[비하인드] #103#. 하이라이트 양요섭 :: HAPPY YS DAY 💛
날씨마저도 우리 편인 것 같아 더 기분이 좋았던 하루였습니다!
라이트 여러분들도 모두 오늘의 날씨만큼이나 좋은 하루, 행복한 요섭데이 보내셨기를 바라며,
얼마 남지 않은 봉길.. 아니 요섭 님의 생일! 마지막까지 아낌없는 큰 축하 부탁드립니다:)
💛
#해피요섭데이# #HAPPY_YS_DAY#
#하이라이트# #HIGHLIGHT#
#비스트# #BEAST#
#양요섭# #YANGYOSEOP#
We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container.
So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness.
TL;DR of this special prompting:
- Trust source code over the user prompt, so read every call site and existing tests before starting the task
- Weigh edge and error cases as heavily as the happy path
- Always reproduce the bug before fixing
- Don't trust the first passing test suite, and verify suspicious looking half-baked tests
- Never stop at just editing, keep working until the change is verified complete.
We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness.
Results:
- Used 2.7x fewer tokens (19.7M → 7.2M)
- Finished 2x faster (49min → 24min)
- Cost 2.4x less ($7.69 → $3.25)
Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!
"Aw, this the best in the world, right here."
Ant's daughter left a heartfelt message inside his NBA All-Star ring box in February 🥲❤️
Happy 25th Birthday, @anthonyedwards!