| ▲ | Tokendoctor – the same Claude Code for up to 38% less(github.com) | |||||||||||||
| 20 points by rsaryev1997 5 hours ago | 8 comments | ||||||||||||||
| ▲ | relyks an hour ago | parent | next [-] | |||||||||||||
I use this and it works well: https://github.com/rtk-ai/rtk I'm trying to figure out if I can use multiple of these tools together without conflicts | ||||||||||||||
| ||||||||||||||
| ▲ | mkagenius an hour ago | parent | prev | next [-] | |||||||||||||
> https://github.com/localixai/tokendoctor/tree/main/bench Don't we need to run it on all of the benches those models publish? This doesn't look very comprehensive. Moreover half of the times factory claude code is better than 'advised' one. Although I don't discourage such experiments, I feel this one is way complicated for very little or no gain provably. | ||||||||||||||
| ▲ | renegat0x0 2 hours ago | parent | prev | next [-] | |||||||||||||
I have a list of ai related tools. There is so many of them For example limiting token usage i think can also be achieved by 'caveman' project. It achieves it differently but the goal is same i suppose Overall Ai tools I found: https://github.com/rumca-js/awesome-database-top/blob/main/l... | ||||||||||||||
| ▲ | pinkyclouds 12 minutes ago | parent | prev | next [-] | |||||||||||||
why not having a tiny fast model summarize tool output instead, maybe with a threshold or something. | ||||||||||||||
| ▲ | ralph84 29 minutes ago | parent | prev [-] | |||||||||||||
These tricks last at most one model dot release. | ||||||||||||||
| ||||||||||||||