> I mean, its open source so people can create benchmark and independently verify if the AI was wrong and then have the claims be passed to the author.
Thank you for volunteering. I look forward to your results.
> Thank you for volunteering. I look forward to your results.
Sure can you wait a few weeks tho? I know nothing about benchmarking so gonna learn it first and I have a few tests to prepare for irl.
I do feel like someone else more passionate about the project should try to pick the benchmarking though.
I don't mind benchmarking it but I only know tools like hyper for benchmarks & I have played with my fair share of zip archives and their random access retrieval but I feel like even that would depend from source to source.
There are some experienced people in here who are really cool at what they do, I just wanted to say that if someone's interested and already has the Domain Specific knowledge to benchmark & they enjoy it in the first place, this having AI benchmark shouldn't be much of a problem in comparison.
Thank you for volunteering. I look forward to your results.