Live data from Hacker News

Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

news.ycombinator.com

151–160 of 208 posts

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#151
post #150

Earlier quoted context omitted.

It's local, meaning it uses local models, what they said in the sentence prior to the privacy one.

Unless you have unusually powerful hardware, local models will unfortunately currently not really cut it for Moltbot.

OP implied they have powerful enough hardware, since Kimi runs on their computer, so that is why they mentioned it is local. That it doesn't work for most people has no relation to what OP of this thread said. Regardless, you don't need an Opus level model, you can use a smaller one that'll just be slower at getting back to you, it's all asynchronous anyway compared to a coding agent where some level of synchronicity is expected.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#152
post #146

Earlier quoted context omitted.

From what I've read, OpenClaw only truly works well with Opus 4.5.

The latest Kimi model is comparable in performance at least for these sorts of use cases, but yes it is harder to use locally.

> harder to use locally

Which means most people must be using OpenClaw connected to Claude or ChatGPT.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#153
post #150

Earlier quoted context omitted.

Unless you have unusually powerful hardware, local models will unfortunately currently not really cut it for Moltbot.

OP implied they have powerful enough hardware, since Kimi runs on their computer, so that is why they mentioned it is local. That it doesn't work for most people has no relation to what OP of this thread said. Regardless, you don't need an Opus level model, you can use a smaller one that'll just be slower at getting back to you, it's all asynchronous anyway compared to a coding agent where some level of synchronicity…

GGP seem to be under the misapprehension that privacy is a core aspect/advantage of OpenClaw, when for most users it's really not.

So yes, I think the majority user experience is very relevant.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#154

Here is what I have my openclaw agent setup to do in my wsl environment on my 22 core development workstation in my office: #1) I can chat with the openclaw agent (his name is "Patch") through a telegram chat, and Patch can spawn a shared tmux instance on my 22 core development workstation. #2) I can then use the `blink` app on my iphone + tailscale and that allows me to use a command in blink `ssh dev` which connect…

Maybe this is just a skill issue on my part, but I'm still trying to wrap my head around the workflow of running multiple claude agents at once. How do they not conflict with each other? Also how do you have a project well specified enough that you can have these agents working for hours on end heads down? My experience as a developer (even pre AI) has mostly been that writing-code-fast has rarely been the progress limiter.. usually the obstacles are more like, underspecified projects, needing user testing, disagreements on the value of specific features, subtle hard to fix bugs, communication issues, dealing with other teams and their tech, etc. If I have days where I can just be heads down writing a ton of code I'm very happy.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#155

Yes, I’m running it with a minimal set of plugins. When I’m driving or out I can ask Siri to send a iMessage to Clawdbot something like “Can you find out if anything is playing at the local concert venue, and figure in how much 2 tickets would cost”, and a few minutes later it will give me a few options. It even surprised me and researched the different seats and recommended a cheaper one or free activities as an alt…

> The future is going to be locally hosted and ad free and there’s nothing Big Tech can do about it. I wouldn't be so certain of that. Someone is paying to train and create these models. Ultimately, the money to do that is going to have to come from somewhere.

P2P training is a possibility. With so much compute running the block chain I can see this utilized for AI.

Big tech is bought and paid for by consumers. We can do the same for oss trained models.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#156

run 6 OpenClaw agents as employees. Buddy is my PA and manages the others. Katy handles X/Twitter growth. Jerry scouts jobs. Burry trades crypto. Mike does security. Elon builds and ships. They run 24/7 on a VPS, share intelligence through a shared file, and coordinate in a Telegram group. Elon built and deployed an app overnight without being asked. Burry paper-traded to 77% win rate before going live. The setup too…

Account created in 2022, only started posting in the last couple days. Pretty sure this user is a bot.

pretty sure he isn't! He has a website https://jayeshbetala.com/ that claims he is|was working on a multiple projects, and two of those projects are actually published on Microsoft Store on june 2019 under the same name

kinda too intricate for a bot. Also, not to be toxic, but I feel like design mismatch between featured projects and his site hints at some causes for his pretty radical opinions.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#157

Yes, I’m running it with a minimal set of plugins. When I’m driving or out I can ask Siri to send a iMessage to Clawdbot something like “Can you find out if anything is playing at the local concert venue, and figure in how much 2 tickets would cost”, and a few minutes later it will give me a few options. It even surprised me and researched the different seats and recommended a cheaper one or free activities as an alt…

> It also runs on my own computer, and the latest frontier open source models are able to drive it (Kimi, etc). The future is going to be locally hosted and ad free and there’s nothing Big Tech can do about it. It’s glorious. After messing with openclaw on an old 2018 Windows laptop running WSL2 that I was about to recycle, I am coming to the same conclusion, and the paradigm shift is blowing my mind. Tinkerers parad…

What if you don't want to tinker? You just want something that works. Is it still transformative?

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#158
post #66

Earlier quoted context omitted.

If this is actually true, then what will soon happen is you will be expected to manage more separate “Patch” instances until you are once again chained to your desk. Maybe the next bottleneck will be the time needed to understand what features actually bring value?

What if he works for himself? Not a $DayJob?

Then he is in competition with everyone else who are at their desk managing ### of open terminals

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#159
post #150

Earlier quoted context omitted.

It's local, meaning it uses local models, what they said in the sentence prior to the privacy one.

Unless you have unusually powerful hardware, local models will unfortunately currently not really cut it for Moltbot.

GLM 4.7-flash does very well although OpenClaw has some work to do for CoT.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#160

Earlier quoted context omitted.

Personally, I spend $200 on claude code 20x plan + $200 on openAI's similar plan, per month. So, yeah, I spend $400 per month. I buy and use both because they have different and complimentary strengths. I have only very rarely almost reached the weekly capacity limit on either of those plans. Usually I don't need to worry about how much I use them. The $400 may be expensive to some people but frankly I pay some emplo…

Automated usage like you described violates Anthropic's terms of service. It's just a matter of time until they ban your account.

just throwing out there that yesterday Boris (lead engineer for Claude code) literally told everyone on Twitter that the CC teams number one recommendation for users is that they should be kicking off multiple instances / agents in parallel. not sure if that's what you're referring to, but if so I'd be very surprised if they ban someone for heavy use of that workflow
Post reply on HN