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+.
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.
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.
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.
The readme links to the paper (in the badges), which is more helpful in understanding the project: https://arxiv.org/pdf/2610.14224
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+.
I think many of us have already started automating it so that they update alongside code changes.
Honestly the readme image bugs me less than the lack of a single end to end example you can actually run.
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.
The promo committee?
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.
>Harness² is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design.
Huh?
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.
I love that even google is using slop images in readmes now
pretty convincing argument to be made that big G invented human web slop AND AI slop, full slop
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.
Yep. They are the Slopfather, basically.