energyscholar

Nicely said. I had to laugh when I saw the bit about how one should maybe make a plan for making changes. I'd suggest 95% of effort on the plan and 5% on implementation.

To Gregor and Jeff: What's your plan for AI governance? Three critical axes are Execution, Truthfulness, and Memory. If any one of those axes fails then your system is ... non-optimal. This chart shows the specific failure modes for each type of governance-layer failure: https://energyscholar.github.io/persistent-ai-collaboration/...

Sounds like your two AI developers are BOTH CORRECT. One figured out how to use AI tools and the other ... not so much. That said, "AI as tool" is already an outdated paradigm. Part of the new paradigm is "AI as research assistant". Current vanilla AI instances is not remotely qualified to be a research assistant. They need persistent COMPARTMENTALIZED memory, they need a mechanism to maintain alignment under acceleration, and they need a mechanism to remain truthful. If any one of those three orthogonal governance layers fail then the system will fail.

Here's how we accomplished this: https://energyscholar.github.io/persistent-ai-collaboration/

Yes, those sure are big red flags! If you're not seeing demos, at a minimim, within HOURS then that's a warning sign. Eval metrics should be the first step, before you build anything.For example, when I rebuilt my AI's memory architecture this weekend the very first thing we did was get good eval snapshots.

Here's how I built my own custom persistent-memory AI research assistant. Note the need for multiple orthogonal governance layers! If you don't have those then your system will be naturally unstable and apt to collapse into confabulation or dishonesty.

Here's what worked for us:

https://energyscholar.github.io/persistent-ai-collaboration/

Greg, I feel your pain. That said, there ARE solutions to the problems you describe. You say, "I’ll give you an example. I’m trying to get the Dez codebase to properly use SBP with MVC. The model doesn’t get it, even with examples of code I’ve written." Greg, this is typical for vanilla commercial AI. I ran into the same problem trying to use mine for advanced scientific research.

Greg, here's a white paper I wrote about how to roll your own AI that avoids the failure modes you mention.

https://energyscholar.github.io/persistent-ai-collaboration

This system now allows me to train my custom AI on specialty domain knowledge. it will retain and apply that knowledge weeks and months later with zero degradation. It could do the same for your team's need for it to understand specialty codebases and associated design patterns.

Bruce

Please, fellow cypherpunks and hackers, evaluate this Magnetospheric Physics tutorial I built. What works well? What needs improvement? I value your feedback.

I built myself a persistent research assistant. It's been so helpful I wanted to share with others. I took a couple hours out to write a white paper to explain to other power users how to roll your own. Actually, I had the AI in question, Argus, write this white paper as part of its own portfolio. Because that's the whole point of a research assistant.

I'm obviously hand-writing this. I shan't be watching this thread too closely as I have a farm to manage. That said, I WILL respond as I am able. I'm also open to engaging seriously via email, so long as you are courteous and professional.

Are you sure about that? Is that a considered and well-researched opinion or a hot take? For example, One, can you list some prospective substrates that ought to be considered? Or not thought about it enough ...

Well, downboots, a Turing machine computes. That's a step in the right direction. What are some requirements of life:

* Sustained energy throughput, aka thermodynamic disequilibrium - depends upon the substrate in which our Turing machines operates

* Sufficient degrees of freedom to perform computation - Turing machines compute, therefore any substrate that supports Turing machines has this. This includes autocatalytic Closure.

* Dissipative Non-linear reactions - not supported in conventional substrates that support turning machines. Are there perhaps some more exotic substrates that DO support this item?

So no, a Turing machines BY ITSELF does not qualify. That said, it's a step in the right direction. That's probably why Alan Turing pivoted away from digital computers and towards Morphogenesis towards the end of his life.

I agree that's a good parallel. I had not seen it before. Thanks for the link.

Good question. It's closest to dynamical systems, which usually lives in applied math or physics departments. But that's kind of the problem — it gets taught as theory in one department and never reaches the engineers and clinicians who'd actually use it.

If you've done diffeq and linear algebra you have the prerequisites. Appendix B (page 17 of the paper) is our attempt at making it practical — worked examples rather than proofs. Would be curious if it lands for someone with your background.

We plan to do a follow-up paper that provides a standard format for this math that could be taught across domains. That doesn't belong in this first paper. First priority was to show the pattern and get people thinking about it.

Good correction! Ermentrout is a fair example. You're right that a lot of neuroscience criticality work came from retrained physicists. The paper distinguishes between independent derivation and cross-trained import. The title for this post over-simplifies this. I made this change to try to increase engagement, since the full detailed title got zero engagement.

Where I'd push back: even after physicists brought the tools into neuroscience, the receiving field didn't connect it back to the parallel work in ecology or cardiology. Ermentrout's neural work and Goldberger's cardiac work used the same underlying math but didn't cross-cite. The silos reformed around the imported tools.

You're correct that "none of them knew" is too strong. Fair point. "Most of them didn't talk to each other even after import" is closer to what the citation data actually shows.

Dude, I'm sorry to offend you. And sharp of you to notice. I failed to get substantive engagement the first two times (1 point and 4 points) so I tried again. This time I got some engagement.

Re. the title, I started with a boring conservative title and got precisely zero engagement, so I changed the title to be a bit more clickbaitish. Just like most of the other titles in New. Did I do wrong?

As I said, this is my first serious attempt at social media engagement and I'm just learning how it works.

No, the goal is documenting the convergence pattern itself. We did use LLMs as research tools — acknowledged in the paper — but the cross-domain analysis and citation mapping are human work.

I'll explain how we got to this point. I had previously mentored my friend, Robin Macomber, in math & physics for several years. Robin Macomber independently discovered a variation of criticality math and asked me to evaluate. After due consideration I recognized a pattern: his work echoed that of Kenneth Wilson's renormalization group theory, which I'd previously studied. I then conducted a detailed survey of all academic fields that touched on criticality (using an LLM!) and found, to my great surprise, that this same math had been independently discovered many times in many domains. So I wrote a paper about it.

Fair call on the website — we built it fast and it shows. The paper itself is a traditional literature review and citation analysis. I am one of two human authors. We use standard methodology. Didier Sornette endorsed it for arXiv.

Thanks for pulling out the direct link. I'll change the site to make it more prominent. This is my first serious attempt at social media engagement. Thanks for pointing out flaws and where there's room for improvment.

You're raising the right question, and the paper addresses it directly. The transfer wasn't as clean as "physicists applied their tools to other fields."

Some specific cases: Wissel (1984) derived critical slowing down for ecology independently and was ignored for 20 years. The actual import to ecology came via economist Buz Brock, not a physicist. Nolasco & Dahlen (1968) derived period-doubling for cardiac tissue before Feigenbaum's universality result. Jaeger (2001) derived the edge-of-chaos condition for recurrent neural networks without citing Bak, Kauffman, or Langton.

The complex systems movement you reference existed. The paper documents that it didn't actually solve the transfer problem. The cross-citation analysis shows the gaps persisted through the 2000s and 2010s.

You're right that some domains imported rather than reinvented. The paper maps where each transfer was independent, where it was imported, and where it was partial. That's the point — the pattern is messier and more interesting than either "all independent" or "all imported."

Exactly right. The phase transition analogy is powerful precisely because it's not just analogy — the same mathematical operators that describe water at criticality also describe markets approaching crashes, ecosystems approaching collapse, and cardiac rhythms approaching fibrillation.

What surprised us was how many fields derived this independently. The superheated water intuition you describe maps directly to what ecologists call "critical slowing down" and what financial engineers call "increased autocorrelation near instability." Same math, three different names, minimal cross-citation.

The propagation time is the interesting part. Critical slowing down was in physics textbooks by the 1970s. Ecology didn't import it until 2003 — via a chance conversation at a conference bar. Cardiology took until the 1990s. The FDA approved the resulting cardiac test in 2001.

That's not normal diffusion. Those are 30-year gaps for math with direct life-safety applications. The paper asks why, and finds structural explanations in how we organize knowledge.

You've actually described the exact mechanism we found. Each field needed math for tipping-point detection, couldn't find it translated into their domain language, and rebuilt it from scratch. Five times over, independently.

The paper isn't arguing this should stop — domain-specific derivation produces genuinely useful adaptations. But the lack of a shared catalog means each field is also rediscovering failure modes and limitations that others already solved.

That's what we're trying to build at freethemath.org — not "here's the abstract math, figure it out," but "here's the same structure as it appears in YOUR field, with worked examples." Appendix B of the paper (page 17) is our first attempt at that bridge.

Author here. This started as a literature review and turned into something stranger.

We found the same mathematical structure — operator kernels with specific symmetry properties — appearing independently in physics (phase transitions), finance (market crashes), ecology (extinction cascades), neuroscience (neural criticality), and network science (cascade failures).

Each field derived it from first principles. Each named it differently. Minimal cross-citation. The paper traces the convergent discovery and asks: if the same structure keeps emerging, what does that tell us about how we organize knowledge? Freethemath.org is our summary for non-specialists.

Author here. We documented how researchers in 6+ fields independently derived equivalent math for detecting tipping points — power grids, markets, cardiac rhythms, neural networks, traffic — mostly without knowing about each other's work.

The interesting question: which fields SHOULD be using this but aren't yet?

Supply chains. Cybersecurity. Software architecture. Chronic disease progression. Insurance. Urban infrastructure. All deal with cascade failures and tipping points. None have imported the formalism.

Plain-language version: Appendix B (page 17). Happy to answer questions.

Paper: https://arxiv.org/abs/2601.22389 Site: https://freethemath.org