


lost to wonder | engineering @thrivecapital


may you live to see rockets as beaten up as shipping containers

masked decoding on gemma 3 12b to control text rivers if a token isn't the length i want it to be, i mask it out added a lora for width tags so the model is aware of text length + coherence RL afterwards

Interesting workflow from @trq212 : - building a game - game engine very agent owned - but a kind of DSL defines characters and abilities - then he can hand edit or use a tab model (!!) to modify game behaviors Reminds me of the “cognitive ergonomics” concept: focus human attention on the interesting part

Alysa Liu photographed by Spike Jonze for LIFE. new.life.com/stories-details…

Latent Blend! an image model dedicated to embedding interpolation I'll share a dedicated thread on this soon, here's a peek: graycrawford.com/?open=laten… It's live on app.lumalabs.ai, ask the agent about Latent Blend :) or rightclick some images directly to blend sweep/grid

This director feedback looks a lot like prompting agents… Detailed creative feedback, communicating intent, delivered as text.
This tweet is unavailable

keeping the flame thesephist.com/posts/flame/


for the past few weeks, I’ve been exploring painting with Fable 5.2 in code. one of the most common critiques I heard about Opus 5.5’s paintings was that it was only emulating real art. I thought that was fair, so i’ve been asking Fable 5.2 to develop personas—artists with some sort of a back story and a consistent style roughly identifiable in time not knowing what to expect, i’ve watched this project evolve in directions i never predicted. I give comments or steers, and Claude updates or revises the engines that power the brushes and paint. where paintings come up i like or find intriguing, i ask it to go deeper. these are some favorites. each of these is a python program, some one to two thousand lines of code, that places every stroke through a simulated paint engine with different bristles. most take a few thousand strokes, but i’ve pushed much higher with varying results. Claude does not use an image model, nor render or trace in advance
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.




can gaussian splats be used to render interfaces? I've seen a lot of incredible spatial demos coming out of the labs (@theworldlabs has been blowing my mind ~weekly), but they've mainly been focused on static 3D environments. I woke up today wondering: are splats any good for UI or other interactive objects, and can AI work with them? it looks like the answer is yes and yes. I prototyped an imagen -> SHARP -> spark -> popmelt pipeline that gets decently far on the first try and really far with a few rounds of art direction + interaction tuning. Smooth animation, dynamic lighting, realistic geometry... all doable, with freely available tech I haven't pushed into full scenes yet, but this experiment already felt somewhere between the detailed magic of generative video UI I've shared before and the stable dependability of textured 3D models (throwback). Plus LLMs like Astra are very good at working with splats, which makes fine tuning them way more fun/efficient next: I'm weighing whether to lean into interactive spatial design (just to see how far I can get with off the shelf tools) OR see how well this workflow handles typical responsive UI design (decidedly not what splats are for, which feels interesting). thoughts?

i am still finding the words for what this summer meant to me. the people you learn from early on set the standards you carry with you for life, and to see what greatness looks like, so young, is an incredible gift. thrive is the kind of place that makes you want to do work worthy of those around you. fellows.thrivecap.com/ apply apply apply!
at thrive, we deeply believe that the best ideas can come from anyone. our fellowship is one way we put it into practice. each year, we support a small group of college students as they pursue their own ideas alongside our team. we have been fortunate to learn from those who have shared their time and experience with us. we do not have all the answers, but we hope that sharing what we have learned can help our fellows find their own. fellows.thrivecap.com/

🖤
at thrive, we deeply believe that the best ideas can come from anyone. our fellowship is one way we put it into practice. each year, we support a small group of college students as they pursue their own ideas alongside our team. we have been fortunate to learn from those who have shared their time and experience with us. we do not have all the answers, but we hope that sharing what we have learned can help our fellows find their own. fellows.thrivecap.com/