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

Reverse-engineering Viktor and making it open source

matijacniacki.com

Post reply on HN
Print view View original

41–50 of 87 posts

Re: Reverse-engineering Viktor and making it open source

#41

Post by zggf »

empath75 wrote: post #39

I just want to point out _how easy it is_ to build any of these tools yourself. I got inspired by nano-claw and built on some of it's ideas to build a whole k8s hosted autonomous agent platform and got it into production in 2 weeks. It's just some api calls and container orchestration. The only hard problem _and it is hard_, is securing it, because you basically have to treat the agents as potentially malicious.

Agree, anything that agent has access to is like giving it to malicious user. Especially when agent is exposed to different users that should have different permission levels

Re: Reverse-engineering Viktor and making it open source

#44

Post by zggf »

xnx wrote: post #21
kklisura wrote: post #20

I find it fascinating that this is just some _plumbing_ around some LLM - sold as a product and "AI coworker". They don't own the LLM model. You're just one silent update from not delivering what you promised.

Thin wrappers over an LLM has been an extremely popular grift for the past few years.

Agree, and cost of creating those thin wrappers is rapidly approaching zero

Re: Reverse-engineering Viktor and making it open source

#45

Post by limagnolia »

skeledrew wrote: post #34
zvqcMMV6Zcr wrote: post #6

Earlier quoted context omitted.

Terms of service might matter more for terminating that user account. Whole ordeal is just plain copyright violation. The author had no licence to that internal code, and whitewashing it with LLM will achieve nothing. That case is much clearer than that recent GPL->BSD attempt story.

According to US courts, the output can't be copyrighted at all. It's automatically in public domain after the "whitewash", regardless of original copyright. https://www.morganlewis.com/pubs/2026/03/us-supreme-court-de...

Thats not at all what this ruling said. What the courts found was that an AI cannot hold copyright as the author. That copyright requires a human creative element. Not that anything that was generated by an LLM can't be subject to copyright.

As an example, a photo taken from a digital camera can be subject to copyright because of the creative element involved in composing and taking the photo. Likewise, source code generated by an LLM under the guidance of a human author is likely to be subject to the human authors copyright.

Re: Reverse-engineering Viktor and making it open source

#48

Post by zggf »

krzkaczor wrote: post #33
popcorncowboy wrote: post #15

Every part of this is genuinely funny. Viktor launching basically OpenClaw for slack (because claw is MIT so yolo let's go mac some monnney and PJ outta Dubai etc etc). Some guy getting all their source code just by asking Viktor for it. Then rebuilding their core in a couple days because there's basically nothing there. push MIT to Github. TeamViktor's faces surely? But they're busy diamond handsing all the way to t…

I don't get it, what OP actually reverse engineered? OpenClaw itself? Of did Viktor team created their own OpenClaw like agent?

Exactly, the team designed their own agent architecture tailored to slack and enterprise setting, that is not based on any popular agent architecture like OpenClaw, NanoClaw, IronClaw or any others that I checked against.

Re: Reverse-engineering Viktor and making it open source

#49

Post by john_strinlai »

popcorncowboy wrote: post #15

Every part of this is genuinely funny. Viktor launching basically OpenClaw for slack (because claw is MIT so yolo let's go mac some monnney and PJ outta Dubai etc etc). Some guy getting all their source code just by asking Viktor for it. Then rebuilding their core in a couple days because there's basically nothing there. push MIT to Github. TeamViktor's faces surely? But they're busy diamond handsing all the way to t…

>MIT so yolo let's go mac some monnney and PJ outta Dubai etc etc

>TeamViktor's faces surely? But they're busy diamond handsing all the way to the moon so probably don't even care. XD

would anyone please be so kind to translate these parts of this comment into something a 45+ year old would understand?

Re: Reverse-engineering Viktor and making it open source

#50

Post by dsjoerg »

empath75 wrote: post #39

I just want to point out _how easy it is_ to build any of these tools yourself. I got inspired by nano-claw and built on some of it's ideas to build a whole k8s hosted autonomous agent platform and got it into production in 2 weeks. It's just some api calls and container orchestration. The only hard problem _and it is hard_, is securing it, because you basically have to treat the agents as potentially malicious.

It's because of this hard problem that I'm thinking I should keep using Viktor (getviktor.com) instead of running this OpenViktor.

The company may not do a perfect job of security either, but I figure they'll do a better job than I can as a solo practitioner.

Post reply on HN