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

OpenClaw’s memory is unreliable, and you don’t know when it will break

blog.nishantsoni.com

Post reply on HN
Print view View original

71–80 of 196 posts

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#71

Post by mekael »

operatingthetan wrote: post #18
thepasch wrote: post #10

It would’ve happened eventually anyway, but OpenClaw is basically what kickstarted the beginning of the end of token subsidies. It’s a almost begging to be used wastefully. And agents would miss and lose nothing without it. It’s devoid of a reason to exist.

I don't follow the thinking here. If you are using it for coding maybe, but the main use case of openclaw is as a personal assistant. I'm using a $10 a month minimax subscription for it, and I've never used more than 10% usage of a 5 hour window.

Serious question, and not meant to be snarky, but what is it doing , in terms of a personal assistant, that couldnt be done with some inbox cleanup, a couple of phone shortcuts, and siri/alexa/whatever google has?

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#72

Post by piva00 »

BeetleB wrote: post #57
tecoholic wrote: post #51

Earlier quoted context omitted.

> It would call a custom API I had set up that adds items to my TODO list You can use anything to call this API right? I have multiple iPhone shortcut that does this. Heck, I think you can even use Siri to trigger the shortcut and make it a voice command (a bit unsure, it’s been a while since I played with voice)

> You can use anything to call this API right? The API is on my home PC and not exposed to the outside world. Only OpenClaw via Telegram was. So my question is about the infrastructure: How do I communicate with something at home (it could be the API directly) using a messaging app like Telegram? I definitely want an LLM in the mix. I want to casually tell it what my TODO is, and have it: - Craft it into a concise TO…

Just leave the bot running on your home PC, a Telegram bot can be programmed in any language of your choice that can communicate via a network.

If you aren't a programmer it's also the kind of small project that LLMs are great at, there are many examples ingested in their training data.

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#73

Post by dia80 »

BeetleB wrote: post #57
tecoholic wrote: post #51

Earlier quoted context omitted.

> It would call a custom API I had set up that adds items to my TODO list You can use anything to call this API right? I have multiple iPhone shortcut that does this. Heck, I think you can even use Siri to trigger the shortcut and make it a voice command (a bit unsure, it’s been a while since I played with voice)

> You can use anything to call this API right? The API is on my home PC and not exposed to the outside world. Only OpenClaw via Telegram was. So my question is about the infrastructure: How do I communicate with something at home (it could be the API directly) using a messaging app like Telegram? I definitely want an LLM in the mix. I want to casually tell it what my TODO is, and have it: - Craft it into a concise TO…

Tailscale on your PC and phone. Free (as in beer). I run vikunja.io in docker at home and simply web browse to it over the tailnet.

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#74

Post by andai »

SyneRyder wrote: post #63

I partly identify with the article. While I don't use OpenClaw itself, I hacked together my own small Claude-in-a-loop/cronjob, and it seems we're all getting our morning briefings and personalized morning podcasts now. The other common use case seems to be kicking off an automated Claude session from an email / voicetext / text / Telegram, and getting replies back. I'm emailing Claude throughout the day now, and som…

Just a heads up if you're using claude -p with the sub your account might be in trouble, they're cracking down on this kind of stuff lately.

Enforcement seems to be a combination of string matching for 3rd party sysprompts, heavy usage, and some random factor.

Not clear if there are any hard rules you can stay on the good side of, the only way to be safe seems to be to pay per token. (There goes the ~90% discount!)

--

Also yeah you get ~80% of Claw by shoving Claude Code in a Telegram Bot ;) It's already a general purpose computer use thing, people forget! (And it's a lot better at extending itself than the actual claws, lol)

I think the least illegal and also least bad option is to just use ngrok and tmux tho

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#75

Post by operatingthetan »

mekael wrote: post #71
operatingthetan wrote: post #18

Earlier quoted context omitted.

I don't follow the thinking here. If you are using it for coding maybe, but the main use case of openclaw is as a personal assistant. I'm using a $10 a month minimax subscription for it, and I've never used more than 10% usage of a 5 hour window.

Serious question, and not meant to be snarky, but what is it doing , in terms of a personal assistant, that couldnt be done with some inbox cleanup, a couple of phone shortcuts, and siri/alexa/whatever google has?

Mine is not connected to any of that. It is only connected to my Obsidian vault. Daily habits are reminded and checked off. It asks about calories etc. Think more of a manager or accountability partner than 'email on steroids.' I use it to track personal projects primarily. Lots of other tools could accomplish task tracking, but this one is more proactive than those. If you read my other comments today you will see I am not an openclaw-maxi.

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#76

Post by andai »

BeetleB wrote: post #44

If you look at my comment history, you'll see what seems to be someone defending OpenClaw (even though I stopped using it). I have some issues with the article, but I agree with some of the conclusions: It's great tinkering with it if you have time to spare, but not worth using weeks of your time trying to get a perfect setup. It's just not that reliable to use up so much of your time. I will say, it's still amongst…

I'd use Obsidian with the sync. Or you can vibe code a telegram bot that calls that API for you in like 50 lines or something.

You can do anything if you believe!

Re: QEMU: For the sandboxing I realized what I actually wanted was "it can't read/nuke my files", so I made a non-privileged linux user and added myself to its group. So I can read/write its files, but not the reverse.

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#77

Post by andai »

SyneRyder wrote: post #55
BeetleB wrote: post #44

If you look at my comment history, you'll see what seems to be someone defending OpenClaw (even though I stopped using it). I have some issues with the article, but I agree with some of the conclusions: It's great tinkering with it if you have time to spare, but not worth using weeks of your time trying to get a perfect setup. It's just not that reliable to use up so much of your time. I will say, it's still amongst…

> I could tell it (via Telegram) to add something to my TODO list at home while I'm in the office. It would call a custom API I had set up that adds items to my TODO list. How can I replicate this without the hassle of setting up OpenClaw? The general idea is make a simple deterministic program that runs on your PC at home in a never ending loop. Every minute or so, check Telegram for a new message. If a message is r…

>telegram bot that runs claude -p

https://github.com/a-n-d-a-i/ULTRON

It also supports Codex :)

I felt pretty clever until (1) I found a repo where they used this trick to create a full OpenAI compatible API endpoint[0] (lmao, the VC money distortion field spawning truly comical Rube Goldberg machines), and (2) they started banning "unauthorized" usage of the Claude sub, which trend unfortunately seems to be accelerating recently as their lower value consumers have grown in both number and usage.

I think shoving claude -p in your bash script / cronjob / messaging app bot of choice counts as "unathorized 3rd party harness", but your guess is as good as mine...

(claude -p with per-token billing (i.e. paying 7x more) is allowed though, of course)

-- There's also an Agents SDK (formerly Claude Code SDK?) which is basically just claude -p but with more typing, as far as I could tell.

[0] https://github.com/router-for-me/CLIProxyAPI

[0b] Honorable mention https://github.com/kronael/claude-serve

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#78

Post by sonink »

estetlinus wrote: post #22

Who is this guy and why is he casually admitting to reading all the user conversations???

To clarify - we don't read user conversations - what I'm referring to is deploy volume (how many times OpenClaw gets spun up on our infra) and direct conversations I've had with people in my network who deployed OpenClaw independently

Re: OpenClaw’s memory is unreliable, and you don’t know when it will break

#79

Post by sailfast »

I dunno - my boss has deployed a couple of claw agents that are pretty good at doing SWE and SRE work. They’re available for the whole company to use, and they save us a ton of time. Pretty decent use case! Personally I haven’t found claw agents replace anything really for personal use outside of commercial tools I’d pay for to handle scheduling and stuff, but I also haven’t tried / trusted too many new use cases outside of that cron / daily briefing or some family schedules.
Post reply on HN