[kristopolous]

It seems wildly trivial. Chat completion loop with toolcalling over a universal chat gateway.

What's the innovation here? Local model? That was always possible. Toolcalling? Been around a couple years now...

It's like 5 minutes of vibe coding at most. There's likely 1,000s of similar projects already on GitHub

[thehamkercat]

And when you can use claude-code from basically any device (termux on phone via ssh), Why even bother?

I had 3 friends ping me yesterday to tell me how this is going to eat their job....

but i don't see how this is different from claude-code + some chat interface + mcp servers

[gbear605]

> termux on phone via ssh

I agree, but it also rhymes a lot with the infamous “why use Dropbox when you can just use rsync” comment. Convenience can be a game changer.

[kristopolous]

Not exactly. This isn't substantive work. Do we really need to find a bunch of identical projects on GitHub?

This is the kind of project I saw at hackathons in 2023 by teams that didn't win anything

[cherioo]

The whole world is about bundling (and unbundling).

Not saying it really is useful, but there are values bundling an easier interface to CC with battery included.

[thehamkercat]

When someone is pushing 500 commits a day, i don't think they have time to review any code, and it was likely written in full YOLO mode.

So it's not just batteries-included, it's probably 100-vulnerabilities-included as well

[aixpert]

this is the whole message of this hype that you can churn out 500 commits a day relatively confidently the way you have clang churn out 500 assemblies without reading them. We might not be 100% there but the hype is looking slightly into the future and even though I don't see the difference to Claude code, I tend to agree that this is the new way to do things even if something breaks on average it's safe enough

[thehamkercat]

Your username says a lot about your whole message

[cherioo]

I agree. It is basically claude code running dangerously all the time. That is actually how I use CC most of the time, but I do trust Anthropic more than random github repo.

(I have the same sentiment about manifest v3 and adblocker, but somehow HN groupthink is very different there than here)

Edit: imagine cowork was released like this. HN would go NUTS.

[ru552]

You can talk to it in discord or whatsap or telegram etc. cause it's checking for you in a loop.

That's the biggest difference I can tell.

[eikenberry]

> Why even bother?

Claude-code is closed-source. That is a good enough reason to look at alternatives.

[adam_patarino]

Yeah but you're still using anthropic's subscription and tokens. That's not really an alternative. That's why we're shipping our own model with cortex.build

[eikenberry]

If you're not using Claude Code, why would you still use Anthropic. AFAIK their API pricing is not competitive.