mickdarling

Joined 16 years ago

Karma
290
Submissions
150
Member since
Sep 12
Builder, and Founder

Dollhouse Research — composable AI tools, mostly open source (dollhouseresearch.com):

- DollhouseMCP: Open-source AI customization with AI safety as at it's core. Turn prompts into modular building blocks you can create, activate, combine, version, and share — Personas, Skills, Templates, Agents, Memories, and Ensembles. (dollhousemcp.com)

- Dollhouse Collection: community catalog of those elements (collection.dollhousemcp.com)

- MCP-AQL: a protocol spec that gives MCP tool calls semantic meaning — Create/Read/ Update/Delete/Execute endpoints that cut token overhead and make safe-vs-destructive operations explicit at the protocol layer (mcpaql.com)

- AILIS: an OSI-inspired, layered model that gives AI systems a shared vocabulary, so teams can tell a routing problem from a tool-invocation, memory, or UX one

- Also check out Merview.com, a local-first Markdown and Mermaid editor and viewer that runs entirely in your browser, no login

Elemental Surveys (elementalsurveys.com):

- Fast-turn market research — turn a brief into a QA'd questionnaire, analysis, charts, and a branded report in hours instead of weeks

Some Previous Projects:

- Created Tomorrowish.com a social media DVR used by Hulu, Fox, Turner Broadcasting, and more

- Cofounder and CEO of TVDuffle a Travel and booking app for concert goers and sports fans.

- Cofounder Biostrut 3D Printed organic tissue scaffold

ping me at my [email protected]

My personal blog can also be found at http://mickdarling.com

View on Hacker News

Recent submissions

Comment · 3 days ago
My iPad Pro has a plenty big screen, a touch screen, and a processor that's faster than my M1 Air...by a lot. I would be ecstatic if they would put MacOS on the iPad. Instead, they put the damn screen for the iPad on the MacBook.
Comment · 10 days ago
In theory, theory and practice should be the same; in practice, they are not.
Comment · 2 months ago
Literally the first thing I thought of. Is he trying to reference an Antichrist?
Comment · 2 months ago
I created MCP AQL, which is an extension to the MCP spec, specifically to reduce the bloat for MCP tools.

It only has five CRUDE endpoint: Create, Read, Update, Delete, and Execute using a GraphQL-like structure for tool calling of the operations within the endpoints. It's very efficient, and robust. there's all kinds of exemplar tools and components to make adapters for any MCP server. You don't even need to rewrite your own MCP server. Just create an adapter for it.

All open source at MCPAQL.com

Comment · 2 months ago
If it stores unique information, by definition it can store arbitrary information because it can point to arbitrary information. So they can have it relate to anything they want. Even a full breakdown of the original text if they choose.
Comment · 2 months ago
Watermarks are context poisoning.
Comment · 4 months ago
If only the AI tools didn't shut you down every time you were trying to red team your own tools. I've had to come up with all kinds of workaround scenarios, effectively bypassing the AI security processes in order to stress test my own systems.
Comment · 4 months ago
No, this is their get out of jail free card if people start complaining about the model being dumb or forgetful or lying, they can just say, oh well, you must have been doing something that triggered its distillation prevention technique.

And, they can say that for anybody at any time, and you'll never know why, and there's no way to prove it.

Everyone needs a flight data recorder to prove... "here's what I was actually doing and why it was not distillation." And now you're having to prove your innocence instead of them having to prove you're guilty, and really at the end of the day, it's just the model being stupid that they're protecting themselves from.

Comment · 4 months ago
The tags are actually displayed in raw text not rendered.
Comment · 4 months ago
Comment · 5 months ago
I effectively distill the frontier models by building whole sets of skills, personas, and other artifacts that I can then run on smaller models and get 10% even 20% improvements on models like haiku or local models.

There's a lot of room for improving the smaller models at many levels of the stack.

Comment · 6 months ago
I used it today to take a look at my previously built design system with Logos, branding, fonts, and everything else. After a lot of annoying tweaking back and forth, finally, I got something that was satisfactory.

Then I looked at the usage and it said I had used 95% of my Claude design usage for the week!

This isn't a real tool. This is a plaything, if that's what they're providing as examples.

Comment · 7 months ago
I'm working on a tool to determine which portions of an LLM process can be optimized, and how to measure that optimization and check whether it's optimizable at all. The shaping pattern that they talk about here is directly relevant and makes a whole lot more processes potentially optimizable by looking at the pattern rather than if the metrics just go up or down.
Comment · 7 months ago
Hey, LLM, take a look at these multiple hundred emails and docs in my docs folder from the last few years, before I started using AI, that I wrote personally. create a list of all of the idiosyncrasies that I have in my writing. Create a file to remember that. And then use that to write any new text that'll be published so it sounds like my authentic voice. Thank you.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton