> If LLMs are electricity, harnesses are the “electronics.” (...) the harnesses ...

conmod278 · 2026-08-23T15:31:03

https://www.latent.space/p/attention-interface

Labs are now post-training models with Harness so that Harness now gets absorbed into the weights.

layer8 · 2026-08-23T16:40:12

I’d say that harnesses almost by definition are the parts that you want to keep customizable. That won’t get absorbed into the weights.

datsci_est_2015 · 2026-08-23T18:13:17

Depends on your product strategy. If you only care about how your model will be used in the context of a harness (perhaps, specifically the harness that you designed), then the incentive is plainly there to optimize the weights within the context of the harness.

wyre · 2026-08-24T01:13:52

What is being absorbed into weights is tool usage. It is incredibly counterproductive to train models on a specific harness, when instead it can be trained to reason about the tools that it has available to itself and how to best use those tools to accomplish it's goal.

Would you rather hire an engineer that can adopt to your org's prefered tooling, or hire an engineer that can only perform well with their own favorite tools? It's the same thing.

goosejuice · 2026-08-23T16:15:31

My naive intuition is that as harnesses converge on shape and models improve the first party advantage will mostly disappear.

theturtletalks · 2026-08-23T15:37:06

I was saying more the custom skills and extensions that make the harness not a commodity. Yes people will use Claude Code, Codex, or Pi but their customizations will make their harness unique and more powerful.

gritzko · 2026-08-23T16:15:07

Either part can be branded a "commodity" or a "sovereign privilege" depending on supply and demand.

Solar goes all the way up => power is commodity.

Some hyperscaler goes bankrupt => hardware is commodity.

Models get real good => output is a commodity, no profitable problems to solve anymore.

Open source models get good => models are commodity.