사랑하는 야니 ♡ 생일축하해~
때로는 나보다 나를 더 믿어주고 응원해 주는 너 덕분에 용기를 얻을 때가 많아♡
내게 이런 친구가 있는 게 너무 고맙단다
많이 사랑하고 고마워 ♡ 팔 잘 회복하쟈
난 벌써 7인 동선 다 까먹을 준비 완료ㅎㅎ😗 #HAPPY_DOYEON_DAY# 🎂 🎈
사실상 위키미키의 귀염둥이 담당..💗
이 사랑스러미가 오늘 생일입니다 여러분!
많은 축하와 사랑을~ 우리 도야니에게 💌✨
소중한 우리 도연이ㅎㅎ 많이 사랑하고,
생일 축하한다 🎉!! 어서 회복해서
Siesta🎵 함께 하자꾸나아아💗
겨울❄️을 좋아하는 해바라기가🌻
#Happy_Doyeon_Day#
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!