If y'all haven't read the Henghis Hapthorn stories by Matthew Hughes e.g. The Gist Hunter and Other Tales iirc, you should check them out. This is a cut at Henghis' "Integrator" assistant.
OpenClaw – Moltbot Renamed Again
151–160 of 422 posts
Re: OpenClaw – Moltbot Renamed Again
#152Earlier quoted context omitted.
It's typically used with external sandboxes. I wouldn't trust its internal sandbox anyway, now that would be a mistake
Yeah, keep it in a VM or a box you don't care about. If you're running it on your primary machine, you're a dumbass even if you turn on sandbox mode.
It's really easy to run this in a container. The upside is you get a lot of protection included. The downside is you're rebuilding the container to add binaries. The latter seems like a fair tradeoff.
What I'll say about OpenClaw is that it truly feels vibe coded, I say that in a negative context. It just doesn't feel well put together like OpenCode does. And it definitely doesn't handle context overruns as well. Ultimately I think the agent implementation in n8n is better done and provides far more safeguards and extensibility. But I get it - OpenClaw is supposed to run on your machine. For me, though, if I have an assistant/agent I want it to just live in those chat apps. At that rate it's running in a container on a VPS or LXC in my home lab. This is where a powerful-enough local machine does make sense and I can see why folks were buying Mac Minis for this. But, given the quality of the project, again in my opinion, it's nothing spectacular in terms of what it can do at this point. And in some cases it's more clunky given its UI compared to other options that exist which provide the same functionality.
Re: OpenClaw – Moltbot Renamed Again
#153asd
Re: OpenClaw – Moltbot Renamed Again
#154I 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…
I think one thing these things could benefit from is an optimization algorithm that creates prompts based on various costs. $$, and what prompts actually gives good results.
But it's not an optimization algorithm in the sense gradient descent is, but more like Bandits and RL.
There has been some work around this practically being tried out using it for structured data outputs from LLMs https://docs.boundaryml.com/guide/baml-advanced/prompt-optim...
I won't claim I understand its implementation very well but it seems like the only approach to have a GOFAI style thing where the agent can ask for human help if it blows through a budget
Re: OpenClaw – Moltbot Renamed Again
#155Earlier quoted context omitted.
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…
No offense, but you'd be a perfect Microsoft employee right now. Windows division probably.
Theres a certain irony to this since im not running windows on a single machine i own - only linux ¯\_(ツ)_/¯
Re: OpenClaw – Moltbot Renamed Again
#156I’m not a lawyer but trademark isn’t just searching TESS right? It’s overly broad but the question I ask myself when naming projects (all small / inconsequential in the general business sense but meaningful to me and my teams) is: will the general public confuse my name with a similar company name in a direct or tangentially related industry or niche? If yes, try a different name… or weigh the risks of having a legal expense later and go for it if worth the risk.
In this instance, I wonder if the general public know OpenAI and might think anything ai related with “Open” in the name is part of the same company? And is OpenAI protecting its name?
There’s a lot more to trademark law, too. There’s first use in commerce, words that can’t be marked for many reasons… and more that I’ll never really understand.
Regardless the name, I am looking forward to testing this on cloudflare! I’m a fan of the project!
Re: OpenClaw – Moltbot Renamed Again
#157Earlier quoted context omitted.
This prompt has iRobot vibes.
And like I, Robot, it has numerous loopholes built in, ignores the larger population (Asimov added a law 0 later about humanity), says nothing about the endless variations of the Trolley Problem, assumes that LLMs/bots have a god-like ability to foresee and weigh consequences, and of course ignores alignment completely.
Cool!
I work with a guy like this. Hasn't shipped anything in 15+ years, but I think he'd be proud of that.
I'll make sure we argue about the "endless variations of the Trolley Problem" in our next meeting. Let's get nothing done!
Re: OpenClaw – Moltbot Renamed Again
#158So 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…
> Having something always waiting in the background that can proactively take actions
That's just reactive with different words. The missing part seems to be just more background triggers/hooks for the agent to do something about them, instead of simply dealing with user requests.
Re: OpenClaw – Moltbot Renamed Again
#159My biggest issue with this whole thing is: how do you protect yourself from prompt injection? Anyone installing this on their local machine is a little crazy :). I have it running in Docker on a small VPS, all locked down. However, it does not address prompt injection. I can see how tools like Dropbox, restricted GitHub access, etc., could all be used to back up data in case something goes wrong. It's Gmail and Calen…
I want to use Gemini CLI with OpenClaw(dbot) but I'm too scared to hook it up to my primary Google account (where I have my Google AI subscription set up)
Gemini or not, a bot is liable to do some vague arcane something that trips Google autobot whatevers to service-wide ban you with no recourse beyond talking to the digital hand and unless you're popular enough on X or HN and inclined to raise shitstorms, good luck.
Touching anything Google is rightfully terrifying.
Re: OpenClaw – Moltbot Renamed Again
#160So 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…
> ...delivers on that promise
Incidentally, there's a key word here: "promise" as in "futures".
This is core of a system I'm working on at the moment. It has been underutilized in the agent space and a simple way to get "proactivity" rather than "reactivity".
Have the LLM evaluate whether an output requires a future follow up, is a repeating pattern, is something that should happen cyclically and give it a tool to generate a "promise" that will resolve at some future time.
We give the agent a mechanism to produce and cancel (if the condition for a promise changes) futures. The system that is resolving promises is just a simple loop that iterates over a list of promises by date. Each promise is just a serialized message/payload that we hand back to the LLM in the future.