larger reference sample? You can test it in action here: https://dejan.ai/tools/ai/ (e.g. drop a claude article or GLM article in and see what it says, it's not perfect but reasonably good).

Re: Ox-Alpha Is GLM?

#63

Post by dejanseo »

tadkar wrote: post #25

I wonder if the NCD metric says something about distillation too. Would you expect that a model that has been distilled/seen traces from other models would have a smaller NCD? It would be really interesting to see if this holds up and provides evidence of distillation or certainly evidence of model outputs being used in the training mix.

Hello! I wrote the above article and did the NCD on model outputs. The same thought crossed my mind when I saw Gemma misclassified as Gemini quite frequently. And GLM almost as Claude and not as Gemini at all. Gave me the feeling as if GLM didn't train on Gemini generated synthetic data at all but mainly on Claude and GPT.

Re: Ox-Alpha Is GLM?

#64

Post by dejanseo »

swiftcoder wrote: post #43

> How many words are in the previous message? Its amazing to me that providers haven't added any sort of masking of the prompt in the thinking traces to avoid prompt extraction via this sort of trivial attack

Hey, it may be trivial, I'm pretty proud of it :)

Re: Ox-Alpha Is GLM?

#65

Post by dejanseo »

krackers wrote: post #32
tadkar wrote: post #25

I wonder if the NCD metric says something about distillation too. Would you expect that a model that has been distilled/seen traces from other models would have a smaller NCD? It would be really interesting to see if this holds up and provides evidence of distillation or certainly evidence of model outputs being used in the training mix.

https://eqbench.com/results/creative-writing-v3/hybrid_parsi...

This looks spot on, where is it from?

Re: Ox-Alpha Is GLM?

#67

Post by Zylokloto »

pijalu wrote: post #45

My bet: it's Google running a "new" model based on GLM

That would be a complete defeat for a Frontierlab / Company like Google/Deepmind.

They will never ever do like this.

They for sure would add architecture ideas from other research/models but thats it.

Re: Ox-Alpha Is GLM?

#69

Post by dezgeg »

troysk wrote: post #58

It is probably from Google and is probably hosted on Vertex AI. Opencode announced that responses from Ox Alpha should be better and soon posted about Vertex eu and us multi region update in their changelog. I could be a Gemini model or a new one based on GLM based on tokenizer. Also the amount of inference it is providing for free is something only google can support with its TPUs. So maybe a GLM based model running…

I extremely doubt it's Gemini - all previous Geminis have had very different output style from other models. In a coding harness Gemini is extremely quiet and mostly just does thinking and tool calls, with the thinking blocks heavily summarized.

Also Claude and the Chinese models really like to say "Let me X", Geminis preference is "I will X".

Re: Ox-Alpha Is GLM?

#70

Post by eli »

e9 wrote: post #34
gvkhna wrote: post #17

If it’s not zhipu then why is it returning errors that zhipu does for other models? Who else would return the exact same errors even if they took a lot of core infra like tokenizer from z?

Someone could've trained model on top of GLM. Same way Cognition trained their SWE model on top of Kimi and Cursor did same with their Composer model.

But it's an error, not a response.
Post reply on HN