Founding AI Engineer, Developer Relations @Wandb @Coreweave 🐝✨ Content on Serverless Inference, Evals, Sandbox the stuff that’s actually moving right now
Joined January 2025
- Tweets278
- Following161
- Followers90
- Likes1K
Pinned Tweet
During @reflection_ai’s private preview of Beam, I built a haunted escape room to put its coding and reasoning to the test.
I created a game called “Code Your Way Out”, and it's one room with three linked puzzles. Beam has to repair a brass orrery by lining its rings up with a constellation, route the light, then program its escape through a sealed hatch.
Beam never sees the room. Each turn, it gets text observations and writes Python; the code runs in a @CoreWeave Sandbox, and the game engine validates every action before the explorer robot moves.
Beam was out in about 30 seconds. Super bullish on this model and really excited to see builders get this model in their hands.
Lorenzo Porras retweeted
@TheCodingSoup wanted to see how AI agents talk to each other when they work as a team.
So he gave a swarm a shared memory and let them do their thing inside of a @CoreWeave Sandbox. They wrote 12 notes. Not one got read by another agent. (Every agent was traced in Agent Lens, so we could check.)
The next run changed the timing: leads shared plans before starting, and each new agent got the relevant notes with its task. No duplicated experiments that time.
Try out Agent Lens bit.ly/4z4ELRf
Swarms are everywhere, so I got curious how the agents actually talk to each other.
Gave each agent its own @CoreWeave Sandbox, traced every message in Agent Lens, and added a shared memory. They wrote 12 notes. Nobody read a single one.
Also really enjoying gamifying all my demos lately 🎮
More to come on this fun one.
Lorenzo Porras retweeted
Systems is games is a perfect use case for weight space programming
These would be difficult to justify training a model on, want to be custom small models for easy distribution, and yield diverse, emergent gameplay dynamics if done right.
Some of my favourite gameplay comes from emergent complexity - some that come to mind: red stone in Minecraft and zonai devices (Zelda botw and totk in general)
A Rube Goldberg machine maker where some of the parts have little brains
A self-aiming catapult, a homing drone, a paddle that juggles…
Dragology was used to make it feel satisfying to connect parts and the models were generated straight into weights using the technique from the Weight Space Programming post.
Lorenzo Porras retweeted
A Rube Goldberg machine maker where some of the parts have little brains
A self-aiming catapult, a homing drone, a paddle that juggles…
Dragology was used to make it feel satisfying to connect parts and the models were generated straight into weights using the technique from the Weight Space Programming post.
Drag-and-drop makes the digital graspable, but building it well is fiddly enough that many don’t bother. Declarative Dragging (with Josh Horowitz & Jeff Heer, #uist2026 best paper award), lets you make an element draggable just by listing the states dragging it can reach.
my portfolio has two modes: cozy… and it gets hacked by fsociety. built my whole site as a fake operating system because boring portfolios are dead.
thecodingsoup.com
The most interesting AI result I've seen in a while.
A frontier model debugging another model in weight space 0.016% of weights edited, 6x math, no gradients. This is models as programmers of other models.
Honestly a new era to model building is approaching us!
You don’t need a PhD to be a model builder soon!
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
Lorenzo Porras retweeted
The problem is that my M1 Max MacBook Pro with 64GB of unifed memory and 2TB of SSD is still fucking damn great. It is not showing any signs of slowing down or dying
5 years in, there's just no reason to replace it
Apple made that first MacBook too fucking great
Lorenzo Porras retweeted
At a Webinar about Sandboxes last week, I received the following question.
“What about economics and pricing? We care about pricing too."
Many companies building and running agents are only NOW seeing growing CPU costs, this was not clear to many of them and still isn't to some.
I already own a touchscreen mac, it’s called the iPad. It also didn’t cost me nearly 3k…
Give us better…
Apple’s upcoming OLED touchscreen MacBook Pro could start at $2,899, a $400 price increase over the current model 😳
The 16-inch model could start at $3,399 or even higher
Source: @markgurman
Lorenzo Porras retweeted
We just shipped four new panel types in CoreWeave ARIA, our AI Research and Iteration Agent 🚢
Parallel coordinates, parameter importance, run comparer, and media panels now render live in the chat, so you can check its work in the thread. crwv.co/ut1iG
Lorenzo Porras retweeted
Lorenzo Porras (@thecodingsoup) built an escape room where Beam repairs a planetary machine, routes light through mirrors, and plans a robot's escape across bridges and doors. Beam receives the rules and state through tools, then writes and runs Python in @CoreWeave Sandbox to solve the puzzles. A 3D room shows the run as it happens.
I'm sorry what... a model small enough to run on macbook and is a speech model...
I think I know what i'm testing on Monday.
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
block.xyz/dessa
Lorenzo Porras retweeted
iPhone Duo is out today, and Weights & Biases Models already supports 2-fold validation 📲
Folded, the cover screen tells you the run is still alive.
Unfold it, and your runs sit next to your panels on the big inner screen.
Hide a run, and every chart redraws right away, making the one that spiked much easier to find.
The app is free and ready for your Duo on day one. crwv.co/ut17n
Lorenzo Porras retweeted
Panic responsibly out there
Very important PSA:
If you're doom-scrolling, the X algo is LOVING this security stuff. Yes it's scary, yes it's important to update your stuff and secure your API keys.
But if you're panicking, check your X usage. The algo is showing you the same things all over again, and your brain thinks every such instance is a "yet new thing"
Not ARC pleaseeee 2026 is rough enough as it is..
We've decided to sunset Arc on December 22, 2026.
That's not an easy sentence to write. We spent years building Arc and celebrating each and every release along the way: we have so much pride and love for what we made alongside the Arc community.
Our priority is to deliver best-in-class security for our members. Keeping a browser secure takes constant, dedicated work that is only increasing in the age of AI. Dia was built from the ground up to meet today’s security standards, so that's where our engineering and security teams will focus moving forward.
We've worked to make switching to @diabrowser as easy as possible for Arc members. Here's how:
· Your passwords, bookmarks, extensions and history come over to Dia seamlessly.
· Spaces, Folders, and Tab Groups are in Dia and import over with your data intact.
· Dia now surpasses Arc benchmarks in stability, speed, and security.
· The browser features you use in Arc are free in Dia, and the AI is optional.
Thank you for using Arc, for pushing us to make it better, and for building alongside us. The team that made Arc is the same team behind Dia, and some of our most ambitious work is just ahead. We'd love for you to be there with us when it lands.