Hacker Newsnew | past | comments | ask | show | jobs | submit | treexs's commentslogin

well yeah since they tell claude code the business decisions and it creates the comments

Yes it's the claude code CLI tool / coding agent harness, not the weights.

This code hasn't been open source until now and contains information like the system prompts, internal feature flags, etc.



I believe GitHub can and does suspend accounts that use such proxies.

won't they just try to dmca or take these down especially if they're more popular

They can't. AI generated code cannot be copyrighted. They've stated that claude code is built with claude code. You can take this and start your own claude code project now if you like. There's zero copyright protection on this.

Given that from 2026 onwards most of the code is going to be computer generated, doesn't it open some interesting implications there ?

It's undetermined if code will be majority written by machines, especially as people start to realize how harmful these tools are without extreme diligence. Outages at Cloudflare, AWS, GitHub, etc are just the beginning. Companies aren't going to want to use tools that can potentially cause $100s of millions in potential damages (see Amazon store being down causing massive revenue loss).

I'm sure it's not _entirely_ built that way, and in practically speaking GitHub will almost certainly take it down rather than doing some kind of deep research about which code is which.

That's fine. File a false claim DMCA and that's felony perjury :) They know for a fact that there is no copyright on AI generated code, the courts have affirmed this repeatedly.

Try not to be overly confident about things where even the experts in the field (copyright lawyers) are uncertain of.

There's no major lawsuits about this yet, the general consensus is that even under current regulations it's in the grey. And even if you turn out to be right, and let's say 99% of this code is AI-generated, you're still breaking the law by using the other 1%, and good luck proving in court what parts of their code were human written and what weren't (especially when being sued by the company that literally has the LLM logs).


Which is why you should clone it right now

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.

Edit: some other interesting unreleased/hidden features

- The Buddy System: Tamagotchi-style companion creature system with ASCII art sprites

- Undercover mode: Strips ALL Anthropic internal info from commits/PRs for employees on open source contributions


Note also the "Claude Capybara" reference in the undercover prompt: https://github.com/chatgptprojects/claude-code/blob/642c7f94...

This seems like a good way to weed out models: ask them to include the term capybara in their commit messages

At least this was known with the Mythos "early blog post" fiasco.

If this true. My old personal agent Claude Code setup I open sourced last month will finally be obsolete (1 month lol):

https://clappie.ai

- Telegram Integration => CC Dispatch

- Crons => CC Tasks

- Animated ASCII Dog => CC Buddy


Not necessarily; I would very much like to use those features on a Linux server. Currently the Anthropic implementation forces a desktop (or worse, a laptop) to be turned on instead of working headless as far as I understand it.

I’ll give clappie a go, love the theme for the landing page!


I didn't know this existed. I had claude put this together for me from scratch a week ago. Tmux and claude and telegram is a really powerful combo!

Clappie looks much more fabulous than CC though. I'll have to give it a try. I like how you put the requests straight into an already running CC session instead of calling `claude -p` every time like the claws.

Thanks so much! It's a fancy landing page thanks to Claude.

Tmux is seriously an amazing tool.


Dispatch and scheduled tasks have been available for a few weeks already, although with limitations.

Poor mum

Not at all. I am a big a Claude Code fan and glad they are releasing more and more features for users

all these flags are findable by pointing claude at the binary and asking it to find festure flags.

(spoiler alert)

Buddy system is this year's April Fool's joke, you roll your own gacha pet that you get to keep. There are legendary pulls.

They expect it to go viral on Twitter so they are staggering the reveals.


lol that's funny, I have been working seriously [1] on a feature like this after first writing about it jokingly [2] earlier this year.

The joke was the assistant is a cat who is constantly sabotaging you, and you have to take care of it like a gacha pet.

The seriousness though is that actually, disembodied intelligences are weird, so giving them a face and a body and emotions is a natural thing, and we already see that with various AI mascots and characters coming into existence.

[1]: serious: https://github.com/mech-lang/mech/releases/tag/v0.3.1-beta

[2]: joke: https://github.com/cmontella/purrtran


You know, that would actually be pretty fun and cool. Like if you had home automation set up with a "pet assistant", but it would only follow your commands if you made sure to keep it happy.

If it could somehow only work if I maintain the kitchen sink and counter, then maybe I'd be motivated to keep the house clean. The gacha game trains you.

Is it just me or does MicroMika kinda resemble Rocky from Project Hail Mary?

haha right! I think if I were to make Rocky though, there are a number of more geometric symbols. Maybe like

  ╭⬟╮

You heard it here first

So close to April Fool's too. I'm sure it will still be a surprise for a majority of their users.

Is there an AGI mode FF? Asking for a friend…

People already can look at the source without this leak. People have had hacked builds force enabling feature flags for a long time.

one of those is adorable and the other one is unethical

Was experimenting with it but it felt like it'd have higher latency, and it seemed more feasible to do eyetracking on a single screen than across screens, especially with different webcam layouts and stuff

?

hundreds of local llm apps exist

the what's next section acts novel but all of them have been achieved or created in some format already: you can run a local llm on a phone and connect it to a agent


it gets to a point


Is this ~cat fishing~ crab potting the NFT crowd?


no NFTs but sadly yes it makes too much sense so might have to do it.


wow it's interesting how noticeable sites built with claude maybe with the frotnend-design skill are now


IYKYK, it’s the new Bootstrap!

The alternative would be “no site”, which is still somehow worse.


Asking the company that is banning use of their subscription in other services, when other subscriptions like Codex and OpenCode don't, to make something that is interoperable with similar systems. Alright lol


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: