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

261–270 of 291 posts

Re: Nvidia NemoClaw

#261

Post by cloudfudge »

mjr00 wrote: post #185
elif wrote: post #163

Earlier quoted context omitted.

alright so the git history goes back 4 days. I learned about nemoclaw 5 days ago here: https://www.youtube.com/watch?v=fL2lMpLjxWA but it was reported 8 days ago here: https://www.youtube.com/watch?v=345GsxnrHHg I am not anyone special. I don't know anything about nvidia. I just know that the "4 day history" you think matters, is not a reasonable belief given that random youtubers have been reporting on it. and by "w…

There's nothing clean about the history. You think commits like [0], with the commit message "improve", count as "clean"? What do you think the motivation for the author would be to modify git history to make it appear that this was written over a weekend, including separating each feature/commit by a few hours, which corresponds to a reasonable amount of time that it may have taken to write that feature? Including a…

Just let go of the notion that a 4 day github history necessarily means the project is only 4 days old. It's a ridiculous assumption to base an argument off of. It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits. There is zero reason for them to let you see their internal progress.

Re: Nvidia NemoClaw

#262

Post by dudeinhawaii »

aavci wrote: post #188

How does this compare the building your own bot that has access to these tools: - web plugin - api access to messaging - access to a job scheduler

This has been my approach and of course what you lose is the "random and surprising" (maybe good) but also the "evolutionary" aspect.

So, if you write strong tooling (even with AI) around the connection points - you can create blackboxes tht are secure and only allow the agent to perform certain actions. The blackbox email service calls out to a secure store (for keys/etc) and accesses your emails in a read-only way, etc (for example).

Everything is then much more intentional. You're writing tools for your agent but you also can't do fun or evolutionary things which is most of the fun behind OpenClaw. That and many people seem to genuinely see them as 'pets' or 'strange Ai friends' but that's a different problem and it's due to the interesting methods OpenClaw uses to give the illusion of intelligence, always on, and memories. These are all well know (variations on RAG, markdowns, etc)

Re: Nvidia NemoClaw

#263

Post by pmdr »

sailfast wrote: post #255
pmdr wrote: post #237

Earlier quoted context omitted.

LLMs have earned their place in many jobs, but I struggle to see claws as more than a rather expensive waste of time and tokens. Downsides are gargantuan, effects of dead internet theory will be ubiquitous.

Maybe? But I guess I won't find out until I try it a bit. For now, I'm not posting anything - just managing some calendars and inboxes and task lists and saving me some data entry. Not sure how that makes downsides gargantuan, or contributes to the internet dying. (Though obviously the bot will get worse as the internet continues to die if that's what it's using as a source)

> or contributes to the internet dying.

People will set these things to run wild on all platforms. Talking to real humans will be a luxury.

Re: Nvidia NemoClaw

#264

Post by jwilber »

BeetleB wrote: post #59
jwilber wrote: post #58

Earlier quoted context omitted.

I agree with the sentiment that there are use cases for web scraping where an agent is preferable to a cron job, but I think your particular example can certainly be achieved with a cron job and a basic parser script. Just have Claude write it.

I didn't say it's not doable. I'm not even saying it's hard. But nothing beats telling Claw to do it for me while I'm in the middle of groceries. Put another way: If it can do it (reliably), why on Earth would I babysit Claude to write it? The whole point is this: When AI coding became a thing, many folks rediscovered the joy of programming, because now they could use Claude to code up stuff they wouldn't have bother…

Fair point, I just think that example is better off running on a cron job than using compute from llm inference, (though that will become negligible over time, anyways).

Re: Nvidia NemoClaw

#265

Post by huey77 »

Can someone who has set up a lobster and given it access to their life please tell me how it’s going? Or has gone? I’ve been waiting and watching and I’m yet to be convinced this is a good idea! But maybe I’m missing something? Looking for a new prospective here, not a jab at your set up. It’s just besides all the media and general consensus from tech people I know, it sounds like a security nightmare.

Re: Nvidia NemoClaw

#266

Post by mjr00 »

cloudfudge wrote: post #261
mjr00 wrote: post #185

Earlier quoted context omitted.

There's nothing clean about the history. You think commits like [0], with the commit message "improve", count as "clean"? What do you think the motivation for the author would be to modify git history to make it appear that this was written over a weekend, including separating each feature/commit by a few hours, which corresponds to a reasonable amount of time that it may have taken to write that feature? Including a…

Just let go of the notion that a 4 day github history necessarily means the project is only 4 days old. It's a ridiculous assumption to base an argument off of. It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits. There is zero reason for them to let you see their internal progress.

> It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits.

Did you even read the commit history? That is not what is happening here.

This is turning into a "don't believe your lying eyes" situation. Why are you people so desperate to pretend this wasn't written in a weekend?

> There is zero reason for them to let you see their internal progress.

Again, I ask you -- what is the reason for them to edit commit history to show incremental progress as if it were written in a weekend, when it actually was not?

Re: Nvidia NemoClaw

#267

Post by cloudfudge »

mjr00 wrote: post #266
cloudfudge wrote: post #261

Earlier quoted context omitted.

Just let go of the notion that a 4 day github history necessarily means the project is only 4 days old. It's a ridiculous assumption to base an argument off of. It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits. There is zero reason for them to let you see their internal progress.

> It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits. Did you even read the commit history? That is not what is happening here. This is turning into a "don't believe your lying eyes" situation. Why are you people so desperate to pretend this wasn't written in a weekend? > There is zero reason for them to let you see their internal…

I don't have to know their reasoning in order to know public github history is not necessarily an accurate record of all changes.

Re: Nvidia NemoClaw

#268

Post by mjr00 »

cloudfudge wrote: post #267
mjr00 wrote: post #266

Earlier quoted context omitted.

> It's extremely normal to have work in one, perhaps internal, repo which you then blast over to a public repo in one (or a few) big commits. Did you even read the commit history? That is not what is happening here. This is turning into a "don't believe your lying eyes" situation. Why are you people so desperate to pretend this wasn't written in a weekend? > There is zero reason for them to let you see their internal…

I don't have to know their reasoning in order to know public github history is not necessarily an accurate record of all changes.

Okay, so there's overwhelming evidence that their public github history is accurate and Nemoclaw was written in a weekend, and the only reason to think it's not accurate is that... it's technically possible to edit git history, and also there's no reasonable explanation for why they would have edited git history they way they did.

So... yeah, draw your own conclusion I guess, whatever.

Re: Nvidia NemoClaw

#269

Post by tenahu »

meindnoch wrote: post #165
acedTrex wrote: post #159

Earlier quoted context omitted.

This is the most delusional comment i think i have ever read on this site. It didn't make sense until i read the part about "Founders and CEOs" and realized it was not a post about any serious software enterprise.

Yeah, it's satire. But the number of upvotes I'm getting on it is a bit concerning.

Well it is subtle satire done well because another person could write the same thing and be completely serious.

Re: Nvidia NemoClaw

#270

Post by Sateeshm »

cyanydeez wrote: post #131
empiricus wrote: post #67

Earlier quoted context omitted.

you put the dog in crate with a COPY of your documents.

Your dog has now ordered a hitman to kill you, assume your identity and to live vacariously as a simple bartender at Cheers.

It's a dog eat dog world and I'm wearin a milk bone underwear
Post reply on HN