31–40 of 97 posts
Who is using grok code and why?
It's a 1.7 trillion token free model. Why wouldn't you try it? I've been testing free models for coding hobby projects after I burnt through way too many expensive tokens on Replit and Claude. Grok wasn't great, kept getting into loops for me. I had better results using KAT coder on opencode (also free).
Because the people behind it and myself having at least some standards
According to the report, 52% of all open-source AI is used for *roleplaying*. They attribute it to fewer content filters and higher creativity. I'm pretty surprised by that, but I guess that also selects for people who would use openrouter
I hope those are not classified as “roleplaying” the “roleplay” here is just a trick to get better answer from the model, often in a professional setting that has nothing to do with creative writing of NSFW stuff
Who is using grok code and why?
Overall really interesting read, but I'm having trouble processing this: > OpenRouter performs internal categorization on a random sample comprising approximately 0.25% of all prompts How can you arrive at any conclusion with such a small random sample size?
For example, even 300 really random people is enough to correctly assertain the distribution of population for some measurement (say, some personality feauture).
That’s the basis of all polls and what have you
Overall really interesting read, but I'm having trouble processing this: > OpenRouter performs internal categorization on a random sample comprising approximately 0.25% of all prompts How can you arrive at any conclusion with such a small random sample size?
[1] https://stats.stackexchange.com/questions/166/how-do-you-dec...
This is interesting, but I found it moderately disturbing that they spend a LOT of effort up front talking about how they don’t have any access to the prompts or responses. And then they reveal that they did actually have access to the text and they spend 80% of the rest of the paper analyzing the content.
I'm not seeing that. All I'm seeing is them analyzing metadata.
Overall really interesting read, but I'm having trouble processing this: > OpenRouter performs internal categorization on a random sample comprising approximately 0.25% of all prompts How can you arrive at any conclusion with such a small random sample size?
https://en.wikipedia.org/wiki/Central_limit_theorem For example, even 300 really random people is enough to correctly assertain the distribution of population for some measurement (say, some personality feauture). That’s the basis of all polls and what have you
(OK, on rereading, you did link to a WP article about CLT, so 30 it is!)
According to the report, 52% of all open-source AI is used for *roleplaying*. They attribute it to fewer content filters and higher creativity. I'm pretty surprised by that, but I guess that also selects for people who would use openrouter
Overall really interesting read, but I'm having trouble processing this: > OpenRouter performs internal categorization on a random sample comprising approximately 0.25% of all prompts How can you arrive at any conclusion with such a small random sample size?
[^1] This is a simplification. I should say that it depends on the standard error of your statistic, i.e, the thing you're trying to measure (If you're estimating the max of a population, that's going to require more samples than if you're estimating the mean). This standard error, in turn, will depend on the standard deviation of the dimension you're measuring. For example, if you're estimating the mean height, the relevant quantity is the standard deviation of height in the population.