John Yang

Co-founder @ Reticular (YC F24). CS & Math @ MIT

[John Yang @johnyang100]

If you’ve ever

- thought AI protein folding is magical ✨
- wanted more than a pLDDT score 🔎
- or just think mech interp in bio is cool 🤓

then read the 🧵 👇 on our first paper towards interpretable protein structure prediction just accepted to workshops at ICLR

[Reticular (YC F24) @ReticularAI]

A First Step Towards Interpretable Protein Structure Prediction

With SAEFold, we enable mechanistic interpretability on ESMFold, a protein structure prediction model, for the first time.

Watch @NithinParsan demo a case study here w/ links for paper & open-source code 👇

[John Yang @johnyang100]

@yifan_zhang_ How does this compare to LieRE and STRING which generalize from SO(d) to general Lie groups?

https://t.co/HdaAFxAZ0Q
https://t.co/LWVkQiv1sl

[John Yang @johnyang100]

@zdeborova @icmlconf cool! have you guys considered extending your spectral analysis to tensor products? i’m curious given there’s machinery there for analyzing spectra with the non-linear activation fns across multiple layers.

[John Yang @johnyang100]

@wilson_spearman @Lovable @antonosika the teacher copies the student

[Wilson Spearman @wilson_spearman]

@kognise7 +78,234% MRR btw

[John Yang @johnyang100]

@NeilDeshmukh @SolaAI_ @a16z @conviction @ycombinator Congrats! 🎊

[Neil Deshmukh @NeilDeshmukh]

Excited to announce that @SolaAI_ has raised a $17.5M Series A led by @a16z with support from @Conviction @ycombinator, bringing total funding to $21M 🚀

From the start, we set out to reimagine human-AI interaction to push the boundaries of process automation. Our agents watch how people do tasks on-screen, then handle those tasks automatically, even in legacy tools.

[John Yang @johnyang100]

@aditabrm unc

[John Yang @johnyang100]

Abstraction requires a tradeoff between task accuracy and compression. Binary codes => 100% accuracy. English => less accuracy, dependent on receiver. I like how the information bottleneck method rigorously describes this tradeoff, formulating it as a minimax optimization. https://t.co/Zf558vPShh

[John Yang @johnyang100]

@nkbuduma @AmbienceAI Congrats on the raise! Goat USABO alum founder👏👏👏

[Kulveer @kul]

Grateful to be featured in @Forbes and to go deeper and share the vision behind @phosphorcap.

Thank you to @dasha_shunina for taking the time to understand Phosphor’s mission.

[Ekdeep Singh Lubana @EkdeepL]

🚨 New paper alert!

Linear representation hypothesis (LRH) argues concepts are encoded as **sparse sum of orthogonal directions**, motivating interpretability tools like SAEs. But what if some concepts don’t fit that mold? Would SAEs capture them? 🤔

1/11

[John Yang @johnyang100]

2/3 companies I mocked this batch got in! Feeling proud. Highest leverage 15 min every time.

[John Yang @johnyang100]

The YC Summer 25 application deadline is May 13th!

No better time to found & build tech that'll shape the next decade.

To pay it forward, I'm happy to review applications & mock interviews so reach out!

https://t.co/wBx0GIk9UD

[Uzay @uzpg_]

@kaivu, @atticuswzf , and I were researching long horizon reasoning (with @jacobandreas). We found existing benchmarks’ hard problems often featured tricky puzzles, not tests of system understanding. So we made Breakpoint: a SWE benchmark designed to disambiguate this capability.

[John Yang @johnyang100]

The YC Summer 25 application deadline is May 13th!

No better time to found & build tech that'll shape the next decade.

To pay it forward, I'm happy to review applications & mock interviews so reach out!

https://t.co/wBx0GIk9UD

[Kyle Tretina, Ph.D. @AllThingsApx]

Biology’s lack of data is holding back its AI boom.

Epoch’s latest report shows explosive growth in biological model training data size from 2017–2021 (9.7×/year), but a (2.1x/year) plateau since.

AI models for biology are ready to transform science if the data can keep up.

[Ankit Gupta @agupta]

I’m at #ICLR2025 the next few days! I’m making lots of time in my schedule to talk to researchers who might someday want to start a company. If that’s you, sign up for a YC office hours with me here. https://t.co/uUMQvPqV6C

[John Yang @johnyang100]

@yusufroohani You too! Hope to bump into you again, especially at the bio workshops

[Maxime Peyrard @peyrardMax]

Our paper "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" will be presented at #ICLR2025!
It's also the first paper of my first PhD student — congrats @maximemeloux! 🎉

blog post: https://t.co/puTwN8dgYS
A short thread 🧵

[John Yang @johnyang100]

Generally curious abt spectral applications for interpretability though! Would love to talk to someone other than o3 abt this haha.

[John Yang @johnyang100]

Heading to ICLR in 🇸🇬 next week.
If anyone’d like to connect abt random matrix theory & Tensor Programs for mechanistic interpretability, DM me and if you’re in Singapore or SF, I’ll treat.

[John Yang @johnyang100]

To put out a specific topic, I’ve been intrigued by the Free Independence Principle and Jacobian SV distribution in TP III and their implications for interpreting cross-layer computation.