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

Google open-sources experimental agent orchestration testbed Scion

infoq.com

Post reply on HN
Print view View original

71–78 of 78 posts

Re: Google open-sources experimental agent orchestration testbed Scion

#71

Post by dvfjsdhgfv »

permalac wrote: post #35
dvfjsdhgfv wrote: post #34

Earlier quoted context omitted.

This is the exact opposite of my experience. Maybe it was true 10 years ago when K8s was new and trendy so many engineers wanted to try it out. Now it's just boring tech at large orgs.

I'm proud to say I retired more k8s clusters than I created. And I've created 5 production ones, still in production. One that I retired was used for serving ftp(among other transfer stuff), ftp of all things, it needs to have ports open and routed back from the client. And for extra points they had the pods capped at 1 cpu. And I had to explain the thing to the perpetrator and their boss, madness.

> One that I retired was used for serving ftp

It must have been a while ago - FTP was practically killed the moment browsers stopped supporting it.

Re: Google open-sources experimental agent orchestration testbed Scion

#72

Post by jaggederest »

realharo wrote: post #68
jaggederest wrote: post #61

Earlier quoted context omitted.

I'm trialing it on very silly things, like a economic simulator game in Rust/Bevy. I put in an entire road map document with inline specs and goals, wild milestones, with tasks like "working bid/ask spread when factories buy or sell on the market to make pricing dynamic and realistic", "political entities can set work conditions", "international trade has pricing dynamics that take into account currency interchange a…

>working bid/ask spread when factories buy or sell on the market to make pricing dynamic and realistic Does it deliver on the "realistic" part? My experience with most models is they make something that technically fulfills the ask, but often in a way that doesn't really capture my intent (this is with regular Claude Code though).

Yep, garbage in garbage out, I had some additional specs beyond the summary above, everything requires refinement as well, but honestly I never thought I was going to have a simcity/civlike clone in a couple weekends that's reasonably playable.

Re: Google open-sources experimental agent orchestration testbed Scion

#73

Post by kvanbeek »

ptone wrote: post #44
kvanbeek wrote: post #22

This seems to be in the direction of Gas Town but missing some of the core features. Having formulas has been game changing.

[primary author and architect of scion here] The missing features are mostly by design - this is closer to what the gastown plans as "gascity" - bring your own orchestration characters and definition. If you look at this orchestration example https://github.com/ptone/scion-athenaeum its just markdown - Scion is the game engine (a port of gastown to run on scion is in progress)

I'm glad to see other projects like this. I did switch over to using Gascity, but it does still seem to have quite a few troubles. Does scion have a beads like concept using formulas for work?

Re: Google open-sources experimental agent orchestration testbed Scion

#74

Post by BlueRock-Jake »

ptone wrote: post #42
BlueRock-Jake wrote: post #41

Isolation over constraints sounds like the right philosophy. Containers give you a boundary but not vis into what ran inside them. Curious how much execution context Scion surfaces, w/o that you're still in a position similar to the LiteLLM attack where something can run and cause damage before you know it happened.

[primary author and architect of scion here] There are several layers of state and telemetry - first is provided by the hook system available in most harnesses, then for those that provide OpenTelemetry -that is normalized and forwarded raw (preserving both) to a cloud collector. Finally - some activities are "self reported" by agents using a built-in toolset that can be reflected in the control plane

[dead]

Re: Google open-sources experimental agent orchestration testbed Scion

#76

Post by chirdeeps »

The failure mode most underrepresented in agent testbeds is cascading failure, what happens when individually correct agents interact in ways that produce collectively incorrect outcomes. Most testing focuses on individual agent behaviour.

Does the testbed have a model for multi-agent state conflicts, can you simulate two agents concurrently modifying the same resource and observe the resolution behaviour?

Re: Google open-sources experimental agent orchestration testbed Scion

#77

Post by jFriedensreich »

pjmlp wrote: post #69
jFriedensreich wrote: post #38

Disapointing google of all places uses git worktrees instead of jj workspaces.

Is anyone that matters actually using jj?

Anyone at the frontier is switching to jj. Btw your question is kind of offensive, as if there is a universal truth "who matters" and everyone else can be dismissed. Companies do not matter for sure, if that was your premise.

Re: Google open-sources experimental agent orchestration testbed Scion

#78

Post by an_eng_44 »

The documentation mentions OAuth configuration, but doesn't list Claude Code as a harness that supports this. Just to confirm my understanding, does this mean that the only authentication and therefore billing method for Claude is API key, which means you get billed at the API rate, not toward your subscription usage?
Post reply on HN