홈으로 돌아가기
Hacker News

Claude Code의 소스 코드가 NPM 레지스트리의 맵 파일을 통해 유출되었습니다.

Claude Code's source code has been leaked via a map file in their NPM registry

1852 points 903 comments treexs 2026-03-31 18:00

댓글

14
mapcars 2026-03-31 18:09
ENGLISH (원문)
Are there any interesting/uniq features present in it that are not in the alternatives? My understanding is that its just a client for the powerful llm
LeoDaVibeci 2026-03-31 18:11
ENGLISH (원문)
Isn't it open source? Or is there an open source front-end and a closed backend?
yellow_lead 2026-03-31 18:14
ENGLISH (원문)
No
avaer 2026-03-31 18:14
ENGLISH (원문)
No, it was never open source. You could always reverse engineer the cli app but you didn't have access to the source.
agluszak 2026-03-31 18:15
ENGLISH (원문)
You may have mistaken it with Codex https://github.com/openai/codex
treexs 2026-03-31 18:17
ENGLISH (원문)
The big loss for Anthropic here is how it reveals their product roadmap via feature flags. A big one is their unreleased "assistant mode" with code name kairos. Just point your agent at this codebase and ask it to find things and you'll find a whole treasure trove of info.
swimmingbrain 2026-03-31 18:18
ENGLISH (원문)
From the directory listing having a cost-tracker.ts, upstreamproxy, coordinator, buddy and a full vim directory, it doesn't look like just an API client to me.
q3k 2026-03-31 18:19
ENGLISH (원문)
The code looks, at a glance, as bad as you expect.
dragonwriter 2026-03-31 18:20
ENGLISH (원문)
> Isn't it open source? No, its not even source available,. > Or is there an open source front-end and a closed backend? No, its all proprietary. None of it is open source.
bob1029 2026-03-31 18:20
ENGLISH (원문)
Is this significant? Copilot on OAI reveals everything meaningful about its functionality if you use a custom model config via the API. All you need to do is inspect the logs to see the prompts they're using. So far no one seems to care about this "loophole". Presumably, because the only thing that matters is for you to consume as many tokens per unit time as possible. The source code of the slot machine is not relevant to the casino manager. He only cares that the customer is using it.
avaer 2026-03-31 18:21
ENGLISH (원문)
I know HN doesn't like AI comments, but since folks might be reluctant to download + investigate this code, Anthropic's own model says the differentiators are: > the hooks lifecycle API, the multi-tier compaction system, the coordinator/swarm architecture, worktree-based isolation, and the enterprise policy layer. From my cursory read, the compaction seems to have a lot of effort put into it.
loevborg 2026-03-31 18:23
ENGLISH (원문)
Can you give an example? Looks fairly decent to me
esseph 2026-03-31 18:24
ENGLISH (원문)
[delayed]
vbezhenar 2026-03-31 18:29
ENGLISH (원문)
LoL! https://news.ycombinator.com/item?id=30337690 Not exactly this, but close.