| ▲ | SubiculumCode 5 hours ago |
| Funny, the cheerleading at HN for leading Chinese models, but a non Chinese lab (building on top of a Chinese model) gets dissed here. |
|
| ▲ | mirekrusin 5 hours ago | parent | next [-] |
| It's simple: close weights = not welcome. |
|
| ▲ | sosodev 5 hours ago | parent | prev | next [-] |
| It's almost as if HN users aren't all the same. |
|
| ▲ | llmslave 5 hours ago | parent | prev [-] |
| all the open source models are a waste of time relative to the bleeding edge from openai/anthropic |
| |
| ▲ | wongarsu 5 hours ago | parent | next [-] | | At work I wouldn't want to use anything else. Compared to my salary a Claude subscription (or two) is cheap For hobby projects I've completely switched to DeepSeek v4 pro. I spend less than on a $10 Claude plan and am not subjected to quota limits (when I have time and motivation, the last thing I want is a 5 hour quota running out). And the difference in model performance is fine for those smaller projects, most of which will end up abandoned or in a state of "good enough" anyways And for utility tasks, those 30b models are also great.
I'm a big fan of gemma4 | | |
| ▲ | llmslave 5 hours ago | parent [-] | | ive just got better things to do with my life than fuss with an inferior model. its like why hire a dumb employee over a smart one | | |
| ▲ | BeetleB 4 hours ago | parent [-] | | I think you misspelled "I've got plenty of money". | | |
| ▲ | llmslave 4 hours ago | parent [-] | | 200 bucks a month? | | |
| ▲ | BeetleB 2 hours ago | parent [-] | | Is a lot of money. The majority of people here aren't willing to spend $200/mo for coding unless their little projects provide a comparable value back to them. For context, I'm paying under $30/year and get GLM-5.2. An extra $2300/year isn't going to get me much better outcomes. |
|
|
|
| |
| ▲ | pixel_popping 5 hours ago | parent | prev [-] | | Not true since a few months, genuinely try GLM 5.2 and Minimax M3, especially in adversarial/gating... as a general model, I can agree, but as a coding model, they are not bad, comparable to maybe Opus 4.5 in real usage which is quite impressive. | | |
| ▲ | villish 5 hours ago | parent | next [-] | | I use GLM or DS4 to help me draft a better initial prompt with more information that I then give to Sonnet 5/Fable/GPT5.5. While benchmarks show the open models close to frontier level, my experience with them is drastically different. I have high confidence that Fable or GPT will 1 shot solutions. At least with low level programming languages. They're all very good for webdev stuff. | |
| ▲ | llmslave 5 hours ago | parent | prev [-] | | yeah but why waste your time on these models, just use the one that gets the better results | | |
| ▲ | nicoburns 5 hours ago | parent | next [-] | | I actively prefer GLM-5.2 for some tasks. For simple tasks the results are just as good as e.g. Opus, and it produces results significantly faster. | |
| ▲ | 9183726518 5 hours ago | parent | prev | next [-] | | Because you can get them from more trustworthy providers or with hardware encryption. | | |
| ▲ | llmslave 5 hours ago | parent [-] | | i trust anthropic/openai with my data far more than some random startup. |
| |
| ▲ | somenameforme 5 hours ago | parent | prev [-] | | I was going to respond until I saw your account name lol. | | |
|
|
|
