flower and tree enthusiast designing @ anthropic
Hudson Valley, NY
Joined January 2012
- Tweets23.6K
- Following1.2K
- Followers12.4K
- Likes51.7K
People are saying this is the hottest AI talk in NYC this fall
Can automating an MMO teach us about multi-agent systems?
On October 14th, @maxbittker will present RuneScape Bench: MMOs for Agents.
RS-sdk is a 2026 project to turn an open source implementation of the game, LostCity, into a testbed for new experiments. Its results have implications in many areas: design libraries for coding agents, evals, LLM post-training, game design, simulated economics, and even the future of multi-agent systems, when agents are tasked with trading and trusting one another in a shared world.
RSVP below:
Ryan Mather retweeted
We're excited to be unveiling the first challenge in our protein design competition! EGFR is the target from the first competition, but we're asking for much more this time: a mouse cross-reactive binder that conditionally binds at acidic pH but not neutral pH. This problem is at the frontier of today's capabilities, but I'm confident that the world's leading designers, equipped with a ton of tokens and compute, and over 1,000 designs screened in the lab will be able to solve it.
We're launching Challenge 1 of the Anthropic x Adaptyv Protein Design Competition on @proteinbase: design a conditional binder to EGFR, a key cancer target.
The goal: bind EGFR under the acidic conditions of the tumor environment, but not at the normal pH around healthy cells. Moreover, the proteins must bind to both the human and the mouse variant of EGFR to support easier preclinical testing
New blog post! How I got into AI. I figured it would be good to write this down, before I forget. ryancan.build/2-blog/the-sto…
interesting to see which parts of this early proto have simply scaled w/ models vs. been replaced with fundamentally new approaches
* points at bitter lesson sign *
beatbox bootcamp 🦝🎤🎶, inspired by @everydaylouie , all assets made with #dalle
I'm so excited for the future of game creation :D
Yesterday, my boys and I vibe coded a game together. They tell me what they want in their game and I prompt it into Opus 5.5 to build it.
And of course they picked "Zelda Breath of the Wild" inspired game, where they can explore an open world, do dungeon puzzles, fight mini bosses and a final boss. The twist is that the hero holds a giant paintbrush as a weapon, each color had a different attack and effect (red = fire, blue = ice, yellow = bounce, green = vines). And oh they also wanted to fly on the paintbrush.
We spent our whole saturday playing and iterating on the game. It was great fun.
I told them, the future is all about Imagination, whatever they can imagine, it will be manifested in a digital experience.
At the end of the day, the game had:
- 2 biomes (1 island and a bunch of floating islands)
- Paintbrush-based combat (4 colors representing different effects and mechanics)
- 3 dungeons with puzzles
- An undeground cave
- Unlockable flying paintbrush when you activate 4 crystals around the island
- 30+ enemies and elites
- 1 giant boss
As you can see in the gameplaye video below, its not the most polished video game but it's so satisfying to see my boys getting bewildered when whatever they asked for, the game is built before their eyes.
Of all the games I have vibe coded so far, this was the most satisfying because my boys were actively co-creating it and playing it.
This is definitely not the last game we're making together, they have already started brainstorming their next game, hint: "Peak with grappling hooks and TNTs."
You can play the game here, works only on desktop:
wildbrush.vercel.app/
doctor: how long does it last, when you have the anxiety?
me: idk a couple hours
doctor: hm, do you feel depressed?
me: no, I mean I think it’s just stress. I don’t want to die
doctor: ok. That could take a while to figure out. Let’s focus on the knee
How it looked up in Ossining
Crazy light across Manhattan with a rainbow as the sun set ahead of an approaching nor'easter storm in New York City, Friday evening #newyorkcity #nyc #newyork #sunset #noreaster #rainbow
Claude Science for adding a loop
New on the Science Blog: Yes, Claude can do Nine Loops.
Theoretical physicists predict how particles behave using formulas called scattering amplitudes. These are notoriously hard to compute, so researchers work with layers of increasingly fine corrections called “loops”—each added loop makes the answer more precise but takes exponentially more computation. Most calculations stop at two or three loops. Eight loops was the previous record in a simplified model physicists use as a testing ground (planar N=4 super-Yang-Mills), set by SLAC's Lance Dixon and collaborators.
Last month, physicist and science writer @4gravitons issued a challenge: could an AI push past eight loops in this model, using only the compute budget an academic could reasonably access?
Given a single prompt describing the nine-loop problem, Claude ran largely unsupervised for days in Claude Science and solved it using methods developed by Dixon and his colleagues, at a total cost of a few thousand dollars. Dixon independently verified the result, and von Hippel wrote about the experience for our blog.
Read more: anthropic.com/research/yes-c…
