Live data from Hacker News

Nvidia NemoClaw

github.com

281–290 of 291 posts

Re: Nvidia NemoClaw

#281
post #279

Earlier quoted context omitted.

I asksed you specific questions and you failed to answer all of them, I think that says everything. Thanks.

Nice job proving you can't read either. I answered everything. Gave you some critical thinking homework and you didn't do it. Great job "It's true because commit history says so" - mjr00 2026. Hall of fame comment really Try answering my questions next: 1. Do you really believe a company like Nvidia would announce a project in their yearly conference when that project was done the weekend before? 2. Do you really bel…

Nothing more to discuss here, the commit history (and your lack of coherent responses beyond hypothetical "it's technically possible it COULD have happened this way") speak for themselves. Thanks for trying though.

edit: Wait, you don't "have buddies at NVidia" -- you literally work at NVidia. Weird that you tried to hide this information? No wonder you're so desperate to pretend this project is more than it actually is though, it must be embarrassing for you that your company didn't scrub git history properly before making this public!

Re: Nvidia NemoClaw

#282
post #281

Earlier quoted context omitted.

Nice job proving you can't read either. I answered everything. Gave you some critical thinking homework and you didn't do it. Great job "It's true because commit history says so" - mjr00 2026. Hall of fame comment really Try answering my questions next: 1. Do you really believe a company like Nvidia would announce a project in their yearly conference when that project was done the weekend before? 2. Do you really bel…

Nothing more to discuss here, the commit history (and your lack of coherent responses beyond hypothetical "it's technically possible it COULD have happened this way") speak for themselves. Thanks for trying though. edit: Wait, you don't "have buddies at NVidia" -- you literally work at NVidia . Weird that you tried to hide this information? No wonder you're so desperate to pretend this project is more than it actuall…

Ding ding ding. See it would have been too easy to just say "i know for a fact". I just wanted to walk you to the conclusion. Congrats.

Now you are more enlightened about how things work. Of course Nvidia is a big company not everyone that works at nvidia knows everything about every team. That's by design. Welcome to working at a big company! I do have buddies that worked on this project internally and yes it was done over many weeks and months

Thanks for playing. I do know for a fact it's definitely not what you think it is but i had a chuckle watching you twist yourself in a knot trying to convince me you knew better. Why would i disclose information about myself? odd thing to expect from someone. But had you riled up enough to have you go looking through my comment history then my github then my website huh! Must have really struck a nerve. Don't worry i won't do the same to you. I don't care about random people yapping on the internet enough

Re: Nvidia NemoClaw

#283
post #281

Earlier quoted context omitted.

Nothing more to discuss here, the commit history (and your lack of coherent responses beyond hypothetical "it's technically possible it COULD have happened this way") speak for themselves. Thanks for trying though. edit: Wait, you don't "have buddies at NVidia" -- you literally work at NVidia . Weird that you tried to hide this information? No wonder you're so desperate to pretend this project is more than it actuall…

Ding ding ding. See it would have been too easy to just say "i know for a fact". I just wanted to walk you to the conclusion. Congrats. Now you are more enlightened about how things work. Of course Nvidia is a big company not everyone that works at nvidia knows everything about every team. That's by design. Welcome to working at a big company! I do have buddies that worked on this project internally and yes it was do…

edit: Removing, not productive to engage with this. pre-emptive apology to dang/tom if this gets cleaned up, most of this thread is not productive and I should not have continued responding much earlier.

Re: Nvidia NemoClaw

#284
post #283

Earlier quoted context omitted.

Ding ding ding. See it would have been too easy to just say "i know for a fact". I just wanted to walk you to the conclusion. Congrats. Now you are more enlightened about how things work. Of course Nvidia is a big company not everyone that works at nvidia knows everything about every team. That's by design. Welcome to working at a big company! I do have buddies that worked on this project internally and yes it was do…

edit: Removing, not productive to engage with this. pre-emptive apology to dang/tom if this gets cleaned up, most of this thread is not productive and I should not have continued responding much earlier.

Lol where did i make it sound like any of that? Just saw you confidently make the wrong claim and tried to socratic method you into understanding. You are sadly too far gone to understand

Good ad hominem. I'd be riled up too if i was publicly dressed down and proved to be wrong. So now you know, commit history doesn't mean jack sh!t. Sorry i had to ruin Christmas for you

> you guys wanted to make this look like it was written in a weekend though

Imagine thinking this was done to convince anyone about the TIME it took to write this project. Here's a very simple explanation, those commits reflect a PORT over to public Github to reflect launch. Author chose to do it in some number of commits instead of "feat: Full implementation in one commit". The port happened before their announcement. Not the write of it

Now I won't propose hypotheses because clearly the socratic method didn't work on you. So now sit down and learn how things work

And next time, try not to be so confidently wrong on the internet. I had a very good laugh watching you twist and turn yourself. Must have been typing furiously thinking you really were in the right :)

Re: Nvidia NemoClaw

#285
post #283

Earlier quoted context omitted.

edit: Removing, not productive to engage with this. pre-emptive apology to dang/tom if this gets cleaned up, most of this thread is not productive and I should not have continued responding much earlier.

Lol where did i make it sound like any of that? Just saw you confidently make the wrong claim and tried to socratic method you into understanding. You are sadly too far gone to understand Good ad hominem. I'd be riled up too if i was publicly dressed down and proved to be wrong. So now you know, commit history doesn't mean jack sh!t. Sorry i had to ruin Christmas for you > you guys wanted to make this look like it wa…

edit: Removing, not productive to engage with this.

Re: Nvidia NemoClaw

#286
post #285

Earlier quoted context omitted.

Lol where did i make it sound like any of that? Just saw you confidently make the wrong claim and tried to socratic method you into understanding. You are sadly too far gone to understand Good ad hominem. I'd be riled up too if i was publicly dressed down and proved to be wrong. So now you know, commit history doesn't mean jack sh!t. Sorry i had to ruin Christmas for you > you guys wanted to make this look like it wa…

edit: Removing, not productive to engage with this.

This is quite funny

> Why are you people so desperate to pretend this wasn't written in a weekend?

Because it wasn't? And your only "proof" of it was commit history. "You're telling me to not believe my lying eyes" hilarious. You are being told again and again that it means nothing. It's not blockchain. You are allowed to write commits as you see fit without making it a system of record of time spent

> People with above room temp IQ can figure out what's going on here

Yes we can. We have one person convinced they can look at commit history and say for sure that is exactly when that code was written. No developer agrees with you. As you have been told a couple times by other people above as well

It's quite obvious you work at some small shop or are a freelancer and have never done work in any kind of big environment. No you cannot just open source a "weekend" project at any big company. Wherever you are you may be allowed to vibe code and ship something under your company's github willy nilly.

It's just not the reality in any serious place. No one is trying to deceive you. You have just deceived yourself. Thanks again for playing

You can have the last word you are so desperate for

Re: Nvidia NemoClaw

#287
post #268

Earlier quoted context omitted.

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.

> there's overwhelming evidence that their public github history is accurate and Nemoclaw was written in a weekend

Aside from commits on github, which we've already established mean absolutely nothing, what is the overwhelming evidence?

Re: Nvidia NemoClaw

#288
post #276

Earlier quoted context omitted.

> 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? Answer this question or we're done here, thanks. > Almost certainly this was built in house for at least a month or two prior. Then private repo. Approvals. Then public. Source, other than you making it up? > That's more plausible than the very normal prac…

You cannot really be this naive but i'll play along: > 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? Like i said. You are letting on that you have never actually worked on an internal project that is going to go open source. There are a million and one reasons. Here are some completely normal and plausible ones. It was wor…

> Here are some completely normal and plausible [reasons]. It was worked on over weeks internally, commits referenced other internal NVIDIA software/libraries they used. It name dropped projects and code names. Maybe it was just an extremely long chain of messy commits that is improper to have on a potentially big open source repo.

... it referenced internal servers and they want to scrub that for security reasons

... it might have had secrets embedded at some point because it was a quick and dirty proof-of-concept

... it could have had swear words in the code

... it had enormous binaries checked in at one point and they don't want the repo to be huge

... they don't want you to know the names of everyone that worked on it

... it's forked off other internal work that isn't public yet

There are so many reasons that the easiest thing to do is just snapshot it and have minimal public git history. Some places I've worked make it so publicly, there's one commit per release. Did NVidia do this? Well, they didn't collapse it down to a single commit, but we have no evidence that the commits we see were the actual internal development timeline.

Re: Nvidia NemoClaw

#290
NemoClaw solves the sandbox problem. The spend problem is still open.

OpenShell can block network egress to suspicious-exchange.io, but it doesn’t know that your agent is about to spend $500 there, or that it has already spent $450 today on other endpoints.

I built Dreamline for this on-chain spend governance that sits alongside NemoClaw. Before any payment the agent calls /proxy/pay. The blacklist lives in a BNB Chain smart contract, independent of both NemoClaw and Dreamline servers.

PR on NemoClaw repo: github.com/NVIDIA/NemoClaw/pull/923

Post reply on HN