Debesh Mandal

Co-founder and CEO @nanograb (YC S23)

[Debesh Mandal @debesh]

mRNA will be crucial to beating cancer and solving disease but only if we can deliver it to the right cells.

Nanograb's AI-designed multivalent nanoparticles address a cell's unique receptor fingerprint, now proven in vivo across multiple cell types and scaling to many more.

[Luca Springer @luca_springer]

Building @numenbio with @_tom_dot_com to engineer a future without cancer deaths. Find out more below in an interview with our partners at @TQVentures!

[Eric Topol @EricTopol]

We are at the beginning of a new and exciting era to be able to program our immune system in the body (in vivo). This new review @SciImmunology nails it https://t.co/ibUYVxGWjl

[Debesh Mandal @debesh]

Wonder how it fares in multiplayer Catan when everyone teams up against it and refuses to trade.

[distributed cognition @distcog]

We're excited to unveil VINCO, our frontier AI model trained to play and win 1v1 Catan.

We've secretly deployed it on the https://t.co/jVgSFYCfkd global leaderboard, where it has reached both the #1 and #2 positions, consistently beating every human world champion.

[Meri Beckwith @meribeckwith]

https://t.co/Rs7gjxxb1M

[Debesh Mandal @debesh]

Very cool, multi-body self-assembly is the next frontier

[Andy I. Nguyen @andy_i_nguyen]

Can assembly into a framework help peptides fold like proteins?

In @J_A_C_S, we show that framework assembly enables 15-19mer peptides to adopt diverse tertiary folds. With 7 mutable positions, it is highly modular platform for framework engineering!

https://t.co/qNS3RTjFGs

[Ankit Gupta @agupta]

The YC deadline is tonight.

It's one of my favorite days of the year. I get to stay up late into the night reading about the future that thousands of founders are dreaming.

There are 20 YC partners, all former YC founders, ready to help you manifest those visions into reality.

Apply today: https://t.co/ZiFluc4zuP

[Shanil Panara @shanilpanara]

Redid a protein visualisation in 10 minutes with Claude Code. The first version took me 2 hours yesterday 🤯

Thanks @JacobMolBio for Proteus! https://t.co/C7bGQRMcli

[Debesh Mandal @debesh]

long bio platforms

[Molly Gibson @gibsmk]

It’s interesting to think about what changes in the “pipeline-in-a-person” era.

When one scientist + AI can run multiple drug programs, differentiated platform capabilities become way more valuable. More, smaller asset companies = more customers.

And now with AI, differentiated platforms should also be able to scale to support enough customers to capture significant platform value.

It used to be that the only way to do build valuable platform companies was to own the pipeline internally. Hopefully that’s not the case anymore. It's a great time to be long bio platforms.

[etn. @etnshow]

Introducing ETN's London Food Map.

These are the best places for techbros, gals, and VCs to increase shareholder value in the field.

Suggestions welcome.

https://t.co/mJ3ayYnzZ4

[Debesh Mandal @debesh]

This is insanely good

[Gabriel Ocana-Santero @OcanaSantero]

Last night an AI agent performed brain surgery on a mouse.

We gave it 19 gene therapy vectors in a spreadsheet, a mouse model of epilepsy, access to a motorize surgery rig with cameras and one goal: reduce seizures.

It picked the drug. It picked the brain region. It derived the coordinates from three papers. Then it drove the stereotaxic arms into the brain and injected 250 nanolitres while watching the entry site through the rig camera for bleeding.

A licensed vet gated every irreversible step and held a physical kill switch to stop the AI agent.

Thread on what it decided, what it saw, and the moment it refused to let me override it.

[Writing this on the spot out of excitement, but I've been 18hrs in front of my laptop coding and coordinating this, so keeping it brief and descriptive, more cohesive thoughts on this soon...]

[Debesh Mandal @debesh]

Delivering mRNA to novel cell types (here cancer) is absolutely going to be the future of medicine. Huge progress from Strand

[Strand Therapeutics @StrandTx]

The first patients have been dosed in ASCENT-1, our Phase 1 trial of STX-003, an IV-delivered mRNA therapy designed to bring the potent immune-activating protein IL-12 to tumors throughout the body.

It’s our first systemic test of programmable mRNA, and it’s built to solve a problem that’s defined cancer treatment for decades: the drugs powerful enough to kill tumors often damage healthy tissue, too. STX-003 is designed to sidestep that problem by selectively activating where it’s needed.

We believe it’s just the start of what the platform could make possible in this era of next-generation delivery. If this works, the same technology could carry other therapeutic proteins, opening the door to a new class of programmable medicines.

Our CEO and co-founder @DrSynbio co-founder, President, and Head of R&D @tasuku_kitada take a moment to discuss this milestone and how this trial is a test of a fundamentally new approach to treating disease.

🧬 Learn more: https://t.co/OH8UG1kQHO

[David Senra @davidsenra]

Revolut CEO Nik Storonsky says the best employees are like “self-guided missiles.”

“You don’t even need to tell them what the goal is. They self-identify the goal, and then they reach it.”

“Average people, you tell them the goal, and then you need to spend weekly iterations with them. So you spend management time. That’s what I don’t want.”

“The best executives are very tough.”

“Likable is never the goal for executives. The goal is always to achieve the goal with the minimal number of resources spent.”

[Philip Johnston @PhilipJohnston]

It took me a while to realize that in Silicon Valley, “He’s good at fundraising” is often meant as an insult 😅

[Debesh Mandal @debesh]

@TomRoseberry789 Fast observation is key!

[Ali Mortazavi @AAMortazavi]

siRNAs and delivery systems are the future of medicine

[CZ 🔶 BNB @cz_binance]

People often want to ask me if their startup idea is good, as if my opinion means anything.

I think 99% of ideas are good if the team can execute well. The problem is, 98% of teams fail at execution.

So, no need to sell me your idea, show your execution.

[Debesh Mandal @debesh]

The real bottleneck is getting the words out of your brain

[Clara Gold @Clara_Gold]

90% of my communication with my engineers is Claude telling me what to say, me sending it on Slack, and them pasting it into Codex, which writes the code.

Basically, my Claude is talking to their Codex through us.

Somehow, we’ve made humans the bottleneck in AI-to-AI communication.

[Debesh Mandal @debesh]

No one in the comments watched until the end

[John Coogan @johncoogan]

Not enough people are talking about this

[Debesh Mandal @debesh]

@MelindaBChu1 I don't know enough about T2.0 or clinical diagnostics to comment but benchtop Raman is possible and demonstrated by SPARTA