Founding MTS @ Edison; PhD ML @ CMU

San Francisco, CA
Joined September 2015
Conor Igoe retweeted
When your children ask what you were doing during the AI revolution, what do you want to tell them? We're using AI to find new medicines and save lives. Join us.
6
20
3
108
13,491
Conor Igoe retweeted
Today, we're announcing Edison Advances, a home for our research announcements, engineering blogs, open-weights models and benchmarks. At Edison, we’re building Kosmos, an AI Scientist, to solve foundational research problems and make truly novel discoveries across scientific domains. Alongside that work, we’re developing better ways to measure and evaluate AI scientists, push their ability to work on long-horizon tasks, and identify gaps in their reasoning. Edison Advances brings our existing work together in one place and we will use it to publish new work as our research progresses. Follow along as the work develops, and get in touch if you’re interested in contributing.
14
39
1
328
14,937
Conor Igoe retweeted
On July 25th in Dublin, I will be running a reading group for Ulysses with the incomparable @DanMulhall – DM if you'd like to join!
1
2
8
2,715
Conor Igoe retweeted
At Edison, we are on a mission to leverage AI to prevent or cure all diseases. Today, we are announcing a critical step: our first partnership using our AI scientist, Kosmos, to launch new biotech companies. Many of the most transformative new medicines begin life in biotech companies rather than big pharmas. We are partnering with Population Health Partners (PHP) to deploy Kosmos across their company creation pipeline. Kosmos will assist in the creation of PHP’s companies, allowing us to bring more medicines to patients. PHP has an outstanding track record of incubating successful biotech companies like @MetseraInc (acquired by @pfizer in a $10B deal), and The Medicines Company (acquired by @Novartis for $9.7B), to name just two. With PHP, we will focus on biotechs treating population-scale diseases like cardiovascular disease and obesity. If we can scale up the process of launching Metsera-style companies, we have an opportunity to transform medicine in the coming years.
6
35
5
167
31,803
Conor Igoe retweeted
The Fitzwilliam maths meetups were featured in the latest paper edition of @WorksInProgMag
3
3
1
21
1,764
Conor Igoe retweeted
New from @_fitzwilliam: We are going all-island, and launching a new reading group in Belfast
1
1
1
8
1,721
Conor Igoe retweeted
Episode 3 of Memo to File is out now! Former Sec Gen Brendan Tuohy discusses how Ireland invested in the internet through the Global Crossing project. Conor Igoe joins us for the digest segment to reflect on the relevance today in the context of AI. linktr.ee/memotofilepodcast
1
2
53
Conor Igoe retweeted
We live in a golden age of biology. So why are people still dying from disease? Because discovery and development move slower than they should. Today, we’re partnering with Incyte to change that. Kosmos is now the first agent that can compress months of drug development into weeks, from the earliest stages of scientific discovery through to FDA approval. @Incyte will be the first company to deploy it across their pipeline. Work that used to take a team of scientists months now happens in weeks. Patients can't wait, and neither can we.
120
438
179
1,925
7,041,754
Dublin has a high density of ML engineering experience. In a new essay, @cvi94 asks: Why is Ireland essentially absent from frontier AI research?
1
2
6
398
Conor Igoe retweeted
Dublin has arguably the highest density of ML engineers in Europe. For a new @_fitzwilliam essay, @cvi94 asks: Why is it virtually absent from frontier AI research?
12
12
2
67
12,365
We're launching a 1,900 question benchmark for measuring AI progress on scientific tasks: lab protocols, reading figures, tables, assessing clinical trials, patents, molecular cloning. This is significantly difficult for frontier models, but it took us over a year to build! Labbench2 was built for agents too, with tasks like retrieving supporting information or accessing a database to answer a scientific question. Including choosing the right database! This may be the last open-answer style benchmark we can make in science. The team has been doing these for almost 3 years and it took real work to find the right people to build questions that are genuinely challenging for LLMs, but still actually meaningful questions. During the QA phase, the human question writers were wrong more often the LLMs with a good agent harness. It took many many rounds of revision to get this done and added months to the process. I'm very happy with the output and look forward to seeing models get better at scientific tasks! The harness and benchmark are open source and a paper describing it is out now. All links to code/paper/data: lab-bench.ai/
15
42
4
307
28,076
We are delighted to announce our $70M seed round today. We are automating scientific research. This is only the beginning. Join us!
Science is too slow. At Edison, we are integrating AI Scientists into the full stack of research, from basic discovery to clinical trials. We want cures for all diseases by mid-century. We have raised a $70M seed to get started. Join us. We need cracked software engineers who want to work on finding cures rather than selling ads and generating slop. If you’re reading this, you’re probably a candidate. We need brilliant AI researchers who want to figure out how AI will accelerate real-world science. We need scientists and researchers with deep expertise in biology, biotech, and pharma who want to figure out how to integrate AI deeply into scientific workflows, from ideation to experimentation, and how to measure success or failure. We need extraordinarily talented generalist operators across BD, sales, product management, and partnerships who can focus on getting our tools into the hands of pharmaceutical companies. If any of these roles sound like you, get in touch. We are also expanding access to our platform. Our goal is to accelerate science writ large. To that end, we will continue to give academics and students 650 credits/mo indefinitely. I can’t promise we’ll keep this up forever, but we will try. Kosmos will still cost 200 credits, and the other agents (Analysis, Literature, etc.) will cost 1 or 2 credits. All paid users will have access to our regular agents, like our Analysis agent, Literature agent, and so on, for free via the UI. API access will still be paid, and users without a paid subscription will continue to get 10 credits per month for those agents. Our $200/mo subscription for 650 credits/mo is staying in place for now, but might be phased out at our next major product update. Along the lines of accelerating science, we’re also doing a major release of PaperQA today, our flagship open source literature agent, as part of our commitment to open science. In the short run, expect major improvements to Kosmos, including the ability to automatically access data, the ability to steer its exploration, and the ability to converse directly with its world model. In the long run, expect exponentially increasing rates of scientific discoveries, in biology and elsewhere. Our round is led by Triatomic Capital, Spark Capital, and a major US institutional biotech investor. We are also joined in this round by existing investors Pillar VC and Susa Ventures, two exceptional early-stage funds who backed us at founding, along with Striker Venture Partners, Hawktail VC, Olive VC, and a host of exceptional angels that includes famous AI researchers, the CEOs of multiple frontier AI labs, and leadership of major biotech and pharma companies.
6
14
4
218
20,306
Science is too slow. At Edison, we are integrating AI Scientists into the full stack of research, from basic discovery to clinical trials. We want cures for all diseases by mid-century. We have raised a $70M seed to get started. Join us. We need cracked software engineers who want to work on finding cures rather than selling ads and generating slop. If you’re reading this, you’re probably a candidate. We need brilliant AI researchers who want to figure out how AI will accelerate real-world science. We need scientists and researchers with deep expertise in biology, biotech, and pharma who want to figure out how to integrate AI deeply into scientific workflows, from ideation to experimentation, and how to measure success or failure. We need extraordinarily talented generalist operators across BD, sales, product management, and partnerships who can focus on getting our tools into the hands of pharmaceutical companies. If any of these roles sound like you, get in touch. We are also expanding access to our platform. Our goal is to accelerate science writ large. To that end, we will continue to give academics and students 650 credits/mo indefinitely. I can’t promise we’ll keep this up forever, but we will try. Kosmos will still cost 200 credits, and the other agents (Analysis, Literature, etc.) will cost 1 or 2 credits. All paid users will have access to our regular agents, like our Analysis agent, Literature agent, and so on, for free via the UI. API access will still be paid, and users without a paid subscription will continue to get 10 credits per month for those agents. Our $200/mo subscription for 650 credits/mo is staying in place for now, but might be phased out at our next major product update. Along the lines of accelerating science, we’re also doing a major release of PaperQA today, our flagship open source literature agent, as part of our commitment to open science. In the short run, expect major improvements to Kosmos, including the ability to automatically access data, the ability to steer its exploration, and the ability to converse directly with its world model. In the long run, expect exponentially increasing rates of scientific discoveries, in biology and elsewhere. Our round is led by Triatomic Capital, Spark Capital, and a major US institutional biotech investor. We are also joined in this round by existing investors Pillar VC and Susa Ventures, two exceptional early-stage funds who backed us at founding, along with Striker Venture Partners, Hawktail VC, Olive VC, and a host of exceptional angels that includes famous AI researchers, the CEOs of multiple frontier AI labs, and leadership of major biotech and pharma companies.
133
163
48
1,529
246,562
Postdoc fellowship applications at @FutureHouseSF are open again! This is a great way to learn how to apply ML and AI agents to problems in biology and chemistry. You'll get a competitive stipend and work with a great team (including resident AI agent wizard @GWellawatte)!
4
32
2
168
19,562
At Edison Scientific, we build agents for scientific discovery. Training these agents often requires scaling to 1000s of simultaneous environments, for which we rely on @nvidia's recently announced NeMo Gym and RL frameworks. Read more about the integration with Aviary
2
26
3
92
29,010
Conor Igoe retweeted
Interested in efficiently learning policies for Bayesian optimization and other BED problems using reinforcement learning? We are presenting our paper on leveraging equivariance structures in BED problems using GNNs at #NeurIPS2025 this week! Joint work with @cvi94 and Jeff Schneider @CMU_Robotics @mldcmu 📍 Dec 4, 4:30 PM–7:30 PM PST at Exhibit Hall C #605 Send me a DM if you are at NeurIPS and would like to grab coffee to chat about reinforcement learning, Bayesian optimization, or decision-making in general!
2
10
569
Today, we’re pushing a major update to Edison Analysis, our data analysis agent, which is tuned for scientific research and SOTA across data analysis benchmarks. In contrast to Kosmos, which runs for 6-12 hours and produces tens of thousands of lines of code, Edison Analysis runs for seconds to minutes and is best for specific, well-defined computational tasks. It is available both on our platform under the Analysis tab, and via API, and costs only one credit per run, so it is available to users on both free and paid tiers. Edison Analysis is a modified version of the data analysis agent Kosmos uses in its trajectories. Try it out! One of the most important improvements over our previous data analysis agents has been the addition of a specialized data retrieval tool. Edison Analysis can either use this tool to access data, or can pull data down directly via API. To evaluate this tool, we ranked the most commonly used public data repositories across recent papers from BioRxiv, and created a new benchmark that measures the ability of a language agent system to retrieve raw data from those sources. Edison Analysis gets 71% on this benchmark, and we’ll be working to increase this over time. You can read more about our benchmarks in the our blog post, link below. Some features worth highlighting: 1. Edison Analysis produces a report on the analysis it runs, along with a Jupyter notebook that you can download to reproduce the analysis yourself. Every figure it produces is linked back to the specific lines of code used to produce the figure, to make it easy to reproduce. 2. It works well with both Python and R. 3. One of the best uses for Edison Analysis is to use it to retrieve datasets that you can then analyze with Kosmos. We have a bunch of major improvements to Edison Analysis coming in the next few months that we’re excited to share. In the meantime, congratulations to the team, especially @ludomitch, @jonmlaurent, @cvi94 , @alexjandonian, and many more.
53
40
8
206
62,045
Replying to @sama
Thanks!! Anyone who is interested can try Kosmos for themselves here: platform.edisonscientific.co… All possible in large part due to the amazing work you guys have been doing at OpenAI. Keep it up, and the next few years are going to be awesome.
39
76
6
514
160,268
Kosmos is unlike any other agent we have at Edison, both in terms of outputs and infrastructure. Running at scale requires our platform to support order-of-magnitude swings in resource requirements, all unknown at submit time. Each run sees between 0 and 120 sandbox environments with up to 4 TB of memory, between 125 and 3,200 documents parsed, and timing between 1 hour and 32 minutes and 14 hours and 12 minutes. It's like a bad interview question!
3
17
5
72
22,229