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

Nvidia NemoClaw

github.com

Post reply on HN
Print view View original

241–250 of 291 posts

Re: Nvidia NemoClaw

#241

Post by defrost »

bigfishrunning wrote: post #240
BeetleB wrote: post #202

Earlier quoted context omitted.

> Now this tool spreads. You help everyone get it set up. Someone hacks the site You sound like my dad in the 90's, when it came to modems. Same tool. Good uses. Bad uses. The bad doesn't negate the good (c.f. Bittorrent).

I could make that same argument about giving my 9 year old a chainsaw and telling her to cut some wood In the best case, some wood gets cut. There are many many worse things that can happen But hey, same tool. Good uses. Bad uses.

The trick is to give them a tree pruning chain saw, one intended for climbing tree loppers to use one handed - it's an ideal weight for nine years old to use two handed.

And to supervise.

As tested on my children and grand children.

Also, if you happen to have a furnace with a large pot of molten glass, five year olds are capable (given a stand) of making marbles from the furnance and will do that for hours if you can spare the time to let them.

Re: Nvidia NemoClaw

#243

Post by BeetleB »

bigfishrunning wrote: post #240
BeetleB wrote: post #202

Earlier quoted context omitted.

> Now this tool spreads. You help everyone get it set up. Someone hacks the site You sound like my dad in the 90's, when it came to modems. Same tool. Good uses. Bad uses. The bad doesn't negate the good (c.f. Bittorrent).

I could make that same argument about giving my 9 year old a chainsaw and telling her to cut some wood In the best case, some wood gets cut. There are many many worse things that can happen But hey, same tool. Good uses. Bad uses.

Exactly. Would you go around telling normal people that chainsaws are bad, because of how harmful they are in the hands of 9 year olds?

Re: Nvidia NemoClaw

#244

Post by jamiemallers »

Netcob wrote: post #228
observationist wrote: post #133

Earlier quoted context omitted.

What makes it even better is that these dogs are like Malinois. If they want to get into something, they will; people have had their entire network compromised by bots they left running overnight, and any important information like account logins and so on runs the risk of being misused. It's one thing to sandbox, maybe give the bot a temporary, limited $100 card or account to go perform a specific task, but there's…

I think it's a use case that identity/authorization/permission models are simply not made for. Sure, we can ban users and we can revoke tokens, but those assume that: 1. Something potentially malicious got access to our credentials 2. Banning that malicious entity will solve our problem 3. Once we did that, repaired the damage and improved our security, we don't expect the same thing to happen again None of these app…

[dead]

Re: Nvidia NemoClaw

#245

Post by ranger_danger »

ethbr1 wrote: post #235
macNchz wrote: post #189

Earlier quoted context omitted.

No maliciousness or injection required, even the newest and most resistant models can start doing weird stuff on their own, particularly when they encounter something failing that they want to work. Just today I had Opus 4.6 in Claude Code run into a login screen while building and testing a web app via Playwright MCP. When the login popped up (in a self-contained Chromium instance) I tried to just log in myself with…

> it turned out Claude had run code to query superadmin users in the database, picked the first one, and changed the password to `password123` so it could log in on its own. Man, every LLM quirk behavior really is a thing a monomaniacal junior dev would do...

LLMs are trained on data produced by humans after all :)

Re: Nvidia NemoClaw

#250

Post by brian_r_hall »

The permission scope debate always ends up in the same place. Lock it down too much and it's useless, loosen it up and you're back to square one. And the boundary keeps moving as the agent gets more capable anyway.

What nobody's really talking about is the moment of action itself. Not whether the agent has bash access but whether this specific call should run given what it's actually trying to do right now. That's a completely different problem and nobody's really solved it.

Post reply on HN