註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Daniel San
@dani_avila7
OSS project ( 33k ⭐️ )
加入 January 2015
3.5K 正在關注    35.7K 粉絲
Very interesting paper on making coding agents actually finish the job (Bookmark this and read the paper when you have time) They trained the model on 1,700 tasks where it gets points for every requirement it meets and zero if it breaks something that already worked Like a kid who already knows how to build with Lego, but learns to check the full instructions before saying it's done Model: Kimi K2.7 Code Harnesses: - Claude Code - mini-swe-agent - Terminus 2 Benchmarks: - SWE-Bench Pro - DeepSWE - Terminal-Bench - SWE-Marathon It improved on all of them, It didn't learn more code, it learned to finish
顯示更多
0
13
36
10
轉發到社區