Matthew J. Maughan, PharmD, MHCDS, CPEL

4.5K posts

Matthew J. Maughan, PharmD, MHCDS, CPEL banner
Matthew J. Maughan, PharmD, MHCDS, CPEL

Matthew J. Maughan, PharmD, MHCDS, CPEL

@MatthewMaughan

Building Charter — open-source AI governance layer. PharmD. MHCDS. CPEL.

New Hampshire, USA Katılım Ocak 2011
226 Takip Edilen731 Takipçiler
Sabitlenmiş Tweet
Matthew J. Maughan, PharmD, MHCDS, CPEL
Every AI agent writing code in your project right now has zero rules. No audit trail. No compliance. No kill switch. Today I'm open-sourcing Charter — the governance layer for AI. Install the VS Code extension. Open a folder. Your AI is governed in 3 seconds. Free. Apache 2.0. Forever. github.com/germpharm/char…
English
3
2
7
1K
AleXandra Merz 🇺🇲
AleXandra Merz 🇺🇲@TeslaBoomerMama·
Soooo, I think I have figured out some more breadcrumbs, but am a bit scared to share publicly. What should I do?
English
112
11
301
33.5K
Farzad 🇺🇸 🇮🇷
How chips are made: Fire a laser at tin droplets in a vacuum, creating plasma hotter than the sun, bouncing that light off mirrors that are the smoothest objects ever made by humans, to print patterns that are smaller than a virus, on a thin slice of purified sand. lol.
English
236
230
5.1K
124.3K
Farzad 🇺🇸 🇮🇷
I would like to personally thank Elon Musk and Tesla for sending me on my next rabbit hole for the next 2 weeks: EUV lithography.
English
80
55
2K
83K
Zack Golden
Zack Golden@CSI_Starbase·
Hey Starship Addicts, Part 2 is going to be delayed by about a week. The episode is completely finished and ready to release… but YouTube ad revenue has taken a major hit recently as advertiser focus shifts heavily toward global conflict coverage. Originally I planned to release this episode without a sponsor because they weren’t able to keep up with the pace we were moving. Unfortunately that’s no longer realistic given the level of time investment involved from multiple people behind the scenes. Despite viewership performing almost exactly the same as the previous episode, ad revenue has dropped by nearly 60%. A year ago I probably wouldn’t have said anything about this. But it’s becoming increasingly clear that YouTube’s ecosystem is rapidly shifting toward high-volume AI-generated content. If that trend continues, genuinely human-made content will become harder and harder to sustain. Many of your favorite creators — especially those producing deeply researched, time-intensive work — may simply disappear because the economics stop making sense. And I’m pretty sure I’m speaking for a majority of the Team Space community when I say that. For now, we’re going to keep doing what we do for as long as we possibly can. Because as long as there are people who still care about real research, real engineering, and real storytelling… this channel will keep pushing forward. Thanks for sticking with us.
English
70
61
1.4K
30.1K
Hans C Nelson 🗽
Hans C Nelson 🗽@HansCNelson·
@EXM7777 Been working on the same thing. I’ll have to go check out his solution an compare notes.
English
1
0
0
284
Machina
Machina@EXM7777·
be Andy >become an OpenClaw power-user >realizes it forgets things and burn tokens very fast >figures out the memory system actually sucks >build his own local, stateful memory skill >make it free, available for everyone on Clawhub gg
andy nguyen@kevinnguyendn

Memory Skill for OpenClaw with 26k+ users in 1 week🚀 OpenClaw's memory system is broken by default. It requires curating massive MEMORY.md files or relying on duplicate-heavy generation. Hours are wasted tuning, and massive amounts of tokens are burned. It's time to stop. So we built the memory skill to solve that prob Here is our superpower ⚔️ 🎯 Top #1 market accuracy (92.19%) after 8+ months of intense architecture iteration 🧠 The ultimate solution to keep the timeline, facts, and meaning perfectly in place ☁️ Local & Cloud + Version control ⚡ Super easy setup

English
46
71
2K
340.4K
Matthew J. Maughan, PharmD, MHCDS, CPEL
I made the jump to OpenClaw. One way to look at it is that I’ve been too nervous to dive in. Another way to look at it is that I’ve been trying to get confident enough in the tool(s) to move forward with a correct expectation of the outcome.
English
0
0
0
25
Zack Golden
Zack Golden@CSI_Starbase·
This will probably be the most re-watched skit on my entire channel. Fly on the on wall type shit going on here
English
2
1
120
5K
malinvestment.jpeg
malinvestment.jpeg@malinvested·
Of course that's your contention. You're a first-time SaaS bear. You just got finished listening to some podcast, Dario on Dwarkesh, probably. Now you think it’s the end of white collar work and seat-based pricing is screwed. You're gonna be convinced of that til tomorrow when you get to “Something Big is Happening”. Then you’ll install ClawdBot on a Mac Mini, vibe code a dashboard on top of a postgres database and say we’re all just a couple ralph loops away from building a Salesforce competitor. That’s gonna last until next week when you discover context graphs, and then you're gonna be talking about how the systems of record will be disintermediated by an agentic layer and reposting OAI marketing graphics. “Well, as a matter of fact, I won't, because ultimately the application layer is just ….” The application layer is just business logic on top a CRUD database. You got that from Satya’s appearance on the BG2 pod, December 2024, right? Yeah, I saw that too. Were you gonna plagiarize the whole thing for us? Do you have any thoughts of your own on this matter? Or...is that your thing? You get into the replies of anyone posting a SaaS ticker. You watch some podcast and then pawn it off as your own idea just to impress some VCs and embarrass some anon who’s long SaaS? See the sad thing about a guy like you is in a couple years you're gonna start doing some thinking on your own and you're gonna come up with the fact that there are two certainties in life. One: don't do that. And two: you dropped thirty grand on Mac Minis and LLM API calls to come to the same conclusion you could’ve got for free by following a handful of VC accounts.
malinvestment.jpeg tweet media
English
361
1.1K
11.8K
1.8M
Hans C Nelson 🗽
Hans C Nelson 🗽@HansCNelson·
@MatthewMaughan @malinvested That last question is exactly what I’m focused on as well. It certainly involves ontological harnessing and robust security & auditability, but that’s just part of the answer. Sounds like we may need to have some more in depth discussion.
English
1
0
0
18
Pejjy
Pejjy@CuriousPejjy·
I can't believe I'm seeing missiles and drones fly across the sky's while driving. It's so surreal.
English
26
9
374
11.3K
Matthew J. Maughan, PharmD, MHCDS, CPEL
Excellent point. We started with MCP because it was the fastest way to to get a proof of concept out into the world for people to interact with. The feedback from people has kept our development running on rocket fuel. You’ve challenged me. I’ll let you know when the Rest API is ready.
English
1
0
1
22
Hans C Nelson 🗽
Hans C Nelson 🗽@HansCNelson·
Excellent instincts. Overall it looks like a bottoms-up competitor to Palantir (who is a top-down market entrant) to me, as I alluded to above. This means you’re going to need to think strategically about how you’re going to navigate a global marketplace where they already exist. Doesn’t mean you can’t thrive. Just need to make sure you don’t stray directly in front them. They won’t be able to stop if you do, and you’ll get creamed.
English
1
0
0
21
Hans C Nelson 🗽
Hans C Nelson 🗽@HansCNelson·
This section is also good. But remember, robust capabilities are about the combination of rigid structure with adaptability/flexibility. The escalation layer hints at the need to differentiate one approach vs. the other, but there’s room to clarify your architecture & communication here.
Hans C Nelson 🗽 tweet media
English
2
0
0
26