Rendered at 15:09:18 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
rancar2 23 hours ago [-]
The readme links to the paper (in the badges), which is more helpful in understanding the project: https://arxiv.org/pdf/2610.14224
mchusma 23 hours ago [-]
I agree with what this paper generally says...but doesn't it seem like something anyone developing ai systems already do? Learn from past runs to update your skills and system prompt etc? I know I have done this a lot over the last year+.
jmathai 23 hours ago [-]
I think many of us have already started automating it so that they update alongside code changes.
cykros 20 hours ago [-]
Maybe I need to give this a more thorough read through, but it sounds largely like what harnesses, or at least, Hermes-agent, are/is already doing. That is. Learning from feedback and creating reusable skills in order to avoid so much reinventing of the wheel, in line with how the user's demands direct things.
Hermes is awesome and perhaps more should be mimicking them as they find paths forward, but is there anything different in kind here going on than they're already doing?
endangeredhuman 14 hours ago [-]
They had Gemini CLI as open-source, used the community for validation, then moved to closed-source Antigravity CLI.
If the harness is closed, why open the "harnessing"?
1 days ago [-]
ridgeComet617 1 days ago [-]
Honestly the readme image bugs me less than the lack of a single end to end example you can actually run.
amritananda 1 days ago [-]
Yeah, doesn't help that the "video overview" is just an animated slideshow of benchmarks. I guess that tells us who the intended audience is.
mobilejdral 1 days ago [-]
The promo committee?
RamblingCTO 1 days ago [-]
I always wanted to exponentially grow slop, thank you. The less I understand about what's happening, the better. Totally what I as a user want. Thanks G.
tjpnz 1 days ago [-]
>Harness² is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design.
Huh?
eithed 21 hours ago [-]
Your harness tells agent to do A when it encounters B. When agent encounters C and it doesnt know what to do it does D and you correct it to do E. Harness keeps track of this and makes agent do E next time it encounters C.
imafish 23 hours ago [-]
It's a plug-and-play framework for recursive agent harnessing. In an open world, agents encounter tasks unseen during the harness design. Harness² is designed for this exact scenario.
xyzsparetimexyz 1 days ago [-]
I love that even google is using slop images in readmes now
0gs 1 days ago [-]
pretty convincing argument to be made that big G invented human web slop AND AI slop, full slop
chubot 1 days ago [-]
Well I wouldn't say "invented", but I'd agree with "incentivized at scale until it became a cancer on the web"
The weird thing is that YouTube seems to have incentivized a lot of good content. Sure there is "scalable slop" like Mr. Beast, but there is also good content on YouTube (Fall of Civilizations podcast, etc.).
Somehow on the web I am not seeing a lot of good content incentivized by ads. I see a lot of WikiHow-type stuff.
It seems like writing moved to Substack and so forth.
hirako2000 20 hours ago [-]
That YouTube got great content, is that it has a quasi monopoly on video streaming.
Also the reason the noise ratio is high with junk, and now shorts.
lompad 1 days ago [-]
Yep. They are the Slopfather, basically.
tohms 1 days ago [-]
[dead]
behnamoh 24 hours ago [-]
[flagged]
embedding-shape 24 hours ago [-]
Well, as luck have it, Google don't let individuals be individuals if they work for Google, so anything under github.com/google or github.com/google-research could be a weekend hack project from an individual with zero association to Google itself, or the most supported project at Google, everything always go under Google's name if you work for Google. Basically, free-time as the typical person understands it, does not exists if you work for Google.
The disclaimer in the bottom of these project makes the distinction a bit clear, once you got to the bottom of the README:
> Disclaimer This is not an officially supported Google product.
Hermes is awesome and perhaps more should be mimicking them as they find paths forward, but is there anything different in kind here going on than they're already doing?
If the harness is closed, why open the "harnessing"?
Huh?
The weird thing is that YouTube seems to have incentivized a lot of good content. Sure there is "scalable slop" like Mr. Beast, but there is also good content on YouTube (Fall of Civilizations podcast, etc.).
Somehow on the web I am not seeing a lot of good content incentivized by ads. I see a lot of WikiHow-type stuff.
It seems like writing moved to Substack and so forth.
Also the reason the noise ratio is high with junk, and now shorts.
The disclaimer in the bottom of these project makes the distinction a bit clear, once you got to the bottom of the README:
> Disclaimer This is not an officially supported Google product.