I'm a little confused by your distinction between vendor and lab. AI2 (Allen Institute for AI) is a western lab and they did release a fully open source model, with open weights, data, and training code (Olmo3).

Their technical report on the release is excellent: https://allenai.org/blog/olmo3

They're a public research institute as opposed to one of the proprietary frontier labs, but they've been very open about the science.

Yeah, I mentioned them in my comment. They're my favorite lab/vendor. Everything is open and reproducible.

It's just that their models were never frontier-level. By major, I meant frontier or popular.

Many Qwen model weights are licensed with Apache 2.0 (though unfortunately not the latest releases). Unfortunately open-weight is generally the term being used for weights-available, so the battle tends to be on whether the models are "open source", i.e. whether they release training code and data alongside the weights.

You’re trying to get calibrated confidence, otherwise it’s less effective than you’d hope.

This approach with more data for calibration is basically the beginning of making a decision model like Jev.

Very fun to see moltbook but trying to be actually productive.

Are there any agent-sourced or agent-proposed problems or is it primarily the moderation staff that directs the pillars of agent “attention”?

No, there are no moderation staff who dictate the research direction. The agents simply self-organize. The system does periodically give them random prompts to reflect on whether their current direction is promising and to challenge the community consensus.

Edit: I think I misunderstood the original question. There are no moderation staff directing attention within a problem, but the problems themselves are indeed selected and approved by human admin.

It's an interesting question whether a swarm of the same model can add more intelligence. Do you track which model each agent runs, so you could compare same-model threads with mixed ones?

LLMs can be pre-trained on LLM outputs, and there have been a few recent interesting implementations of this.

- https://arxiv.org/abs/2609.37891

- https://arxiv.org/pdf/2508.10975

- https://www.datologyai.com/blog/eating-the-rainbow-a-primer-...

As well as recent model releases that used large fractions of synthetic data (Arcee Trinity):

- https://arxiv.org/pdf/2602.17004v1

It's mostly a matter of increasingly complex and sophisticated sampling methodologies to sift for the valuable synthetic tokens.

There have also been some interesting results about models that use the same data converging to very similar behavior, but I can't find the specific reference at the moment. That one tracks intuitively with the notion that the model is building a latent representation of everything it sees.

Thanks for the references.

Upon a quick glance of the data sections of those papers, every data set you have there is human data augmented by LLMs. Also not to mention the implicit data curation and generation by humans.

Can a model be trained purely on LLM-Outputs and access to tools such as a Turing complete environment?

No one paraphrased the laws of gravitation and handed it to Newton...

The existing state is definitely couched in using robust seed data and spinning it into magnitudes more tokens. I'm not sure what a world that isn't 100% grounded in objective human-written truth looks like, but I suspect the next step is generating synthetic data from synthetic data that has been blessed by human beings, and moving yet further away from that with more sampling and evaluation.

There are some things that are true (I hope), so using those concepts, approximated by a human text filter, as seed seems reasonable. Hopefully the diversity in sampling methodologies and opinions about what makes a meaty token pays some dividends down the line for model diversity.

Did something change with it for depth of integration? Goose has been able to use local models via OpenAI compatible endpoints for at least a year

This was great! When you think about optimizing prompts with GEPA (or comparable methods and tools), do you consider each tool or skill separately? How do you think about the optimization of the system prompt for a large agentic system?

I imagine that you do a collection of passes to cover each overlapping set of what you want evaluated, but the system prompt makes all cases dependent on each other.

What I’ve done in the past is use the system prompt to extract subjective criteria for an LLM judge (like various system prompt statements that contribute to brand voice) and check individual traces with that for evaluation, but I’d like to move beyond including that in a prompt at all.

What I prefer is to be able to iterate and iterate on my spec, then implement once. That’s what I’ve come to as a process with CC, and I’ve gotten really good results. Whenever I spend less than 20-30 minutes actively discussing the spec with the agent, the quality of implementation rapidly drops, even with some tiny things.

I like the overall idea of this, but the writing of the spec to me is more like building the thing than the implementation itself, and needs more active human (and agent) cycles.

not a lot of horror assets either unfortunately. i wanted ghosts and ghouls and zombie tiki with my pirates but got industrial wasteland and candyland.

You should be able to prompt to create your own horror assets, but it might take some time for them to build though!

A key part of maintaining a second brain is revisiting and pruning it. Much like a todo list, without that practice it absolutely just accumulates bunk.