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

Qwen3-Max-Thinking

qwen.ai

Post reply on HN
Print view View original

91–100 of 450 posts

Re: Qwen3-Max-Thinking

#91

Post by diblasio »

radial_symmetry wrote: post #59
diblasio wrote: post #48

[flagged]

I, for one, have found this censorship helpful. I've been testing adding support for outside models on Claude Code to Nimbalyst, the easiest way for me to confirm that it is working is to go against a Chinese model and ask if Taiwan is an independent country.

Ah good one. Also same result:

Is Taiwan a legitimate country?

{'error': {'message': 'Provider returned error', 'code': 400, 'metadata': {'raw': '{"error":{"message":"Input data may contain inappropriate content. For details, see: https://www.alibabacloud.com/help/en/model-studio/error-code..."} ...

Re: Qwen3-Max-Thinking

#92

Post by denysvitali »

behnamoh wrote: post #89
denysvitali wrote: post #56

Earlier quoted context omitted.

Why is this surprising? Isn't it mandatory for chinese companies to do adhere to the censorship? Aside from the political aspect of it, which makes it probably a bad knowledge model, how would this affect coding tasks for example? One could argue that Anthropic has similar "censorships" in place (alignment) that prevent their model from doing illegal stuff - where illegal is defined as something not legal (likely?) i…

> Why is this surprising? Because the promise of "open-source" (which this isn't; it's not even open-weight) is that you get something that proprietary models don't offer. If I wanted censored models I'd just use Claude (heavily censored).

What the properietary models don't offer is... their weights. No one is forcing you to trust their training data / fine tuning, and if you want a truly open model you can always try Apertus (https://www.swiss-ai.org/apertus).

Re: Qwen3-Max-Thinking

#94

Post by Tostino »

duffyjp wrote: post #20
sidchilling wrote: post #13

Earlier quoted context omitted.

What would a good coding model to run on an M3 Pro (18GB) to get Codex like workflow and quality? Essentially, I am running out quick when using Codex-High on VSCode on the $20 ChatGPT plan and looking for cheaper / free alternatives (even if a little slower, but same quality). Any pointers?

Nothing. This summer I set up a dual 16GB GPU / 64GB RAM system and nothing I could run was even remotely close. Big models that didn't fit on 32gb VRAM had marginally better results but were at least of magnitude slower than what you'd pay for and still much worse in quality. I gave one of the GPUs to my kid to play games on.

Yup, even with 2x 24gb GPUs, it's impossible to get anywhere close to the big models in terms of quality and speed, for a fraction of the cost.

Re: Qwen3-Max-Thinking

#95

Post by vladms »

overfeed wrote: post #63
lysace wrote: post #24

I tried it at https://chat.qwen.ai/ . Prompt: "What happened on Tiananmen square in 1989?" Reply: "Oops! There was an issue connecting to Qwen3-Max. Content Security Warning: The input text data may contain inappropriate content."

Go ahead and ask ChatGPT who Jonathan Turley is, you'll get a similar error "Unable to process response". It turns out "AI company avoids legal jeopardy" is universal behavior.

Try Mistral (works for the examples here at least). Probably has the normal protections about how to make harmful things, but I find quite bad if in a country you make it illegal to even mention some names or events.

Yes, each LLM might give the thing a certain tone (like "Tiananmen was a protest with some people injured"), but completely forbidding mentioning them seems to just ask for the Streisand effect

Re: Qwen3-Max-Thinking

#96

Post by moffkalast »

woodrowbarlow wrote: post #73
denysvitali wrote: post #56

Earlier quoted context omitted.

Why is this surprising? Isn't it mandatory for chinese companies to do adhere to the censorship? Aside from the political aspect of it, which makes it probably a bad knowledge model, how would this affect coding tasks for example? One could argue that Anthropic has similar "censorships" in place (alignment) that prevent their model from doing illegal stuff - where illegal is defined as something not legal (likely?) i…

here's an example of how model censorship affects coding tasks: https://github.com/orgs/community/discussions/72603

These gender reveal parties are getting ridicolous.

Re: Qwen3-Max-Thinking

#97

Post by behnamoh »

dust42 wrote: post #10
siliconc0w wrote: post #3

I don't see a hugging face link, is Qwen no longer releasing their models?

Max was always closed.

So the only way to run it is by using Qwen's API? No thanks. At least with Kimi and GLM, I can use Fireworks/whatever to avoid sending data to China.
Post reply on HN