harnesses are so ironic because their cognitive scaffolding is probably the most Bitter Lesson-able layer of the agent, but their guardrails are almost impossible to replace in prod
in the future i think harnesses will just be guardrails on what agents can and cannot do
HOW TO GET INFINITE AGENTS 🤫🤫🗣️🗣️🔥🔥☝️☝️
1. go to yc startup school
2. win $10k AWS credits
3. set up $800/mo devbox to run 50 agents 24/7
4. go to next yc startup school
hello hi everyone i am saying my first words 😃😃
my name is shayaan and i’m an undergrad studying cs at udub! i really like proteins and work in david baker’s lab using RL to post-train protein design models so they behave like a good boy
im really interested in post-training, especially for flow-matching models. i also love mech interp. i think there’s so much low hanging fruit when applying this to protein design
my end goal in life is to solve disease and as a first step i prolly need to solve my sleep schedule
hmu if you’re working on ANYTHING cool i need to do more OOD things 🫡
I work in the Baker Lab building AI for protein design. I want to use Codex Pro to build a probe for RFdiffusion3 that will self-correct the model at test-time. By training the probe on AlphaFold3 metrics for each denoising step and guiding the diffusion model, we can significantly increase the yield of stable and unique de novo proteins!