4 points | by pankaj4u4m 3 days ago
6 comments
No buzz, No fuzz. Real honest measurable savings on real benchmark tasks.
I was tired of hearing every tools out there, promising 40-50-60 even 80% saving but when it comes to actual tasks they go fuzz.
So I benchmarked everyone to see where they stand. https://github.com/atelier-ws/atelier/blob/main/BENCHMARKS.m...
what would be best way to include this in a harness?
There is SDK but it is not tested. if you are using claude -p directly then it is already included in claude. Else there is atelier -p which required API key.
But contact me on telegram and we can discuss this in detail.
i am working around C++ specific harness and looking for such solutions. you can reach out to me at:
https://discord.gg/vx5Eu4YNzG
Hey it takes me to a group instead. it is easier conact me on telegram @pankaj4u4m
[flagged]
No buzz, No fuzz. Real honest measurable savings on real benchmark tasks.
I was tired of hearing every tools out there, promising 40-50-60 even 80% saving but when it comes to actual tasks they go fuzz.
So I benchmarked everyone to see where they stand. https://github.com/atelier-ws/atelier/blob/main/BENCHMARKS.m...
what would be best way to include this in a harness?
There is SDK but it is not tested. if you are using claude -p directly then it is already included in claude. Else there is atelier -p which required API key.
But contact me on telegram and we can discuss this in detail.
i am working around C++ specific harness and looking for such solutions. you can reach out to me at:
https://discord.gg/vx5Eu4YNzG
Hey it takes me to a group instead. it is easier conact me on telegram @pankaj4u4m
[flagged]