Luca Pegolotti

Co-founder at Nucleo (YC F25). AI for oncology imaging. Coding agent aficionado

[Luca Pegolotti @zucpeg]

A couple of weeks ago, we announced that OmniLesion, @Nucleo_Research's pan-cancer detection and segmentation model, took first place in the MICCAI FLARE 2026 challenge.

Today, OmniLesion is available on our research platform. Researchers can run the model on CT scans with one click, review and edit individual lesions, and measure their size and volume.

Reach out to me or @AngelicaIAC if you’d like to know more.

[Angelica Iacovelli @AngelicaIAC]

We built the state of the art for whole-body tumor detection and segmentation.

Our pan-cancer model just won Best Pan-cancer Segmentation Accuracy at FLARE 2026 at MICCAI, #1 medical imaging conference in the world.

[Luca Pegolotti @zucpeg]

Good point actually

[morgan — @morqon]

sam: local inference is a terrible allocation of scarce resources

“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre

but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time

you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment

somehow many people's intuition is the opposite of that”

[Charlie O'Neill @oneill_c]

If anyone catches whiff of any investor at all thinking about giving these guys money, please direct them to me and I will explain why this cannot happen

Giotto is trained on kimi and launched as "the smartest european sovereign ai" 8 days after the CEO wrote that open source is a trojan horse for europe and then enacting the same trojan horse as an excuse to raise money from people who don't know better. For those who don't know I can't describe how laughable it is to use these old "benchmarks". Half the benchmark table is saturated, really old maths, zero agentic evals, and the launch EULA banned you from publishing your own numbers.

Building on open weights is fine, it's literally my job. Lying about it, but most importantly doing it so incompetently and poorly, is not. Incompetence can itself be a form of evil

[Thariq @trq212]

very weird thing happening rn

technical people are sad, they think their skills are now useless

non-technical people are desperately wishing they were more technical so they could use agents better

[Luca Pegolotti @zucpeg]

@eg0rev @mattyp 💯

[Luca Pegolotti @zucpeg]

@matthewcanham did you find a good use case for group chats by any chance?

[Luca Pegolotti @zucpeg]

@larsencc @bot Voice mode imo. Very unnatural and behind compared to eg dots

[Luca Pegolotti @zucpeg]

Good talk by @leerob from the @spacexai team on the engineering behind Grok Bot.

I really appreciated when he mentioned that team is ready to delete the product if the next generation of models doesn't fit the current harness or UI.

Given how fast models are improving, I've been wondering how long persistent agents will stay the best way to use them.

I'm a Grok Bot user (thanks to @poteto for getting me into it), and I spend a lot of time teaching it how I want it to work. Hearing this makes me hopeful the team will make the move to whatever comes next as smooth as possible.
https://t.co/SwfvwbgJ7l

[Luca Pegolotti @zucpeg]

Remembering when this graph meant something 🥲

[Luca Pegolotti @zucpeg]

@GergelyOrosz I would say that it is also very dangerous to optimize for architecture when there’s no clear demand

[Luca Pegolotti @zucpeg]

@rauchg Not so sure. I am finding that agents have allowed me to go wide but not as deep as I used to. Even if I wanted to learn more about any of the tasks I am running concurrently, I would pay that in opportunity cost. Everything boils down to a trade off between depth and width.

[Luca Pegolotti @zucpeg]

@poteto @Ionkosm It’s miles ahead of anything else I’ve tried. The only area where OAI still has a bit of an edge is voice mode imo.

[Luca Pegolotti @zucpeg]

@marcelkargul Like any code editor in the past 10 years + transparency?

[Luca Pegolotti @zucpeg]

@Bencera what if they are completely delusional?

[Luca Pegolotti @zucpeg]

@poteto @bot sheesh even listing what I got done today wouldn't fit in a tweet

[Luca Pegolotti @zucpeg]

@JFPuget Any model with max level of thinking over engineers IMO. I once instructed GPT to solve a (quite open-ended to be honest) task, which it broke down into 24 "acts", it worked 2 days straight on the first 2 and burned through my weekly usage. Been using high or x-high ever since.

[Luca Pegolotti @zucpeg]

@poteto @bot Agree. One thing I'd add: working on medical imaging software, visual bugs are hard to catch with automation, so I still lean on review. Doesn’t feel great to be the bottleneck but something can render slightly wrong and still pass every type check and test.

[Luca Pegolotti @zucpeg]

New body composition paper to keep an eye on: same raw CT from 202 patients, reconstructed 3 ways (FBP, hybrid IR, DL recon). L3 muscle and fat areas barely moved, but HU-threshold metrics shifted more. Curious to read the methods when paper is available https://t.co/Eqhs9J8vjM

[Luca Pegolotti @zucpeg]

@TaylorLorenz @Lovable Vegan options available?