Live data from Hacker News

Qwen2.5-VL-32B: Smarter and Lighter

qwenlm.github.io

171–180 of 303 posts

Re: Qwen2.5-VL-32B: Smarter and Lighter

#171

So today is Qwen. Tomorrow a new SOTA model from Google apparently, R2 next week. We haven't hit the wall yet.

> We haven't hit the wall yet. The models are iterative improvements, but I haven't seen night and day differences since GPT3 and 3.5

Tbh such a big jump from current capability would be ASI already

Re: Qwen2.5-VL-32B: Smarter and Lighter

#172

Earlier quoted context omitted.

The hard-to-swallow truth is that American models do the same thing regarding Israel/Palestine.

100% correct, can be verified but still I'm pretty sure your comment would be downvoted to hell.

Ironic that your comment is currently, as you say, being downvoted to hell.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#173

Earlier quoted context omitted.

I trust big companies far more with my data than small ones. Big companies have so much data they won't be having a human look at mine specifically. Some small place probably has the engineer looking at my logs as user #4. Also, big companies have security teams whose job is securing the data, and it won't be going over some unencrypted link to cloudflare because OP was too lazy to set up Https certs.

Equifax.

I'm not convinced any humans have worked there for most of my lifetime.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#174
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

This makes my day.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#175
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

9.9 is larger than 9.11. This right here is the perfect example of the dunning-kruger effect.

Maybe try rephrase your question to "which version came later, 9.9 or 9.11".

Re: Qwen2.5-VL-32B: Smarter and Lighter

#176
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

Lol, well I guess we've a achieved the functional equivalent of AGI, at least for you. Please don't delete your comment.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#177
post #152

Earlier quoted context omitted.

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

I suggest we’ve already now passed what shall be dubbed the jschoe test ;)

jschoe's post is actually a Turing test for us. :)

(just kidding jschoe)

Re: Qwen2.5-VL-32B: Smarter and Lighter

#178
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

+1 to Deepseek

-1 to humanity

Re: Qwen2.5-VL-32B: Smarter and Lighter

#179
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

This is hilarious, especially if it's unintentional.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#180
post #152
post #4

Big day for open source Chinese model releases - DeepSeek-v3-0324 came out today too, an updated version of DeepSeek v3 now under an MIT license (previously it was a custom DeepSeek license). https://simonwillison.net/2025/Mar/24/deepseek/

And it still can't answer this: Q: "9.11 and 9.9, which one is larger?" A: "To determine which number is larger between 9.11 and 9.9, let's compare them step by step. Both numbers have the same whole number part: 9. 9.11 has a 1 in the tenths place. 9.9 has a 9 in the tenths place. Since 9 (from 9.9) is greater than 1 (from 9.11), we can conclude that 9.9 is larger than 9.11." "Final Answer: 9.9" I don't think anythi…

I’ve legit seen a heated online debate with hundreds of comments about this question (maybe not the exact numbers), and I don’t think most participants were memeing. People are that bad at math. It’s depressing.
Post reply on HN