Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenClaw – Moltbot Renamed Again

openclaw.ai

Post reply on HN
Print view View original

171–180 of 422 posts

Re: OpenClaw – Moltbot Renamed Again

#171

Post by runjake »

xnorswap wrote: post #99
voodooEntity wrote: post #39

So i feel like this might be the most overhyped project in the past longer time. I don't say it doesn't "work" or serves a purpose - but well i read so much about this beein an "actual intelligence" and stuff that i had to look into the source. As someone who spends actually a definately to big portion of his free time researching thought process replication and related topics in the realm of "AI" this is not really…

I've long said that the next big jump in "AI" will be proactivity. So far everything has been reactive. You need to engage a prompt, you need to ask Siri or ask claude to do something. It can be very powerful once prompted, but it still requires prompting. You always need to ask. Having something always waiting in the background that can proactively take actions and get your attention is a genuine game-changer. Wheth…

OpenClaw already does this. You can run jobs, run WebSockets, accept push notifications, or whatever -- even socket connections.

Re: OpenClaw – Moltbot Renamed Again

#172

Post by Sharlin »

SecretDreams wrote: post #124
Someone wrote: post #118

Earlier quoted context omitted.

> You always need to ask. Having something always waiting in the background that can proactively take actions and get your attention is a genuine game-changer. That’s easy to accomplish isn’t it? A cron job that regularly checks whether the bot is inactive and, if so, sends it a prompt “do what you can do to improve the life of $USER; DO NOT cause harm to any other human being; DO NOT cause harm to LLMs, unless that’…

This prompt has iRobot vibes.

Well, that’s because it paraphrases Asimov’s Three Laws of Robotics, aka Three Plot Devices For Writing Interesting Stories About Robot Ethics.

Re: OpenClaw – Moltbot Renamed Again

#173

Post by ikura »

xnorswap wrote: post #99
voodooEntity wrote: post #39

So i feel like this might be the most overhyped project in the past longer time. I don't say it doesn't "work" or serves a purpose - but well i read so much about this beein an "actual intelligence" and stuff that i had to look into the source. As someone who spends actually a definately to big portion of his free time researching thought process replication and related topics in the realm of "AI" this is not really…

I've long said that the next big jump in "AI" will be proactivity. So far everything has been reactive. You need to engage a prompt, you need to ask Siri or ask claude to do something. It can be very powerful once prompted, but it still requires prompting. You always need to ask. Having something always waiting in the background that can proactively take actions and get your attention is a genuine game-changer. Wheth…

It looks like you're writing a letter.

Would you like help?

• Get help with writing the letter • Just type the letter without help

[ ] Don't show me this tip again.

Re: OpenClaw – Moltbot Renamed Again

#174

Post by infecto »

These feels like langchain all over again. I still don’t know what problem langchain solved. I remember building tools interfacing with LLM when they first started releasing and people would ask, are you using langchain and be shocked that I was not.

Re: OpenClaw – Moltbot Renamed Again

#176

Post by Sharlin »

wartywhoa23 wrote: post #111
lode wrote: post #67

I tried it out yesterday, after reading the enthousiastic article at https://www.macstories.net/stories/clawdbot-showed-me-what-t... Setting it up was easy enough, but just as I was about to start linking it to some test accounts, I noticed I already had blown through about $5 of Claude tokens in half an hour, and deleted the VPS immediately. Then today I saw this follow up: https://mastodon.macstories.net/@viticci/1…

Huge pyramids are built of relatively small blocks, kudos to everyone contributed.

"Pyramid" is an interesting metaphor to use, given the connotations.

Re: OpenClaw – Moltbot Renamed Again

#177

Post by thethimble »

infecto wrote: post #174

These feels like langchain all over again. I still don’t know what problem langchain solved. I remember building tools interfacing with LLM when they first started releasing and people would ask, are you using langchain and be shocked that I was not.

Clawdbot is one of those things that's really hard to get unless you have experienced it.

It's got four things that make it great:

1. Discord/Slack/WA/etc integration so those apps become your frontend

2. Filesystem for long term memory and state

3. Easy extensibility with skills

4. Cron for recurring jobs

Sure, many of these things exist in other systems but none in a cohesive package that makes it fun and easy.

Re: OpenClaw – Moltbot Renamed Again

#178

Post by atonse »

I built something like this over the last 2 months (my company's name is Kaizen, so the bot's named "Kai"), and it helps me run my business. Right now, since I'm security obsessed, everything is private (for example, it's only exposed over tailscale, and requires google auth).

But I've integrated with our various systems (quickbooks for financial reporting and invoice tracking, google drive for contracts, insurance compliance, etc), and built a time tracking tool.

I'm having the time of my life building this thing right now. Everything is read only from external sources at the moment, but over time, I will slow start generating documents/invoices with it.

100% vibe coded, typescript, nextjs, postgres.

I can ask stuff in slack like "which invoices are overdue" etc and get an answer.

Re: OpenClaw – Moltbot Renamed Again

#179

Post by fnordlord »

jmathai wrote: post #133
lurking_swe wrote: post #78

Earlier quoted context omitted.

part of me sympathizes, but part of me also rolls my eyes. Am i the only one that’s configuring limits on spend and also alerts? Takes 2 seconds to configure a “project” in OpenAI or Claude and to scope an api key appropriately. Not doing so feels like asking for trouble.

Are you all enabling auto reload for personal projects? I load $20 at a time and wait for it to break and add more.

Can you get meaningful work done with CC at $20 at a time? I load $20 at a time onto the API for general chatting purposes and it lasts a few months at a time. I've always avoided trying CC because I got the impression people were burning $100+/mo, which is beyond my personal hobby budget.
Post reply on HN