AI · វីដេអូ
All Code Is Slop (Except Mine) — Lauren Tan, SpaceXSI
AI Engineer ·
An English version of this summary isn't ready yet, so the Korean summary is shown below.
មើលត្រួសៗ
AI 코딩 에이전트(사람 대신 코드를 짜고 고치는 AI 프로그램)를 안정적으로 쓰는 방법을 다룬 영상이에요. 발표자 Lauren Tan이 SpaceXSI의 Grok Bot 팀 사례를 소개해요.
ចំណុចសំខាន់ៗ
- 한 달에 11,000건의 코드 변경 요청(PR)을 처리하고, 되돌리는 비율은 약 0.5%라고 소개해요
- 소프트웨어 구조, 린트 규칙(코드 실수를 잡는 자동 검사), 자동 테스트를 기반으로 삼아요
- TLA+와 Lean이라는 형식 검증 도구(프로그램이 설계대로 동작하는지 수학적으로 확인하는 방법)를 다뤄요
- Cursor 에이전트와 pstack으로 이런 기반 위에 안정적인 소프트웨어 공장을 만드는 과정을 보여줘요
ហេតុអ្វីវាសំខាន់
AI가 짠 코드를 믿고 쓰려면 어떤 검증 체계가 필요한지 궁금한 개발자와 기술 리더에게 도움이 돼요.
ប្រភពដើម
All Code Is Slop (Except Mine) — Lauren Tan, SpaceXSI
AI Engineer · Nov 14, 14:20 KST
មើលនៅលើ YouTube ↗AI summarized the video title and description. Check the original for accuracy. Copyright belongs to AI Engineer.
បន្ថែមពីវិស័យនេះ
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST