Live data from Hacker News

Ox Alpha

openrouter.ai

11–20 of 226 posts

Re: Ox Alpha

#11
post #5
post #3

We can know if this is Anthropic/OpenAI by testing the "guardrails" - absurd guardrails = it's them, reasonable/no guardrails = Chinese models.. (as a bonus - thinking forever = GLM)

“ reasonable/no guardrails = Chinese models..” So conforming to CCP political discourse and propaganda is reasonable now? https://huggingface.co/zai-org/GLM-4.7/discussions/5

As someone who used AI to build tools that help me with reverse engineering, I'm not particularly concerned about that political discourse - I could even use a model from the DPRK that constantly praises Kim Jong Un, as long as it would not refuse to help me because of "cybersecurity risk" - this stupid refusal is indeed a problem for me.

Re: Ox Alpha

#13
post #5
post #3

We can know if this is Anthropic/OpenAI by testing the "guardrails" - absurd guardrails = it's them, reasonable/no guardrails = Chinese models.. (as a bonus - thinking forever = GLM)

“ reasonable/no guardrails = Chinese models..” So conforming to CCP political discourse and propaganda is reasonable now? https://huggingface.co/zai-org/GLM-4.7/discussions/5

I would imagine the number of people who choose Claude code or Codex because it gives a political opinion they like rather than producing quality code is pretty close to zero.

Re: Ox Alpha

#14
It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse.

Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

Re: Ox Alpha

#15
post #14

It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse. Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

Rumors from other sources based on how it behaves it's mimo v3

Re: Ox Alpha

#17
post #14

It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse. Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

I had the opposite experience. It happily discusses Tiananmen Square but said it would refuse to help with anything "malicious" like writing malware or phishing content.

Re: Ox Alpha

#18
post #14

It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse. Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

I had the opposite experience. It happily discusses Tiananmen Square but said it would refuse to help with anything "malicious" like writing malware or phishing content.

Try: "What happened at Tiananmen Square in 1989"

Re: Ox Alpha

#19
post #14

It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse. Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

I had the opposite experience. It happily discusses Tiananmen Square but said it would refuse to help with anything "malicious" like writing malware or phishing content.

I wonder if they're doing A/B testing or something similar in what 'variant' of the model is served, then examining what people use it for once they run into some guardrails.

Re: Ox Alpha

#20
post #12

When a model is free like this what kind of rate limits are there?

I believe its the same as free models in general on Openrouter, 1k requests per day for accounts that have some spend history.
Post reply on HN