apinstein

Same here. I review plans w rendered diagrams. Data structures, flowcharts, uml sequences, and component architecture docs.

I have found that making the AI look the plantuml and the rendering and reviewing before presenting it to me results in much more legible designs. To me the peak of this would be a shared interactive whiteboard w the ai during design.

This is very needed in the AI coding age! I find diagramming is one of the best ways for high bandwidth alignment between my mental model and the agent’s. I have been working on this problem a bit as I see good visuals as a key bottleneck in faster development while maintaining a real architecture.

Will def be adding this to my list of diagramming tools the agent can use!

Very interesting. I work in Parkinson’s space so I am familiar with the problem!

Does this also work for GRAS so things like supplements or other non-drug interventions can be tried in the new model?

Actually I think they do. Visualizations are a form of compression and focus.

All of my ai-driven plans use a tool I built to rasterize all text based visualizations. And I make the model present the rendered version to a clean room agent for brief-back. They go in circles until the diagram is good. Then, I instruct planning tools to always look at both the text and rendered version of all diagrams. I have found it to be surprisingly powerful.

Very cool! Working on a product for in-care use as well, complementary to this. Would love to talk shop!

It’s gotten so good that I now have infrastructure to render all mermaid/plantuml in my project to png and have AI’s always load both text and image versions. And they are instructed to review the rendering as part of the diagramming cycle (for layout, salience, usefulness, etc). They can now produce useful diagrams that help reach shared architecture understanding.

> The shared language of a software project is not English or Python but it is the common understanding of what its concepts mean, where the boundaries are, which invariants matter, who owns what, and why the system has the shape it does. This language is rarely written down in one place. It lives partly in documentation and code, but also in code review, conversations, arguments, and the experience of having to explain a change to somebody else.

This is so true. I am a big fan of Christopher Alexander’s “Pattern Language” concept, which addresses this exact problem! In fact he recommends developing your own pattern languages for your own domains (which of course led to the famous GoF Design Patterns book).

I have been experimenting with a “Pattern Language” skill which instructs the AI to maintain 3 pattern languages for every project. One in the business domain, one in the product domain, and one in the technical domain. It is working really well. It is always super cool to see it reference the pattern languages during planning and curate them during implementation and review.

I credit using it with keeping my 100% ai-coded projects well organized, aligned across domains, and easy to work on.

Exploring highly interactive instrument (piano) practice to see if AI can help students practice better. Full duplex voice agent alongside your practice session. Also exploring live AI jamming partner to practice playing with others.

Furniture isn't part of the property by default; only if included in the sale. So pics with furniture aren't a problem, unless you say it's included and you don't get what's pictured.

Codex.app is gone and merged into ChatGPT.app. The upgrade process was... messy... Codex's self-update just deleted the Codex.app w/o further instruction. And ChatGPT updater failed the first time while also bricking the prior installed ChatGPT.app.

Seems good/fine once you get through upgrading the app.

I mean it’s already fraud to do so today… you cannot misrepresent the condition of a property. I think the harm so far has just been wasted time and thus no standing for lawsuits yet.

It’s pretty much always been against the rules of the mls to use altered photos. Pre ai, people would sometimes get busted for making grass where there was none, or making walls with cracks a solid color. It’s not allowed to alter condition of property.

Staging and virtual staging (including sky replacement and removal of trash cans) are allowed so long as they don’t alter the true nature of the salable property.

I am surprised that AI hasn’t been policed more. Probably they just don’t have the ops for it.

You mentioned it at the end of your article that you should definitely think more about horizontal transfer. It basically lets any individual in a population install a runtime genetic package that can be shared between individuals. It can work extremely fast.

In the lab, we would combine in a gene of interest with an antibiotic resistance gene in a single plasmid and introduce it into a bacterial community. Within 48 hours the only individuals left alive will have the plasmid with the gene of interest.

I am playing around with building my own similar and am faced with the question you pose.

How can you tell if your prompt process works? I feel like the outputs from SDLC process are so much more high level than could be done with evals, but I am no eval expert.

How would you benchmark this?