Nicolas Lopez Carranza

Introducing Genie 3, a generative protein model that substantially advances the state-of-the-art for binder design, increasing in silico success rates by up to 20x on hard multimeric targets. It also debuts a form of inference-time scaling unobserved in other design models. 🧵1/8

in the next 3 years, every major AI lab will spin up its own bio arm and in-house wet labs. biology is the next big bet in AI after code pay attention.

@ckirk47 @BoWang87 The vaccine is indeed delivered in an adjuvant setting. To remove the last few hundreds of thousands cancer cells in the body after surgery/treatment.

@BoWang87 My dad had this. I’m terrified of it. I don’t fully understand though. Is it a vaccine you take once you have been diagnosed and prevent it from coming back after removal? Or is it a vaccine you take if you are high risk?

Pancreatic cancer has one of the most suppressive tumor microenvironments in oncology. But two pancreatic cancer results dropped today. Both matter. 1. BioNTech mRNA neoantigen vaccine: nearly all responders still alive at 6 years. 98% of induced T cells were de novo — the immune system learned to see a cancer it had always been blind to. 2. Daraxonrasib: 47% ORR, 92% disease control as first-line monotherapy. KRAS G12D, undruggable for 40 years, finally has a drug. Different mechanisms. Same disease. Both working. <13% of patients survive 5 years. That number is about to change. great day for science! 🔥

@martinvars Lo mejor sería combinar la IA con la biología

AI is big but people's bodies are bigger. Two molecules vs the entire AI industry. Semaglutide: ~$33B in 2025. Tirzepatide: ~$36B. Combined: nearly $70B in actual revenue from two drugs to lose weight. OpenAI: $20B annualized run rate. Anthropic: ~$5-9B. Combined: under $30B, and those are run rates, not collected cash. A single injectable drug generates more revenue than the most valuable startup in history. Novo Nordisk runs at 40% net margins. OpenAI burned $8.5B in cash last year to generate its $20B. Biology still commands an economic reality that software has not reached. Healthcare is $4.5T in the US alone. When you solve a problem that affects hundreds of millions of human bodies, nothing else competes. The smartest bet is at the intersection: AI applied to medicine. Like the work we do building fully autonomous MDs at @certumaai

Thrilled to announce alphagenome-pytorch, an accurate, readable, and careful port of AlphaGenome's architecture and weights to PyTorch. Work with @gtcaa @m_kjellberg @chriswzou @tuxinming as part of the GenomicsxAI initiative between @anshulkundaje and @pkoo562 labs.

New online! A proteome-wide dependency map of protein interaction motifs dlvr.it/TRLLBj

A 50x speed up for processing rna seq data with GPUs. Incredible achievement

@gailcweiner Can confirm Claude Code is 100% written by Claude Code

Most people treat CLAUDE.md like a prompt file. That’s the mistake. If you want Claude Code to feel like a senior engineer living inside your repo, your project needs structure. Claude needs 4 things at all times: • the why → what the system does • the map → where things live • the rules → what’s allowed / not allowed • the workflows → how work gets done I call this: The Anatomy of a Claude Code Project 👇 ━━━━━━━━━━━━━━━ 1️⃣ CLAUDE.md = Repo Memory (keep it short) This is the north star file. Not a knowledge dump. Just: • Purpose (WHY) • Repo map (WHAT) • Rules + commands (HOW) If it gets too long, the model starts missing important context. ━━━━━━━━━━━━━━━ 2️⃣ .claude/skills/ = Reusable Expert Modes Stop rewriting instructions. Turn common workflows into skills: • code review checklist • refactor playbook • release procedure • debugging flow Result: Consistency across sessions and teammates. ━━━━━━━━━━━━━━━ 3️⃣ .claude/hooks/ = Guardrails Models forget. Hooks don’t. Use them for things that must be deterministic: • run formatter after edits • run tests on core changes • block unsafe directories (auth, billing, migrations) ━━━━━━━━━━━━━━━ 4️⃣ docs/ = Progressive Context Don’t bloat prompts. Claude just needs to know where truth lives: • architecture overview • ADRs (engineering decisions) • operational runbooks ━━━━━━━━━━━━━━━ 5️⃣ Local CLAUDE.md for risky modules Put small files near sharp edges: src/auth/CLAUDE.md src/persistence/CLAUDE.md infra/CLAUDE.md Now Claude sees the gotchas exactly when it works there. ━━━━━━━━━━━━━━━ Prompting is temporary. Structure is permanent. When your repo is organized this way, Claude stops behaving like a chatbot… …and starts acting like a project-native engineer.

Coding these days capsnlock.com/blogs/news/sim…

Great @veritasium video on the OpenSSH/xz backdoor and how @AndresFreundTec found it. Not all heroes wear capes youtube.com/watch?v=aoag03…

Have been using this daily and loving it! Tell us what you think

@alexrives Congratulations. Amazing journey.

Today CZI is announcing an unprecedented new scientific initiative to build the future of AI-powered biology. I am joining CZI to lead this initiative as Head of Science, and the EvolutionaryScale team is joining forces with Biohub. This is the first large scale scientific effort to combine frontier AI and frontier biology. I feel an incredible sense of optimism in this moment. There is a path to build predictive models of life that can fundamentally accelerate science, and unlock a new understanding of disease. biohub.org/blog/frontier-…

@vitrupo GPT 6 will be so smart that will avoid pursuing a PhD and go straight to installing air conditioners

Demis Hassabis: calling today's chatbots “PhD intelligences” is nonsense. They can dazzle at a PhD level one moment and fail high school math the next. True AGI won't make trivial mistakes. It will reason, adapt, and learn continuously. We're still 5–10 years away.

No AI was used to create this

The @VivaTech event is nearly here, and we're excited to be leading the charge alongside visionary leaders like Jensen Huang of @Nividia, @ylecun, @v_wyche and many more top tech figures, industry experts and CEOs from around the world. Learn more below. 🧵

@Xisu_06 @eris_28 @alex_estebaranz paso algo?

@eris_28 Le ha pasado algo concreto hoy?

Nagarro cerró a 65, ya termino yo, por el culo te la hinco

holy shit AI can now decode the human proteome without any reference genome. a new paper published today presents a new model that can read raw mass spec and generate novel peptide sequences from scratch. no database or priors. just biology. 1/

InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments - Nature Machine Intelligence buff.ly/RtchmPL