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

141–150 of 196 posts

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

#141

Post by chris_money202 »

mickeyp wrote: post #108
chris_money202 wrote: post #97

Earlier quoted context omitted.

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

You say that with the wisdom of experience. But there's still value in people exploring new spaces they find interesting, even if they do not meet your personal definition of pareto-optimal.

Exploring with AI doesn’t lead to the same level of learning. They are doing the equivalent of paying to skip the level up of their character and going to the final boss with level 1 armor

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

#143

Post by ejeje »

_pdp_ wrote: post #48

IMHO, the biggest problem with OpenClaw and other AI agents is that the use-cases are still being discovered. We have deployed several hundred of these to customers and I think this challenge comes from the fact that AI agents are largely perceived as workflow automation tools so when it comes to business process they are seen as a replacement for more established frameworks. They can automate but they are not reliab…

That’s not the issue. It’s an issue of trust and whether the thing does exactly what it should continuously over long periods of time without having to keep an eye on it.

Until it gets there, it’ll remain a fringe product.

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

#144

Post by ejeje »

wg0 wrote: post #126
tomhow wrote: post #80

Earlier quoted context omitted.

Please don't do this here.

I am sorry. I understand that many of us are heavily invested financially or emotionally into AI but the key insight about OpenClaw remains the same that it really isn't much useful beyond maybe a daily news summary. Nothing that cannot be done otherwise.

I think it broadly speaks to the issue of llm’s in general.

People have to actively interact with these things to get outputs of them. Why can’t they do it passively?

Because on the surface LLM’s seem intelligent. But they’re not. They need constant attention to ensure they are doing what one wants and not going off track. I experienced this myself many times - the variance in the output can be jarring at times. From surprisingly good to absolutely disappointing.

Why hasn’t customer service over the web/telephone become completely autonomous or at least partially via llm’s? We have all this talk about agentic programming and yet much of the world carries on as it was.

Interesting. I don’t think this variance problem is going away. It’s a different kind of variance than humans are used to when dealing with other humans.

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

#145

Post by mike_hearn »

gbro3n wrote: post #130
loehnsberg wrote: post #122

As long as there's no solution to the long-term memory problem, we will have a "country of geniuses in a data center" that are all suffering from anterograde amnesia (movie: Memento), which requires human hand-holding. I have experimented with a lot of hacks, like hierarchies of indexed md files, semantic DBs, embeddings, dynamic context retrieval, but none of this is really a comprehensive solution to get something…

I've used open claw (just for learning, I agree with the author it's not reliable enough to do anything useful) but also have a similar daily summary routine which is a basic gemini api call to a personal mcp server that has access to my email, calendar etc. The latter is so much more reliable. Open claw flows sometimes nail it, and then the next day fails miserably. It seems like we need a way to 'bank' the correct…

This is interesting. I haven't used OpenClaw but I set up my own autonomous agent using Codex + ChatGPT Plus + systemd + normal UNIX email and user account infrastructure. And it's been working great! I'm very happy with it. It's been doing all kinds of tasks for me, effectively as an employee of my company.

I haven't seen any issues with memory so far. Using one long rolling context window, a diary and a markdown wiki folder seems sufficient to have it do stuff well. It's early days still and I might still encounter issues as I demand more, but I might just create a second or third bot and treat them as 'specialists' as I would with employees.

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

#146

Post by quietsegfault »

chris_money202 wrote: post #97
jwpapi wrote: 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 like to experiment with AI flows to make iteration quicker, then once something work investing in is found, back up and build something that's actually repeatable.

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

#147

Post by quietsegfault »

chris_money202 wrote: post #141
mickeyp wrote: post #108

Earlier quoted context omitted.

You say that with the wisdom of experience. But there's still value in people exploring new spaces they find interesting, even if they do not meet your personal definition of pareto-optimal.

Exploring with AI doesn’t lead to the same level of learning. They are doing the equivalent of paying to skip the level up of their character and going to the final boss with level 1 armor

I look at it more like speedrunning a level. You're skipping the parts of the level that take up the most time, some times using hacks. Is it universally as much fun as playing the game? No, just like using AI to prototype might get you to the same place, but without the experience of discovery and blockers along the way.

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

#148

Post by gbro3n »

Gareth321 wrote: post #139
gbro3n wrote: post #130

Earlier quoted context omitted.

I've used open claw (just for learning, I agree with the author it's not reliable enough to do anything useful) but also have a similar daily summary routine which is a basic gemini api call to a personal mcp server that has access to my email, calendar etc. The latter is so much more reliable. Open claw flows sometimes nail it, and then the next day fails miserably. It seems like we need a way to 'bank' the correct…

That unreliability was why I gave up on OpenClaw. I tried hard to give it very simple tasks but it had a high degree of failure. Heartbeats and RAG are lightyears away from where they need to be. I'm not sure if this can be overcome using an application layer right now, but I trust that many people are trying, and I'm eager to see what emerges in the next year. In the mean time I know that they're working very hard o…

That would be great if that comes to fruition. Investing in a model with weights updates would be like investing in employee training, rather than just giving the same unreliable employee more and more specific instructions.

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

#149

Post by gbro3n »

mike_hearn wrote: post #145
gbro3n wrote: post #130

Earlier quoted context omitted.

I've used open claw (just for learning, I agree with the author it's not reliable enough to do anything useful) but also have a similar daily summary routine which is a basic gemini api call to a personal mcp server that has access to my email, calendar etc. The latter is so much more reliable. Open claw flows sometimes nail it, and then the next day fails miserably. It seems like we need a way to 'bank' the correct…

This is interesting. I haven't used OpenClaw but I set up my own autonomous agent using Codex + ChatGPT Plus + systemd + normal UNIX email and user account infrastructure. And it's been working great! I'm very happy with it. It's been doing all kinds of tasks for me, effectively as an employee of my company. I haven't seen any issues with memory so far. Using one long rolling context window, a diary and a markdown wi…

What sort of tasks do you have it do for you?

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

#150

Post by wat10000 »

operatingthetan wrote: post #110
wat10000 wrote: post #103

Earlier quoted context omitted.

What a bizarre article. The morality of recreational torture is not a matter of factual correctness. Burden of proof is not a concept that makes any sense when there’s a disagreement over morality. You can make arguments for your position and those arguments may involve factual claims which can be proven or disproven, but the underlying morality can’t. And then it ends with that sudden left turn into denouncing athei…

It appears that analytic philosophy may not be for you.

If it thinks I’m evil then clearly they don’t want me.
Post reply on HN