Today, we’re launching the Geodesic API Platform. geodesiclab.com/api For the first time, Geodesic is making our AI models and drug discovery capabilities available through APIs. At its core is NovaAtom, our in-house model for predicting the structures of proteins, small molecules, nucleic acids, and their interactions. Now available in Lite Preview, this is the first time NovaAtom has been made available beyond Geodesic’s own discovery platform. Alongside NovaAtom, we’ve integrated the field’s core models — carefully curated and continuously updated. To use the API: curl -X POST platform.geodesiclab.com/api… \ -H "Authorization: Bearer $GEODESIC_API_KEY" \ -F "model=novaatom" \ -F 'params={"jobName":"rbd-nanobody","sequences":">rbd\nTNLCPFGEVFNATRFASV...\n>nb\nQVQLVESGGGLVQAGGSLR..."}' Poll the job, pull the results, and feed them directly into the next model. Your AI assistant can use the platform directly, too. Connect Claude Code, Codex, or your own agent with one URL and an API key. We manage the integrations and handoffs. You focus on the science. Understand biology. Predict structures. Design proteins. Discover molecules. One key. One interface. Start building today!

We just ran Jev on our WebMCP benchmark. The result: basically broke the benchmark. Jev + Mercury 2.5 (a fast, low-cost LLM) using WebMCP solved 100% of the tasks at roughly 112× lower model cost than GPT-6 Astra using computer use with code execution. Compared to Astra using screenshot-based computer use, the model cost was 245× lower (!). We also compared Jev operating the browser with and without WebMCP. We used Browser Use’s open-source Ultrafast, with some improvements to the harness to make it more reliable across the benchmark. Jev’s browser-control accuracy on its own was not amazing - adding WebMCP nearly doubled the number of solved tasks, from 25/49 to 49/49, while reducing model cost by 18% (more on why below). The benchmark and methodology are fully open and reproducible. Full results: webmcp.com/benchmark A few words on how the Jev + WebMCP harness works and why this is exciting: Jev receives text as input and a set of discrete options it can choose from. With WebMCP, those options are the tools exposed by the website. At each step, Jev sees the task, the available tools and previous results, then picks what to do next. The limitation is that Jev can’t generate arbitrary text, which you need for tool arguments. For example, it can choose the search_products tool, but it can’t generate the search query itself. So we split the work: Jev picks the tool and Mercury 2.5 generates the arguments if needed. This works well because turns out most of the cognitive load in these tasks is around choosing the right action. The argument generation itself is relatively simple, so we can delegate to a small and very fast model. We used Mercury, which outputs 1,000+ tokens/sec and is very cheap. The result is a pretty simple combination: Jev for tool selection + Mercury for arguments + WebMCP for the interface. It ends up being very reliable, very fast, and very cheap. A few words about Ultrafast and why do we think it underperforms: Without WebMCP, Jev chooses from the page’s controls: which button to click, which field to fill, or which option to select. But choosing a valid button is different from choosing the right next step. The agent still has to navigate menus, understand forms, recover from errors and recognize when the task is actually complete. Our hypothesis is that WebMCP makes the decision space much simpler. Instead of figuring out a sequence of clicks through a website, Jev chooses explicit actions that directly advance the task. @typesafeai itself documents weaker accuracy on questions requiring multiple reasoning steps. WebMCP moves much of that complexity into the website’s tools, leaving Jev with clearer decisions and fewer opportunities to go wrong (in a sense WebMCP "compresses" a sequence of clicks into one tool call). Our modified Ultrafast setup solved 25/49 tasks - that is a result for our particular implementation and benchmark, not a universal limit on Jev or Browser Use. We are open to more harness optimization to get this result to perform better, feel free to directly contribute to the benchmark here: github.com/nekuda-ai/WindTun… Browser-use ultrafast: github.com/browser-use/jev-u…

NovaDDE Plus is now live! Built for scientists who use AI for drug discovery every day — more compute, priority access, concurrent runs, API access, and end-to-end campaign execution. $30/month and sign up by September 25 to get your first month free. Our goal is simple: put the most powerful AI for drug discovery into the hands of every scientist. geodesiclab.com/pricing

We’re launching the Geodesic Grand Challenges. What are the hardest questions in drug discovery that, if solved, could change what’s possible over the next 5–10 years? We’re asking you to help define them. Selected questions will become official Geodesic Grand Challenges. Each selected contributor receives 10,000 Geodesic credits. Once the challenges are selected, we’ll open a call for solutions, with a $1 million prize for a verified solution to each challenge. The next breakthrough starts with the right question. Submit yours！ geodesiclab.com/grand-challe…

We’re launching the Geodesic Grand Challenges. What are the hardest questions in drug discovery that, if solved, could change what’s possible over the next 5–10 years? We’re asking you to help define them. Selected questions will become official Geodesic Grand Challenges. Each selected contributor receives 10,000 Geodesic credits. Once the challenges are selected, we’ll open a call for solutions, with a $1 million prize for a verified solution to each challenge. The next breakthrough starts with the right question. Submit yours！ geodesiclab.com/grand-challe…

We built high-throughput materials labs in Menlo Park to create a loop between experiments and models. The labs generate fresh data, the models learn from it, and then help us decide what to try next. Using only 1,300 H200s, plus months of our experimental data, we mid-trained and RL’d an open-source model to surpass GPT-6 Astra on our analysis benchmark. We call it Neon. This is real footage from our lab. We’re focusing first on hard problems in materials science, including superconductors, magnets, and semiconductor materials. Read our blog posts below.

One way to frame mathematicians’ concerns about the impact of AI on math: it may lead to the gradual disempowerment of humanity in our ability to understand math because it may degrade the social structures that presently enable that understanding.

25 Fields Medalists are worried AI solving math too fast could damage mathematics. I see the opposite happening in coding. Imagine scientists delaying a cancer cure by 100 years just so they can experience discovering it themselves. It would be a disaster for humanity.

Here is a potential roadmap to reversing aging by 2040, created by GPT-6 Pro with Image 2.5. It is important to point out that we will already reach longevity escape velocity by around 2035, so if you can make it to then, you are very likely to live for hundreds of more years!

1/ Today, we’re introducing Geodesic Intelligence, and launching NovaDDE and NovaAtom-Lite-Preview. Geodesic is building an AI-native platform for protein therapeutics, building AGI for drug discovery to find the shortest path from biology to medicines. geodesiclab.com

1/ Today, we’re introducing Geodesic Intelligence, and launching NovaDDE and NovaAtom-Lite-Preview. Geodesic is building an AI-native platform for protein therapeutics, building AGI for drug discovery to find the shortest path from biology to medicines. geodesiclab.com

1/ Today, we’re introducing Geodesic Intelligence, and launching NovaDDE and NovaAtom-Lite-Preview. Geodesic is building an AI-native platform for protein therapeutics, building AGI for drug discovery to find the shortest path from biology to medicines. geodesiclab.com