what are you using for memory with your local models? is there a specific harness you would recommend for local agents?

I’m using Hermes at the moment - it comes with lots of tools already baked in for the agent to use - for example web and browser access just worked, rather than having to mess around loads with config scripts and plugins.

I’ve also tried OpenCode (similar but a bit less so) and Pi (fast but you have to add lots of features yourself which is a bit of a pain). Claude Code can also be pointed at a local model and works, but the default system prompt is huge. (~140k of text when I extracted mine, IIRC.)

I use HugstonOne (that backend a personalized version of llama.cpp). Implemented it´s own double layer memory that recall the full or partial previous session/file with an ON/OFF switch (which picks up where left off in CLI or Server or both same time) and another that reads back a % of current tab if memory switch is off doing checkpoints every certain tokens, summarizing and referring back to it when needed (recalled by certain logics). There is more to it when involving local RAG (making it tripple memory layer) but thats a long story.

About the harness depends on for what you need it, but basically for a universal unit of measure, Harness is multilayered and logic and domain specific dependent. I would definitely include Type of Hardware, Model parameters/knowledge, Model Intelligence, Model size/context, type of conversion, type and quantization (models comes with some default tools), but adding your (domain specific), skills, tools, memory, logs, security, Rag, Online search... (which as scary as they sound are mostly simple logics in a txt file, like if this do that).

The full pack is Harness 10, every missing thing lower the harness score.

To answer to your question I would definitely recommend smth like HugstonOne (or anyway llama.cpp CLI) with Qwen 3.6 35B finetuned/distill (deepseek 4 or claude 4.7) with none of the current coding agents out there that are screaming internet connection and proprietary API and data collection. DO this, if you can find a tool that you can download and choose a local model (of your choice in whatever folder locally) and load it ready for inference without any need of internet connection that is the tool you should aim for. Right now there is none out there.

there has been a lot of pushback about building new data centers basically anywhere on earth might as well build them in space.

why are those ai chemistry books any different than the anarchist cookbook which can also be bought on Amazon? actually now that I think about it a faulty chemistry book might be less dangerous than a book that teachers readers how to make explosives.

There's a difference between something that properly advertised itself as dangerous, and something that advertises itself as a professional authority.

an organisms behavior outside of reproduction certainly can have an impact on natural selection. the vast majority of ants cannot reproduce by your logic their behavior shouldn't have any impact on natural selection. if a non-reproducing members behavior impacts those who can reproduce it will have an impact on natural selection.

I never said an organisms behavior outside of reproduction does not have an impact on natural selection.

I don't think most people would want dozens of task specific robots in their house it would be far more economic to have a single general purpose robot that can use pre existing tools and methods.

Right, I am saying that the fundamental design of household objects need to change to allow much simpler maintenance without humanoid robots.

I think its easier to build a dish washer that can stack plates from first principles than humanoid robots. The cultural shift is the harder part.

how can you prove that a human is appreciating and enjoying music instead of just generating sentences that imply they do?

They put in effort and resources to experience music and don't just say they enjoy it, and they generate noises and movements that signal happy feelings.

LLM doesn't have any signals for what they feel, nor do they have an agenda they work towards, so you don't have the same proof there.

or because they're trying to attract talent?

agent teams can help with that, the main agent acts as an orchestrator and spawns sub agents to do the actual tasks it generally keeps the main context from overflowing.

I thought we wanted robots to take over the boring and back breaking jobs?

Well, of course. Of note, this region in question has a problem with a dearth of young people and specially young people wanting to take those jobs, and if it voted right-wing and populist, you don't need me to tell you what kind of solutions they don't like to their demographic issue.

it looks like they have been used at least once to help develop a vaccine. they're not as significant as writing but they do seem to have their uses.

https://theconversation.com/a-man-used-ai-to-help-make-a-can...