Joel Simonoff

@moinnadeem Modal is expensive for agents running computationally heavy science work loads I.e. tens of thousands of agents that need 6 cpus and 32 GiB - compute requirements only increase. For biotech, at least now, Modal isn't feasible and you have to build in house alternatives.

Modal's advantage over all of these companies is bundling. I never even looked at the other agent sandbox providers: we run Phonic's inference workloads on Modal, I have our sales pipelines on Modal, agents were just a natural fit too. Why use 3 providers when 1 suffices?

Blog: blog.latch.bio/p/why-an-open-… Benchmarks: benchmarks.bio/txbench @badlogicgames, thanks for your work on the Pi harness - we love it at Latch!

I published a new blog today! It is widely known that prompting can have small effects on performance, but in this blog we show 2 lines of behavioral prompting can substantially impact a model’s ability on frontier biology tasks. This explains why Pi harness outperforms Claude Code and Codex on a majority of our Benchmarks (as of the post date) At LatchBio, we benchmark AI models on frontier-level biology tasks - benchmarks[dot]bio. This blog explores Tx-Bench-PP and ScBench-Long.

Reviving my Twitter to see first-hand why people are mad at Elon, and stay up to date with tech/ai. Send me accounts to follow.

Loving the signs we’re seeing today from #MarchForScience crowds around the world

Humans still rule drone racing, but NASA's AI pilot might change that bit.ly/2zOBv3H

Campanile

Let's crush a compact car! bit.ly/1OkZWoE

Cool picture x.com/NatGeo/status/…

NASA engineers use the "Scarecrow" rover to test mobility performance for Curiosity! bit.ly/1SxlWv7

Hello Twitter! #myfirstTweet