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

Clawdbot - open source personal AI assistant

github.com

Post reply on HN
Print view View original

171–180 of 274 posts

Re: Clawdbot - open source personal AI assistant

#171

Post by jwally »

Thanks for sharing.

For the past month or so I've been slowly having claude build something in the same ballpark. Basically something to nag you to take care of grown-up things so your boss/spouse/local municipality doesn't have to.

I was going to call it "Nagatha Christy", but the joke gets old after 48 hours. At the moment, its called "Jarbis" (old Simpsons reference).

For me, checklists are useful but I suck at creating them, maintaining them, etc. I want this thing to be able to look at my calendar/email/groupme and be able to say things like:

"Hey, you have 2 kid birthday parties this weekend and a soccer game - you're bringing snacks. You want me to update your shopping list?"

or

"The dentist office just sent out a reminder - you have an appointment on Thursday that's not on the calendar. It conflicts with your daily standup. You want me to create a task for you to resolve it?"

Its using: - AWS CDK - Telegram as primary chat interface - Trello/Jira/Something Custom - Integrations into GoogleCalendar and GMail - Ability to use Claude/OpenAI and different models

FWIW, if someone figures out how to create a reliable "secretary in a box" that I don't have to DIY but doesn't scream data-collection-watering-hole (facebook) I'd _happily_ pay $200 / mo for it. ;-)

Re: Clawdbot - open source personal AI assistant

#172

Post by cztomsik »

gmerc wrote: post #44
hexsprite wrote: post #17

Clawdbot finally clicked for me this week. I was renting out an apartment and I had it connect to FB messenger, do the initial screening messages and then schedule times for viewings in my calendar. I was approving it's draft messages but starting giving it some automatic responses as well. Overall it did 9/10 on this task with a couple cases where it got confused. This is just scratching the surface but this was som…

Wait until you figure out prompt injection. It's wild

I'm following Owain Evans on X and some of the papers they've been sharing are much worse. IIRC there was something with fine-tuning a LLM to be bad actor, then letting it spit out some text, and if that response was copy-pasted into the context of the ORIGINAL LLM (no fine-tune) it was also "infected" with this bad behavior.

And it makes a lot of sense, the pre-training is not perfect, it's just the best of what we can do today and the actual meaning leaks through different tokens. Then, QKV lets you rebuild the meaning from user-provided tokens, so if you know which words to use, you can totally change the behavior of your so-far benign LLM.

There was also paper about sleeper agents and I am by no way a doomer but the LLM security is greatly underestimated, and the prompt injection (which is impossible to solve with current generation of LLMs) is just the tip of the iceberg. I am really scared of what hackers will be able to do tomorrow and that we are handing them our keys willingly.

Re: Clawdbot - open source personal AI assistant

#173

Post by maxehmookau »

I get that this is cool, but I also feel grateful that my life just isn't busy enough to justify this as a thing beyond "oh wow, that's cool tech".

I'm able to juggle the competing priorities in my life without the need of an AI assistant, and I guess I'm just gonna enjoy that for as long as I can because I assume at some point it will become assumed of me.

Re: Clawdbot - open source personal AI assistant

#174

Post by jason_tko »

barrenko wrote: post #158
jason_tko wrote: post #77

I've seen many people say "I don't get the hype", so here's my attempt to explain it. I've been working in technology and software companies my entire life, but not as a developer. Two days ago, I submitted and had my first pull request merged to an open source project (Clawdbot) thanks to my AI assistant rei. A short story: rei suddenly stopped responding in some Slack channels. So I asked it to help me troubleshoot…

I can't parse this story. "rei" stopped working and you asked "rei" or "clawdbot" to help your troubleshoot? Are you using both? Whos is 'we' in the "we fixed it ourselves" substory?

rei is introduced in this sentence: "thanks to my AI assistant rei" and then referenced in the next sentence.

Clawdbot allows you to configure your assistant with a name and a persona.

Re: Clawdbot - open source personal AI assistant

#175

Post by jason_tko »

tttpob wrote: post #122
jason_tko wrote: post #92

Earlier quoted context omitted.

https://news.ycombinator.com/item?id=9224

i disagree with your dropbox example. dropbox is apprently easier to use than a selfhost ftp site and well maintained by a company. but this clawedbot is just a one-man dev developed project. there are many similar "click to fix" services.

Not exactly, clawdbot is an open source project with hundreds of contributors (including me!) in only 3 weeks of its existence. Your characterization of just a one-man dev developed project is inaccurate.

Re: Clawdbot - open source personal AI assistant

#176

Post by afcool83 »

maxehmookau wrote: post #173

I get that this is cool, but I also feel grateful that my life just isn't busy enough to justify this as a thing beyond "oh wow, that's cool tech". I'm able to juggle the competing priorities in my life without the need of an AI assistant, and I guess I'm just gonna enjoy that for as long as I can because I assume at some point it will become assumed of me.

This is roughly my defense against anxieties about “missing the boat” on this stuff. If my life was complex enough to justify quote-simplifying-unquote it with a tool like this, I’d be quite excited about experimenting with it…but it’s not. And I don’t relish artificially adding that complexity.

The key to productivity is doing the _right_ things, not doing everything. Tools that make more possible frequently miss the point entirely.

Re: Clawdbot - open source personal AI assistant

#177

Post by akmarinov »

PurpleRamen wrote: post #166
akmarinov wrote: post #161

Earlier quoted context omitted.

Like it or not, it's where most people are

Most whom? If we're talking about any kind of people, then no, there are far bigger Social networks than eX-Twitter. And if we are just talking about tech-people, it's disputable, but at least we could talk about the quality discussions there.

Mastodon has a lot of tech people but very much a hard on for hating anything with AI, especially with AI coding. The rest of the social networks don’t really get a meaningful amount of tech discussions.

X is the only place to learn about the latest developments on AI coding. And yes, you do have to sift through a lot of idiots on there and a lot of scams and bots, but the point remains.

Re: Clawdbot - open source personal AI assistant

#178

Post by aaronbasssett »

eclipxe wrote: post #39
hecanjog wrote: post #32

This seems like a nightmare. I wanted to be interested, I'm still interested I guess, but the onboarding experience is just a series of horrible red flags. The point I left off was when it tried to install a new package manager so it could install support for all of its integrations. Hell no.

Uh. You can choose to use npm, pnpm or bun during install. It doesn’t try to install a new package manager. Maybe you were confusing clawdhub for something?

It doesn't try to install a package manager, except for Node Package Manager, Performant Node Package Manager, and the Bun package manager. Except for one of those three package managers, it doesn't install any package managers.

Re: Clawdbot - open source personal AI assistant

#179

Post by esskay »

hobo_mark wrote: post #168
hexsprite wrote: post #17

Clawdbot finally clicked for me this week. I was renting out an apartment and I had it connect to FB messenger, do the initial screening messages and then schedule times for viewings in my calendar. I was approving it's draft messages but starting giving it some automatic responses as well. Overall it did 9/10 on this task with a couple cases where it got confused. This is just scratching the surface but this was som…

Waitaminute, clawdbot has access to facebook? how since there is no API? it puppeteers the browser and somehow facebook antibot algorithms do not instaban it?

I mean, it's got full desktop access so browsing a webpage is going to be pretty trivial for it. We're well beyond anti-bot stuff at this point.

Re: Clawdbot - open source personal AI assistant

#180

Post by g947o »

esskay wrote: post #149

This may be amazing. But it's also incredibly scary what it will do, and how many people using it just dont understand the issues. Also as of the time of writing theres 337 open issues on the repo, many of which are bug reports and security issues. This thing isn't close to stable.

It seems like if you have a specific use case, you are better off vibe coding your own bot from scratch and deploying it to your own server.
Post reply on HN