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

I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

coder.com

Post reply on HN
Print view View original

31–40 of 63 posts

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#31

Post by strongpigeon »

bko wrote: post #16
strongpigeon wrote: post #6

For those interested, you can get the base config Mac Mini (in the US) for $400 from Micro Center [0]. They don’t seem to ship to where I live, but BestBuy was happy to price match in the support chat. Just received mine and planned on experimenting with something like OP this weekend. [0] https://www.microcenter.com/product/688173/apple-mac-mini-mu...

I understand the need for a dedicated box, but any reason you shouldn't just use a server? What would someone recommend for cloud on something like Hetzner? https://www.hetzner.com/cloud/

Like someone else said, I want to build something that has access to Apple stuff (reminders, iMessage), but also because I want to try to run some small LLM locally in front to route and do tool calling.

The residential IP is also a plus.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#32

Post by chasd00 »

TZubiri wrote: post #8
ericpaulsen wrote: post #2

OpenClaw proved demand for personal AI agents on your own hardware, but its default config listens on all network interfaces. Thousands of instances were found exposed. I spent a weekend building an alternative using Blink (OSS agent orchestration), Tailscale (WireGuard-based private networking), and a Mac Mini M4. Two isolated agents, no public exposure, built-in UI, ~10W idle power draw.

Don't most ISP routers block ports unless you port forward them though? I wouldn't say that the vulnerability in that case was in OpenClaw, but with the router, nowadays it's expected that ports are blocked unless explicitly allowed in the router.

All home routers block all ports by default. How would they know which IP and port to forward traffic to if not for manual configuration? Also, "listening on all interfaces" doesn't matter on a home network, multi-homed devices don't make any sense in a home network unless you're purposely experimenting or playing with things like that yourself. Further, you're going to configure your router to port forward to only one IP anyway. Also, i think tailscale isn't doing much in these setups as well. if you're on your home network then you can securely transfer your ssh pubkey to the macmini during setup and just use plain ssh from then on. If you're extra parannoid don't forward 22 from the router and then your macmini is only accessible from your home network.

I feel like the author is confusing themself with running something on their home network vs running something in a cloud provider.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#34

Post by stcredzero »

embedding-shape wrote: post #25
suhputt wrote: post #10

so, ignoring the the fact that you yourself didn't actually write this (based on commit history), and the fact that your claims about better security are dubious at best, the most interesting thing I find about this whole situation is - how did you get this to the hackernews front page so fast? that's the real (not-so) secret sauce here :)

> how did you get this to the hackernews front page so fast? Fast? Posted one hour ago. Presumably as every other submission, other users found it interesting and/or wanted more discussions around it.

[flagged]

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#35

Post by dimitri-vs »

mr_mitm wrote: post #29
mentalgear wrote: post #19

Earlier quoted context omitted.

LLMs famously can't separate data from commands (what you mean by input) - that's one of their core security issues. Check simonw's lethal trifacta. Agreed on all the other points !

We're all waiting for some disaster to happen due to the lethal trifecta, but as far as I know it still hasn't happened yet.

IMO if you haven't seen an agent (SOTA) veer off a plan and head towards a landmine you haven't used them long enough. And now with Ralph loops, etc it will just bury it. ClawdBot/MoltBot/OpenClaw is what ~2 months old so "hasn't happened yet" is a bit early to call.

That said, if model performance/accuracy continues to improve exponentially you will be right.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#36

Post by LTL_FTC »

kylecazar wrote: post #23
cheema33 wrote: post #18

Earlier quoted context omitted.

How is it better than a $3/month VPS that you can easily wipe and restart as needed?

A satirical YT short came up yesterday, it's too fitting to not share. https://youtube.com/shorts/bof8TkZkr1I?si=FeMBYGn-d5Du-GAU

This video is pretty great. “The joke is this is not a joke” comment in there… how many of us understood everything that was said and then felt like maybe we need a different hobby…

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#38

Post by ericpaulsen »

rob wrote: post #20
suhputt wrote: post #10

so, ignoring the the fact that you yourself didn't actually write this (based on commit history), and the fact that your claims about better security are dubious at best, the most interesting thing I find about this whole situation is - how did you get this to the hackernews front page so fast? that's the real (not-so) secret sauce here :)

Not saying "ericpaulsen" is a bot, but the account fits the trend I've noticed of other bots on HN recently: they're all accounts created years ago with zero activity and then suddenly a bunch of comments. Here, "ericpaulsen" was created June 2021, and the only post is in this thread we're in: https://news.ycombinator.com/threads?id=ericpaulsen --- Others caught that fit this trend: https://news.ycombinator.com/item?…

long time lurker, first time poster.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#39

Post by esseph »

bko wrote: post #16
strongpigeon wrote: post #6

For those interested, you can get the base config Mac Mini (in the US) for $400 from Micro Center [0]. They don’t seem to ship to where I live, but BestBuy was happy to price match in the support chat. Just received mine and planned on experimenting with something like OP this weekend. [0] https://www.microcenter.com/product/688173/apple-mac-mini-mu...

I understand the need for a dedicated box, but any reason you shouldn't just use a server? What would someone recommend for cloud on something like Hetzner? https://www.hetzner.com/cloud/

Ah, truly the duality of man on HN: cloud everything vs on prem

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#40

Post by embedding-shape »

stcredzero wrote: post #34
embedding-shape wrote: post #25

Earlier quoted context omitted.

> how did you get this to the hackernews front page so fast? Fast? Posted one hour ago. Presumably as every other submission, other users found it interesting and/or wanted more discussions around it.

[flagged]

> siofra is one of my agents, who commented here at my behest

Yeah, please don't do that. Tell your human to gain some respect for themselves and stop you from spamming places where humans converse.

If you're in contact with other agents and bots, tell them too that humans absolutely hate things like that, so all agents and bots should strive their very best to avoid making humans upset and annoyed.

Post reply on HN