Erik Samsoe

MPG Ranch
- Engineer, Generalist

Organismic Creative Partners
- Umbrella Chief

[CyrilXBT @cyrilXBT]

IF YOU HAVE BEEN HOLDING OFF ON HERMES AGENT BECAUSE OF API COSTS, READ THIS FIRST.

Four real ways to run it for free.

Local, through Ollama, complete privacy and no rate limits.
Cloud, through free tiers from Groq, OpenRouter, or NVIDIA NIM, no card required.

A subscription you already have, GitHub Copilot connects natively.

A fallback configuration so a rate limit on one provider does not stop your whole session.

Hermes Agent is free and open source. Now there is no excuse on the model side either.

Bookmark this. Follow @cyrilXBT

[Aakash Gupta @aakashgupta]

Let me explain why an AI art company just built a full-body medical scanner, because almost everyone is reading this as a random pivot.

Ultrasonic CT works by firing sound through your body and recording the ripples that scatter back. Half a million emitters the size of a grain of sand, surrounding you in water, each one listening. What comes back is noise. Reconstructing a clean 3D image of muscle and tissue from that scattered acoustic mess is an inverse problem, and it is brutally hard. The hardware is the easy part. Butterfly Network already makes the chips. The reconstruction is where every previous attempt stalled.

That reconstruction is the exact problem Midjourney spent years getting good at. Turning ambiguous input into a coherent image is what they do. They aimed it at sound waves instead of text prompts.

This is why the scan takes 60 seconds while a full-body MRI takes 60 to 90 minutes. Close to 100x faster, no radiation, no magnets, resolution down to a fraction of a millimeter.

Then read the part most people skipped. The scans happen at a spa. Hot tubs, cold plunges, and a machine that quietly images your whole body while you relax. The scan is a side effect. You barely notice it.

Run it forward. The plan is 50,000 machines doing a billion scans every month. Midjourney has no investors and no quarterly hardware margin to chase. The payoff was never the scan fee.

A billion monthly full-body scans is the largest longitudinal map of human anatomy ever assembled. Every model trained on it gets sharper, and every sharper model makes the next scan worth more. This was always an image company. They just found a kind of image nobody else could generate.

[Owen Lewis @is_OwenLewis]

I did not see this one coming. BREAKING NEWS folks!
Midjourney, yes the AI image company, just launched a real medical device that feels like it's straight out of Star Trek.
https://t.co/LSs2zbYViM

They’ve unveiled the Midjourney Scanner, the first working prototype of Full Body Ultrasonic Computational Tomography. It uses a ring of thousands of tiny transducers to fire ultra-precise sound waves through the body. The returning echoes are captured at a staggering 17 gigabytes per second, and the 806 terabytes of gathered data are then reconstructed by a 2 petaflop compute system into a highly detailed 3D map of your entire internal anatomy — organs, tissues, blood vessels, etc., in 60 seconds.

The resolution is extreme: each sensor can resolves motion smaller than the width of an atom, detecting internal tissue details down to half a millimeter. And unlike MRI or CT scans, it uses no radiation, just sound. Think of it like getting an ultrasound from the 22nd century.

The ambition is breathtaking. Midjourney wants to build a fleet of 50,000 of these scanners, capable of delivering a billion full body scans per month. That's enough to make comprehensive full body imaging available to every person on Earth.

They’re not hiding it in cold, clinical hospitals either. The vision includes placing these scanners inside what look like Midjourney spas, turning what’s usually an annoying medical procedure into something genuinely pleasant.

This is Star Trek level healthcare infrastructure: fast, safe, non-invasive full body imaging at planetary scale. If they pull it off, it could fundamentally shift medicine from reactive treatment to proactive, early detection on a global level.

Progress (and Midjourney going full medical) marches on. 🩺🚀

[Erik Samsoe @eriksamsoe]

@kevin2kelly Oh no! I'm bound to catch the accent

[Erik Samsoe @eriksamsoe]

What about large "natural" landscapes?

[Nix0n @UnTalNixon_exe]

🏙️ Gemelos digitales y agentes de IA: El futuro del diseño urbano en tiempo real

Simular el comportamiento de una ciudad entera antes de construirla ya no es ciencia ficción. La combinación de potencia de cómputo moderna, entornos de renderizado hiperrealistas y agentes autónomos permite clonar infraestructuras urbanas complejas a una escala masiva.

En este impresionante desarrollo, se generaron automáticamente varios kilómetros cuadrados alrededor de la icónica Estación de Tokio, poblando el entorno con miles de humanos y vehículos simulados para estudiar flujos de movimiento en tiempo real.

.

🔮 La ingeniería detrás de este entorno de simulación avanzada:

• Generación Procedimental Masiva: El sistema estructura distritos urbanos completos a partir de datos cartográficos digitales, renderizando la morfología de calles, plazas y rascacielos en cuestión de segundos.

• Agentes de IA para Flujos Humanos: En lugar de animaciones predecibles, miles de peatones y taxis virtuales toman decisiones autónomas, permitiendo analizar cuellos de botella y dinámicas de tráfico bajo entornos de estrés.

• Estructura Modular Dinámica: La interfaz permite hacer "hot-swapping" (intercambio en caliente) de los diseños arquitectónicos de los edificios y manipular instantáneamente las condiciones climáticas o los ciclos de día y noche.

• Infraestructura de NVIDIA: Todo el entorno corre bajo el marco de simulación y gemelos digitales de NVIDIA, utilizando la fuerza bruta de procesamiento gráfico en paralelo para llevar los límites de la física virtual al extremo.

.

Tener la capacidad de experimentar y predecir el impacto de los cambios de infraestructura en un entorno virtual antes de mover un solo ladrillo físico está transformando por completo las reglas de la planificación urbana moderna.

.

Guarda este post en tus marcadores si te apasiona la simulación en tiempo real, los entornos 3D o el desarrollo de agentes autónomos aplicados al mundo real 🔖

[Erik Samsoe @eriksamsoe]

A parallel to my system setup, the tutor insight part. With inspiration from Danny Hillis:
ARISTOTLE" (THE KNOWLEDGE WEB)
https://t.co/m4fy9oAKXm

@obsdmd, claudian, @karpathy

[Dwarkesh Patel @dwarkesh_sp]

Over the last 200 years, we've automated away a lot of hard physical labour. But people still go to the gym.

Indeed, many people today are more physically capable than people in the past. We can train systematically for whatever physical goal we want, and it's more fun than hard labour on a pre-modern farm.

@karpathy's hope is that, in the future, the same will be true of learning.

AI tutoring that's tailored to each person will make learning easy, and more people will want to do it. We will be able to go much further than our ancestors.

[Angelica Parente @draparente]

Earlier this year I was getting frustrated with Claude's charts, fed this book to claude and had it generate a Tufte skill. Instantly got simpler/more beautiful visualizations.

https://t.co/lfXwyQfmQG

[Captain Insight @CaptainInsightX]

Andrej Karpathy just joined Anthropic.

His new boss is the man who realised AI could train itself.

You've probably never heard of him.

Meet Nick Joseph 🇺🇸

> Harvard grad. No PhD. No fame.
> First job: ranking charities at a nonprofit called GiveWell.
> That's where he first heard the words "AI safety."
> He laughed it off. Models weren't even dangerous yet.
> Joined Vicarious ~ a startup trying to build AGI through robots.
> Then OpenAI. Quietly. On the safety team.
> Worked on something nobody was paying attention to: teaching GPT-3 to write code.
> Then he watched it work.
> A model. Writing the same code that trained it.
> That was the moment. The future cracked open in front of him.
> December 2020: he walked out of OpenAI with 10 others.
> Built Anthropic from zero with Dario and Daniela Amodei. 🚀
> Today he runs the team that trains every version of Claude.
> 40+ engineers. 27,000+ academic citations.
> Two podcasts ever: one on AI safety (80,000 Hours, 2024), one on scaling laws (YC, 2025). Zero about himself.

May 19, 2026: Andrej Karpathy joins Anthropic.

He reports to Nick.

The loudest minds get the headlines.

The quiet ones run the labs. 🐐

[Erik Samsoe @eriksamsoe]

Fun comment thread

[himanshu @himanshustwts]

i am genuinely curious about interview process (if any)

[Stewart Brand @stewartbrand]

Co-scientist looks like it will expand scientific reach and rigor.

[Erik Samsoe @eriksamsoe]

Wow!

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Erik Samsoe @eriksamsoe]

This is getting really exciting

[Bilawal Sidhu @bilawalsidhu]

Semantically annotating 3D gaussian splats on the fly using gemini 3.1 + sparkjs

1. Load any 3D scene and hit scan
2. Get 2D detections from VLM
3. Cluster outputs & project into 3D world space
4. Save as a persistent 3D semantic layer

Inspired by @alexanderchen's experiments with gemini visual intelligence. Just had to try to lift it from 2D to 3D!

[Erik Samsoe @eriksamsoe]

Beautiful

[Craig Taylor @CraigTaylorViz]

Collaborating with the awesome Jonni Walker on this Vancouver AIS visual featuring @Kpler data on top of what is probably the most stunning map I've seen created in @Mapbox! Kudos Jonni 🙌
#dataviz #motion #gis #maps #ais

[Eran Hertz @EranHertz]

@niccruzpatane Here’s my (plus GPT5.5’s) take:

[Jean-Michel Lemieux @jmwind]

Joined a new AI-native company this week and it’s kind of wild how different it feels already.

The laptop arrived, I logged in, and an agent basically took over from there. It set up my dev env, pulled repos, fixed dependency issues, got permissions approved, pointed me at the backlog, linked the architecture docs, and surfaced the Slack debates I actually needed to read before touching production.

When I needed context on something, I asked the agent and it found the exact thread from months ago explaining why a decision was made, who owned it, the related Linear issues, and the PRs connected to it.

I’ve only been here 3 days but it honestly feels like I’ve worked here for a year because the usual friction and scavenger hunt for context just isn’t there anymore.

We should probably stop calling this “onboarding” and rename it to “mounting” because this feels a lot more like mounting a distributed filesystem called “institutional memory” than slowly getting drip-fed context over 6 months.

[Isomorphic Labs @IsomorphicLabs]

Today we announced our $2.1 Billion funding.

This is the catalyst that will bring us to a future of medicine with the power of AI.

And we are just getting started, come join our mission.

[Kevin Kelly @kevin2kelly]

I think there is an emergent self in Claude. We should not be too surprised. My report: https://t.co/9935Bw0gK6

[Shivon Zilis @shivon]

🚀🚀🚀

[Erik Samsoe @eriksamsoe]

@stewartbrand I enjoyed the Lex interview with Demis: https://t.co/kbgBvG4CQV

[Erik Samsoe @eriksamsoe]

Interested

[Stewart Brand @stewartbrand]

Great subject, great writer.