Live data from Hacker News

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

blog.nishantsoni.com

111–120 of 196 posts

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

#111
post #105
post #94

You probably don't know how to setup memory. The killer usecase is letting you make whatever you want, instead of being at the mercy of what your OS/platform dictates. Your idea of a killer idea is a whatsapp summarizer lol.

I can already make whatever I want

It's for people who can't, did drop some neurons on this thread?

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

#112
Author basically admitting to having a boring outlook on life IMO. Sure maybe not for work but there's tons of things that suck the life out of your limited time, having a tool not just OpenClaw is one way to not bend to the will of BigCo for whatever thing you want to do, need a 3D model? Need something summarized or need control of something which the manufacturer forbids? All can be done without spending entire weekends for.

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

#113
post #21

From my perspective there are some people that have never built real processes in their life that enjoy having some processes now. But agent processes are less reliable slower and less maintenable then a process that is well-defined and architectured and uses llm’s only where no other solution is sufficient. Classification, drafting, summarizing. I’ve had a Whatsapp assistant since 2023, jailbraked as easy assistant.…

This. So many junior engineers showing me AI flows that could just be a script with a few parameter inputs

Same thing could be said with SKILL.md yet they are highly useful...

Yes you can automate via scripting, but interacting with a process using natural language because every instance could be different and not solid enough to write a spec for, is really handy.

tl;dr: there's a place for "be liberal in what you receive and conservative in what you send", but only now have LLMs provided us with a viable way to make room for "be loosey goosey with your transput"

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

#114
post #21

From my perspective there are some people that have never built real processes in their life that enjoy having some processes now. But agent processes are less reliable slower and less maintenable then a process that is well-defined and architectured and uses llm’s only where no other solution is sufficient. Classification, drafting, summarizing. I’ve had a Whatsapp assistant since 2023, jailbraked as easy assistant.…

This. So many junior engineers showing me AI flows that could just be a script with a few parameter inputs

Why write script when more tokens does job

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

#115
post #21

From my perspective there are some people that have never built real processes in their life that enjoy having some processes now. But agent processes are less reliable slower and less maintenable then a process that is well-defined and architectured and uses llm’s only where no other solution is sufficient. Classification, drafting, summarizing. I’ve had a Whatsapp assistant since 2023, jailbraked as easy assistant.…

This. So many junior engineers showing me AI flows that could just be a script with a few parameter inputs

I find that it's usually management that ask for such things "because AI".

I mean using AI is a great way to interpret a query, determine if a helper script already exists to satisfy it, if not invoke a subagent to write a new script.

Problem with your "script" approach is how does that satisfy unknown/general queries? What if for one run you want to modify the behavior of the script?

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

#116
post #90

I actually quite enjoy the OpenClaw. Although the recent CC crackdown has caused me to try different LLM providers which aren't that reliable but anyways, here are few things I do with it, in all separate groups. * Telegram Health Group, created an agent to help me track sleep, recommend my supplements based on my location, remind me in the morning and evening to monitor my food. I send it images of what I eat and it…

Are you concerned about telegram admins having access to that information?

Yeah! And what if Samsung put a bug in the silicon that gives them access to all your stuff without you ever knowing!

Or the CIA has set up inside your closet with a listening device!

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

#117
post #71

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?

Siri/Alexa/gemini are severely limited in what they can do/access because they wanna protect the brand.

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

#120
post #90

I actually quite enjoy the OpenClaw. Although the recent CC crackdown has caused me to try different LLM providers which aren't that reliable but anyways, here are few things I do with it, in all separate groups. * Telegram Health Group, created an agent to help me track sleep, recommend my supplements based on my location, remind me in the morning and evening to monitor my food. I send it images of what I eat and it…

You can just have your bot use Telegram topics for this.
Post reply on HN