Brendan Hogan
@brendanh0gan
870 Following 4K Followers
beautiful work - inspired me to do a similar idea I have had for a while - train a model to create those minified js /canvas animations
Full details below - all trained on @PrimeIntellect 's Lab
Example animation + code:
setup=()=>createCanvas(400,400);draw=()=>{background(8);let t=frameCount/40;stroke(180,220,255,140);strokeWeight(1.2);for(let i=0;i<320;i++){let x=width/2+(sin(t+0.02*i)*150);let y=height/2+(cos(t+0.03*i)*120);let dx=sin(t*0.8+0.01*i)*30+noise(t*0.3+i*0.1)*20;let dy=cos(t*0.7+0.01*i)*25+noise(t*0.4+i*0.15)*25;push();translate(x+dx,y+dy);rotate(t*0.5+i*0.1);for(let j=0;j<8;j++){point(0,0);line(0,0,cos(t+j*0.5)*40,sin(t+j*0.5)*20);}pop();}}
Show more
I am extremely excited to announce I am starting a new position on the applied research team at @PrimeIntellect !
open source intelligence is the future, and every company and everyone should be able to train and control their own models - let a thousand flowers bloom
I fully believe Prime Intellect is the company that will build this version of the future, and I am just so excited and grateful to be part of the mission!
Show more
Today, we’re extending our RL stack beyond individual agents to multi-agent systems.
You can now express arbitrary agent interactions and train them.
A little over 2 years ago, I solved the SolidGoldMagikarp stability problem.
Today, I am releasing the results of that work as a new technique to regularize training.
More details below.
Introducing Prime Agent:
A self-improving RLM harness for coding and long-running autonomous tasks.
Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.
Show more
Agents are handling more and more of YOUR money — so much so that AIE NYC will be our first Finance-mainstage conference this Oct!
🆕Live now: the entire WF26 AI in Finance Track!
Watch ↓
@brendanh0gan, Morgan Stanley
Lucas Palma, Nubank
@YogiNotTheBear, FactSet
@Saikallis9012, Fidelity Investments
@menkesu, Intuit
Divakar Kumar, FlyersSoft
Shawn Chan, China Resources Holdings
@siddanth2486, Auditoria AI
@vinooganesh, Kepler
@ShreyaR + @aman2304, Nubank (with Snowglobe)
Show more
3 months ago my mom started using chatgpt to help with lesson plans, meal prep etc.
today she showed me how chat suggested she try codex and she used it to build and deploy to vercel her own personal to do // organization // planning app that she uses and optimizes daily - she doesn’t know how to code at all / has no idea what vercel even is but wanted a way to see the site on all her devices
Very strange and cool to see this all happen organically
Show more
Scaling agentic RL environments: today we're publishing 365,000+ tasks for SWE, terminal, and search agents - 23 tasksets behind one API, one sandbox lifecycle, one command.
all this time bjork was my favorite artist and I never knew
what this means is we all win
running an agent on a droplet, that I message via telegram when I have a thought I want to save // a link to bookmark // something I need to do - and it categorizes it for me and updates a dashboard site I can access anywhere
starting to get the use of claw like things
Show more
wow cmux + digital ocean droplet is amazing - cant believe I didnt do this earlier
We've made 2 quality breakthroughs since the original demo, and have a new model training that's gonna be even better
DM me or Justin for beta access!
Announcing our $130M Series A to build the Open Superintelligence Stack
Led by Radical Ventures, with NVIDIA, Intel Capital, Dell Capital, and existing investors
Train, deploy, and continuously improve your own models using our stack.
Own your intelligence.
Show more
