[🎁] 위로(WELO) 생일 카페 ‘WELO ZONE’ 이용 안내
위로 생일 카페 내 위로의 발자국을 남길 수 있는
‘WELO ZONE’을 만나 보세요🐾
작성해 주신 모든 메시지는 옹성우 배우에게 전달됩니다💌
#옹성우# #ONGSEONGWU# #위로# #WELO# #HAPPY_WELO_DAY# #WELO_ZONE#
[🎁] 위로(WELO) 생일 카페 오픈 안내
📍 인천 부평 ‘하트온디저트카페’
⏰ 12PM - 10PM
📍 서울 홍대 ‘W카페’
⏰ 11:15AM - 10PM
📍 서울 성수 ‘뉴앳던 성수’
⏰ 12PM - 10PM
위로 여러분을 위한 카페가 잠시 후 오픈됩니다💕
#옹성우# #ONGSEONGWU# #위로# #WELO# #HAPPY_WELO_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!