24 comments

[ 3.2 ms ] story [ 54.5 ms ] thread
From what I understand this is a fully open-source bot that anyone can run with no restrictions. what a time to be alive, let's see what these bots will break first
Anyone chime in on how they typically engage something like this? No way am I dropping my primary contact info into something so outwardly cryptic. Phone number? Hah! Do you scaffold a new identity/email (semi-automagically)?
This is great. AI is too revolutionary to be in control of three closed models / companies. The more the merrier.

(I know this is not a new model but it's not just about the model, it's about the entire ecosystem)

I use AI a LOT. OpenAI said I'm in the 1% of people using ChatGPT (bad thing imo). I use Claude and Codex all day long, building and shipping.

But just do not get the Clawbot / OpenClaw hype at all. What are people doing with this thing? I tried it out, and I found it a bit underwhelming.

What am I missing?

For me :

1. Makes the input easy - use familiar tool of choice -> WhatsApp/Telegram/etc

2. Integrate with anything - for example gmail through gog

3. Save to memory without prompting

4. Has a Soul.md which you can customize.

5. Have a reason to use a VPS

All of these are possible with Claude Code etc, however it's the the whole package that makes it more useful.

I went through the setup process for Openclaw. Near the end I felt like I had wrestled more with setting it up than I would have had to if I had just built it from the ground up. So I pointed Pi at Nanoclaw and asked it to review it and build me a minimal clone. It took a few minutes and I had the core of something that is easier to maintain (for me) than some unknown large and cumbersome system, or whatever Openclaw is.

To each their own.

I really don’t understand the widespread adoption of OpenClaw when a simple prompt injection in an email, chat message, or calendar event has the potential to leak the credentials/keys for every attached service.
Has anyone used Kimi Claw? Is it good? Comparing to Manus for example?
(comment deleted)
I want to set this up but I'm concerned about the privacy and security risks. On the one hand, person data is flowing through cloud models. Then there's the risks of prompt injection and such.

I thought about running it locally but it gets expensive.

Those that have taken the plunge, how did you make peace with these trade offs?

Hmm, you need $40/month plan just to try it out.

Not sure who's the target audience

Tempted to try, but the pricing is bit vague. The kimi bot itself was concerned if the minimum plan covers usage for more than a day, when asked.
(comment deleted)
is there any way to make it safe? I mean since so many people are trying to make sense of it so I think in future they will come up with a solution really soon..
It's impressive how many services the Moonshot team is pushing out. The agent swarm was already impressive enough. Kimi has become a whole ecosystem of tools.