211–220 of 400 posts
Earlier quoted context omitted.
US companies hate that trick?!
you mean: invented
Earlier quoted context omitted.
> We've seen all the American models be closed and proprietary from the start. Most*. OpenAI, contrary to popular belief, actually used to believe in open research and (more or less) open models. GPT1 and GPT2 both were model+code releases (although GPT2 was a "staged" release), GPT3 ended up API-only.
OpenAI has released their GPT-OSS series more recently.
It's a good model though, would be nice with a refresh.
Earlier quoted context omitted.
> We've seen all the American models be closed and proprietary from the start. Most*. OpenAI, contrary to popular belief, actually used to believe in open research and (more or less) open models. GPT1 and GPT2 both were model+code releases (although GPT2 was a "staged" release), GPT3 ended up API-only.
That's fair but those days seem so long gone now. Also the Chinese models aren't following a typical American SaaS playbook which relies on free/cheap proprietary software for early growth. They are not just publishing their weights but also their code and often even publishing papers in Open Access journals to explicitly highlight what methods and advancements were made to accomplish their results
Earlier quoted context omitted.
I wonder why glm is viewed so positively. Every time I try to build something with it, the output is worse than other models I use (Gemini, Claude), it takes longer to reach an answer and plenty of times it gets stuck in a loop.
I've been running Opus and GLM side-by side for a couple weeks now, and I've been impressed with GLM. I will absolutely agree that it's slow, but if you let it cook, it can be really impressive and absolutely on the level of Opus. Keep in mind, I don't really use AI to build entire services, I'm mostly using it to make small changes or help me find bugs, so the slowness doesn't bother me. Maybe if I set it to make a…
Yes, but... isn't the same true for Opus and all the other models too?
Qwen appears to be much more expensive:
- Qwen: $1.3 in / $7.8 out
- Kimi: $0.95 in / $4 out
--
The announcement posts only share two overlapping benchmark results. Qwen appears to score slightly lower on SWE-Bench Pro and Terminal-Bench 2.0.
Qwen:
- Teminal-Bench 2.0: 65.4
- SWE-Bench Pro: 57.3
Kimi:
- Terminal-Bench 2.0: 66.8
- SWE-Bench Pro: 58.6
--
Different models have different strong suits, and benchmarks don't cover everything. But from a numbers perspective, Kimi looks much more appealing.
Earlier quoted context omitted.
I tried GLM and Qwen last week for a day. And some issues it could solve, while some, on surface relatively easy, task it just could not solve after a few tries, that Opus oneshotted this morning with the same prompt. It’s a single example ofcourse, but I really wanted to give it a fair try. All it had to do was create a sortable list in Magento admin. But on the other hand, GLM did oneshot a phpstorm plugin
Do you use Opus through the API or with subscription? Did you use OpenCode or Code?
Earlier quoted context omitted.
Change layer size and you have to retrain. Change number of layers and you have to retrain. Change tokenization and you have to retrain.
None of that is true, at least in theory. You can trivially change layer size simply by adding extra columns initialized as 0, effectively embedding your smaller network in a larger network. You can add layers in a similar way, and in fact LLMs are surprisingly robust to having layers added and removed - you can sometimes actually improve performance simply by duplicating some middle layers[0]. Tokenization is probab…
Earlier quoted context omitted.
> "Actually…" or "But wait!" You’re absolutely right! Jokes apart, I did notice GLM doing these back and forth loops.
I was watching Qwen3.6-35B-A3B (locally) doing the same dance yesterday. It eventually finished and had a reasonable answer, but it sure went back and forth on a bunch of things I had explicitly said not to do before coming to a conclusion. At least said conclusion was not any of the things I'd said not to do.
Earlier quoted context omitted.
Change layer size and you have to retrain. Change number of layers and you have to retrain. Change tokenization and you have to retrain.
And yet the KL divergence after changing all that stuff remains remarkably similar between different models, regardless of the specific hyperparameters and block diagrams employed at pretraining time. Some choices are better, some worse, but they all succeed at the game of next-token prediction to a similar extent. To me, that suggests that transformer pretraining creates some underlying structure or geometry that ha…
Tokenization breaks up collocations and creates new ones that are not always present in the original text as it was. Most probably, the first byte pair found by simple byte pair encoding algorithm in enwik9 will be two spaces next to each other. Is this a true collocation? BPE thinks so. Humans may disagree.
What does concern me here is that it is very hard to ablate tokenization artifacts.
Ok I find it funny that people compare models and are like, opus 4.7 is SOTA and is much better etc, but I have used glm 5.1 (I assume this comes form them training on both opus and codex) for things opus couldn't do and have seen it make better code, haven't tried the qwen max series but I have seen the local 122b model do smarter more correct things based on docs than opus so yes benchmarks are one thing but realit…
Qwen3-Coder produced much better rust code (that utilized rust's x86-64 vectorized extensions) a few months ago than Claude Opus or Google Gemini could. I was calling it from harnesses such as the Zed editor and trae CLI. I was very impressed.