Viewing profile — mickdarling

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 t…

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 somet…

The tags are actually displayed in raw text not rendered.

Below is the EXACT text in Claude Desktop introducing Fable 5, including the very professional looking break tags, and at least I know where the links begin and end by looking at t…

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…

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 go…

Hi, I'm Mick. I've been building this for the last 9 months DollhouseMCP 2.0 is an open-source MCP server for making and using composable building blocks for AI customization. You …

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 pa…

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 …

Maybe for you reading a paper deeply is the most constructive way that you have to absorb information. For me, it is having a document and interrogating it. Maybe having many sets …

Might be worth something to create an AI summary of the actual documents that are behind the curtain. That way the Client can have some assurance of what the deliverables are. It's…

I don't use Claw. It is way too dangerous. I built my own system where I know the ins and outs and how they can break. When it comes to agents' tasks, I tend to focus on things tha…

You could literally drop this into Claude Code or Codex and point it at a local fork of Zulip and have it build your bimodal version with triage and grazing styles.

I use an LLM behavior test to see if the semantic responses from LLMs using my MCP server match what I expect them to. This is beyond the regex tests, but to see if there's a seman…

It looks like it does have an MCP Gateway https://github.com/github/gh-aw-mcpg so I may see how well it works with my MCP server. One of the components mine makes are agent element…

This is where the desire to NOT anthropomorphize LLMs actually gets in the way. We have mechanisms for ensuring output from humans, and those are nothing like ensuring the output f…

I'm looking at it right now as a tool I can hollow out and stuff in my own MCP server that also has personas, skills, an agentic loop, memory, all those pieces. I may even go simpl…

Thank you for the note. It's not a site I used all that often. Whether you had anything to do with it or not, I have no idea. And, since you didn't follow best practices and tell m…

Wasn't my project to manage. That was a consulting gig. And I fired the client right after this.

Had humans not been doing this already, I would have walked into Samsung with the demo application that was working an hour before my meeting, rather than the android app that coul…

I think Claude Cowork should come with a requirement or a very heavily structured wizard process to ensure the machine has something like a Time Machine backup or other backups tha…

This looks cool! And, to add to the list of shameless plugs for OSS markdown editors/renderers With mermaid support, I will add mine to the list: https://merview.com with full sour…

It certainly doesn't seem to have a trouble creating MIT licenses, that's for sure. I've had it insert an MIT license against my express direction instead of the AGPL license.

Claude code refuses to generate AGPL 3.0 licenses or modify them. I've run into this with several projects.