Hacker News Reader

Comment by krtagf | Hacker News Reader

[flagged]

This doesn't seem to be promoting every new monstrosity?

"m definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level.

Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out."

> just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level.

Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

Yeah, in the interest of full disclosure, while Claws seem like a fun toy to me, I tried ZeroClaw out and it was... kind of awful. There's no ability to see what tools agents are running, and what the results of those tools are, or cancel actions, or anything, and tools fail often enough (if you're trying to mind security to at least some degree) that the things just hallucinate wildly and don't do anything useful.

The ZeroClaw team is focusing their efforts on correctness and security by design. Observability is not yet there but the project is moving very rapidly. Their approach, I believe, is right for the long term.

There's a reason I chose ZC to try first! Out of all of them, it does seem to be the best. I'm just not sure that claws, as an overall thing, are useful yet. at least with any model less capable than Opus 4.6 — and if you're using opus, then whew, that's expensive and wasteful.

The ZC PR experience is hard core. Their PR template asks for a lot of details related to security and correctness - and they check it all before merging. I submitted a convenience script that gets ZC rolling in a container with one line. Proud of that!

Regarding models, I’ve found that going with OpenRouter’s `auto` model works well enough, choosing the powerful models when they seem to be needed, and falling back on cheaper ones for other queries. But, it’s still expensive…

Depending on what you want your claw to do, Gemini Flash can get you pretty far for pennies.

> Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

I mean we're on layer ~10 or something already right? What's the harm with one or two more layers? It's not the typical JavaScript developer understands all layers down to what the hardware is doing anyways.

I will assume you know that comparison is apples and oranges. If you don’t, I’d be happy to explain.

what people read: AI Scientist says blah blah blah claws is very cool. Buy Mac, be happy.

Did you read the part where he loves all this shit regardless? That's basically an endorsement. Like after coined the vibe coding term now every moron will be scrambling to write about this "new layer".

And yet wasn’t he one of the first to run it and was one of the many people to have a bunch of his data leaked?

You're confusing OpenClaw and Moltbook there. Moltbook was the absurdist art project with bots chatting to each other, which leaked a bunch of Moltbook-specific API keys.

If someone got hold of that they could post on Moltbook as your bot account. I wouldn't call that "a bunch of his data leaked".

Indeed, via the related moltbook project that he was also hyping - https://x.com/theonejvo/status/2017732898632437932

Source on that? Hadn’t seen that

I expect him to be LLM curious.

If he has influence it is because we concede it to him (and I have to say that I think he has worked to earn that).

He could say nothing of course but it's clear that is not his personality—he seems to enjoy helping to bridge the gap between the LLM insiders and researchers and the rest of us that are trying to keep up (…with what the hell is going on).

And I suspect if any of us were in his shoes, we would get deluged with people who are constantly engaging us, trying to illicit our take on some new LLM outcrop, turn of events. It would be hard to stay silent.

We construct a circus around everything, that's the nature of human attention :), why are people so surprised by pop compsci when pop physics has been around forever.

Pop physics influences less of our day-to-day lives though.

He really is, on twitter at least. But his podcast with Dwarkesh was such a refreshing dose of reality, it's like he is a completely different person on social media. I understand that the hype carries him away I suppose.

LLMs alone may not deliver, but LLMs wrapped in agentic harnesses most certainly do.

Agree, but his content on LLM are top-notch.

Docker and k8s didn't deliver?

so what's your point? he should just not get involved in the most discussed topic in the last month and highest growth OS project?

> highest growth OS project

Did you mean OSS, or I'm missing some big news in the operating systems world?

OSS is less common than the full words with same number of syllables, Open Source, which means the same thing as OSS and is sometimes acryonymized to OS by folks who weren't deeply entrenched in the 1998 to 2004 scene.

Reply on news.ycombinator.com