Biology’s Bitter Lesson - Basecamp Research BCR

Your privacy is important to us. It is Basecamp Research’s policy to respect your privacy and comply with any applicable law and regulation regarding any personal information we may collect about you, including across our website, https://basecamp-research.com, and other sites we own and operate.

Personal information is any information about you which can be used to identify you. This includes information about you as a person (such as name, address, and date of birth), your devices, payment details, and even information about how you use a website or online service.In the event our site contains links to third-party sites and services, please be aware that those sites and services have their own privacy policies. After following a link to any third-party content, you should read their posted privacy policy information about how they collect and use personal information. This Privacy Policy does not apply to any of your activities after you leave our site.

This policy is effective as of 27 September 2022

Last updated: 27 September 2022

Information We Collect
‍
Information we collect falls into one of two categories: ‘voluntarily provided’ information and ‘automatically collected’ information.

‘Voluntarily provided’ information refers to any information you knowingly and actively provide us when using or participating in any of our services and promotions.
‘Automatically collected’ information refers to any information automatically sent by your devices in the course of accessing our products and services.

Log Data
‍
When you visit our website, our servers may automatically log the standard data provided by your web browser. It may include your device’s Internet Protocol (IP) address, your browser type and version, the pages you visit, the time and date of your visit, the time spent on each page, and other details about your visit.

Additionally, if you encounter certain errors while using the site, we may automatically collect data about the error and the circumstances surrounding its occurrence. This data may include technical details about your device, what you were trying to do when the error happened, and other technical information relating to the problem. You may or may not receive notice of such errors, even in the moment they occur, that they have occurred, or what the nature of the error is.

Please be aware that while this information may not be personally identifying by itself, it may be possible to combine it with other data to personally identify individual persons.

Collection and Use of Information
‍
We may collect personal information from you when you do any of the following on our website:
‍
* Use a mobile device or web browser to access our content
* Contact us via email, social media, or on any similar technologies
* When you mention us on social media

We may combine voluntarily provided and automatically collected personal information with general information or research data we receive from other trusted sources. For example, our marketing and market research activities may uncover data and insights, which we may combine with information about how visitors use our site to improve our site and your experience on it.

Security of Your Personal Information
‍
When we collect and process personal information, and while we retain this information, we will protect it within commercially acceptable means to prevent loss and theft, as well as unauthorised access, disclosure, copying, use or modification.

Although we will do our best to protect the personal information you provide to us, we advise that no method of electronic transmission or storage is 100% secure and no one can guarantee absolute data security.

You are responsible for selecting any password and its overall security strength, ensuring the security of your own information within the bounds of our services. For example, ensuring you do not make your personal information publicly available via our platform.

How Long We Keep Your Personal Information

We keep your personal information only for as long as we need to. This time period may depend on what we are using your information for, in accordance with this privacy policy. For example, if you have provided us with personal information such as an email address when contacting us about a specific enquiry, we may retain this information for the duration of your enquiry remaining open as well as for our own records so we may effectively address similar enquiries in future. If your personal information is no longer required for this purpose, we will delete it or make it anonymous by removing all details that identify you.

However, if necessary, we may retain your personal information for our compliance with a legal, accounting, or reporting obligation or for archiving purposes in the public interest, scientific, or historical research purposes or statistical purposes.

Children’s Privacy

We do not aim any of our products or services directly at children under the age of 13 and we do not knowingly collect personal information about children under 13.

Your Rights and Controlling Your Personal Information

‍Your choice: By providing personal information to us, you understand we will collect, hold, use, and disclose your personal information in accordance with this privacy policy. You do not have to provide personal information to us, however, if you do not, it may affect your use of our website or the products and/or services offered on or through it.

‍Information from third parties: If we receive personal information about you from a third party, we will protect it as set out in this privacy policy. If you are a third party providing personal information about somebody else, you represent and warrant that you have such person’s consent to provide the personal information to us.

‍Marketing permission: If you have previously agreed to us using your personal information for direct marketing purposes, you may change your mind at any time by contacting us using the details below.

‍Access: You may request details of the personal information that we hold about you.

‍Correction: If you believe that any information we hold about you is inaccurate, out of date, incomplete, irrelevant, or misleading, please contact us using the details provided in this privacy policy. We will take reasonable steps to correct any information found to be inaccurate, incomplete, misleading, or out of date.

‍Non-discrimination: We will not discriminate against you for exercising any of your rights over your personal information. Unless your personal information is required to provide you with a particular service or offer (for example providing user support), we will not deny you goods or services and/or charge you different prices or rates for goods or services, including through granting discounts or other benefits, or imposing penalties, or provide you with a different level or quality of goods or services.

‍Notification of data breaches: We will comply with laws applicable to us in respect of any data breach.

‍Complaints: If you believe that we have breached a relevant data protection law and wish to make a complaint, please contact us using the details below and provide us with full details of the alleged breach. We will promptly investigate your complaint and respond to you, in writing, setting out the outcome of our investigation and the steps we will take to deal with your complaint. You also have the right to contact a regulatory body or data protection authority in relation to your complaint.

‍Unsubscribe: To unsubscribe from our email database or opt-out of communications (including marketing communications), please contact us using the details provided in this privacy policy, or opt-out using the opt-out facilities provided in the communication. We may need to request specific information from you to help us confirm your identity.

Use of Cookies

We use ‘cookies’ to collect information about you and your activity across our site. A cookie is a small piece of data that our website stores on your computer, and accesses each time you visit, so we can understand how you use our site. This helps us serve you content based on preferences you have specified.

Please refer to our Cookie Policy for more information.

Business Transfers

If we or our assets are acquired, or in the unlikely event that we go out of business or enter bankruptcy, we would include data, including your personal information, among the assets transferred to any parties who acquire us. You acknowledge that such transfers may occur, and that any parties who acquire us may, to the extent permitted by applicable law, continue to use your personal information according to this policy, which they will be required to assume as it is the basis for any ownership or use rights we have over such information.

Limits of Our Policy

Our website may link to external sites that are not operated by us. Please be aware that we have no control over the content and policies of those sites, and cannot accept responsibility or liability for their respective privacy practices.

Changes to This Policy

At our discretion, we may change our privacy policy to reflect updates to our business processes, current acceptable practices, or legislative or regulatory changes. If we decide to change this privacy policy, we will post the changes here at the same link by which you are accessing this privacy policy.

If required by law, we will get your permission or give you the opportunity to opt in to or opt out of, as applicable, any new uses of your personal information.

Contact Us

For any questions or concerns regarding your privacy, you may contact us using the following details:
legal@basecamp-research.com

HomeOur DataFoundation ModelsTherapeuticsContact Us

Biology's bitter lesson

PROGRESS TOWARDS programmable medicine will ultimately be driven by large, general models computing over vast quantities of novel biological information, not by the specialist models and expert heuristics that have defined the field so far.

Just as language models learn from the internet, Basecamp’s EDEN models learn from BaseData, the largest, fastest-growing and most information-rich biological dataset ever built. That foundation gives EDEN an incredible understanding of how life works, and makes it the first model able to translate directly from disease biology to therapeutic candidates. EDEN works across a wide range of modalities and diseases, and works zero-shot in living systems.

To mark the release of the BioNeMo Agent Toolkit, NVIDIA’s open platform that turns any AI agent into an autonomous life sciences scientist, we show how frontier biological models and frontier agentic capabilities, together, open a path to a world where programmable medicine is accessible to all.

The path to designing medicine with machines

The Bitter Lesson is one of the hardest won lessons in AI. Wherever there has been a breakout success, the winning approach has not been the one with the most human expertise built in, but the one able to absorb the most information and compute at the largest scale. Think of the face unlock on your phone: the early vision systems were hand built to recognise a face by measuring the eyes, nose and jaw, and they lost to models that simply looked at millions of photos. Speech systems with detailed linguistic rules lost the same way, to models trained on more data. Time and again, as computer scientist Richard Sutton observed, carefully built human priors have proven to be a ceiling, and removing them has been rewarded with rapid improvement.

Biology has been slow to accept this. Computational biology still runs on heavy expert input, structural assumptions and painstaking optimisation target by target: thousands of specialist models, each built for a narrow task, almost all trained on the same narrow public data, skewed towards the handful of organisms studied first.

The instinct to compress the problem space is understandable, but it runs against everything we know about biology and disease. Biology is non-random, logical and fundamentally learnable, yet the information space is staggering. It is reasonable to think humanity has seen less than a trillionth of a trillionth of the DNA on Earth.

Human disease is where this matters most, and where it is least forgiving. Disease is hyper-personalised and it moves fast. It is rarely a single thing, but a population of cells, each defined by the presence of something that should not be there, or the absence of something that should. Its limit case is a single patient: one genome, one tumour, one history - an experiment that runs exactly once and never repeats. You cannot gather a million examples of the person in front of you, and you never will.

If the data that matters is capped at a single patient, the only variable left to grow is the prior - the understanding the model brings before it ever sees that patient. This is not a constraint peculiar to biology; it is exactly the lesson the language models have just taught. A model with a large enough prior no longer needs many examples to perform a task, only one to locate it: where adapting a language model once took thousands of labelled cases, models are now at a scale where they understand language sufficiently to work from a single example. That is the bitter lesson in its newest form - scale of prior is what makes one example enough. Personalised medicine, steered in the limit by a single patient record, is only ever going to be possible with a large enough prior understanding.

Much is still to be learned on the way there. But the lessons from every other domain tell us the same thing: reaching that level of general intelligence will take orders of magnitude more biological information than we have today.

At Basecamp, we see three barriers to progress in general biological AI: the lack of diverse, ground truth biological information; the lack of models large and general enough to compute over it; and the difficulty of communicating with models that big. With the Trillion Gene Atlas, we are breaking down the first. With EDEN, the second. Here we show how pairing EDEN's frontier biological capabilities with frontier agentic capabilities gives us a new level of control over the design of medicine.

At Basecamp, our strategy has three parts. The first focus is on information - the bitter lesson’s promise is empty when the corpus is small and repetitive. The second part is computation: models large and general enough to learn from all of it. The third part is communication, and here the bitter lesson turns on our own pipelines. For all of biology’s history, using a model has meant a researcher translating the question into code, stitching tools together, and supplying detailed, hand-built input at every step - the same expert scaffolding the Bitter Lesson warns against, simply moved up a level. The ultimate goal should be to remove it: to reach the point where the problem is stated in plain language - a person is ill, in this particular way - and the model reasons its own way to an answer, without a human laying the path.

The coming era of agentic science will deliver a dramatic acceleration in discovery across biology, chemistry, genomics and medicine. At Basecamp, we are driving that change.

1. Information: One trillion genes in the largest biological dataset on Earth

Evolution has been optimising biological code for four billion years, yet almost all of life on Earth remains unobserved, incomplete, or stripped of context. The Bitter Lesson tells us to compute over ever more information, but that premise breaks down when the available corpus is small and repetitive. The information you need is simply not there.

This is the challenge we take on at Basecamp. We have built a global data supply chain that makes scale possible: physical, continuous, partnership driven exploration reaching every corner of planet Earth.

The resulting dataset, BaseData, is a new foundational dataset for biology. Today it holds over 10 billion genes from more than 1 million species new to science, more than a trillion proprietary nucleotide tokens, assembled from more than 30 countries across six continents. It is the largest, most diverse dataset of its kind, and, to our knowledge, the only one ever built with consent agreements tied to every token.

Scale alone is not the whole story. In BaseData, each sequence comes with the genomic and ecological neighbourhood it evolved in, captured at a signal to noise ratio that lets a model learn how biology actually works, rather than how it looks in isolation.

That belief underpins our next step: scaling BaseData by another 100x to the Trillion Gene Atlas, a landmark initiative to assemble over a quadrillion tokens of DNA — making it one of the largest AI training datasets ever assembled, in any field — and model the genomes of more than 100 million new species. Built with Anthropic, Ultima Genomics, and PacBio on NVIDIA infrastructure, it is the data foundation the Bitter Lesson calls for.

2. Computation > EDEN: Where disease prompts the cure

With BaseData beginning to close biology's information gap, we set out to test a simple but radical idea. Could a single model, trained only on evolutionary data and never on a human cell, a clinical record or any task specific label, learn the rules of biology well enough to design real therapeutics on demand, in response to disease biology alone?

In January, in collaboration with NVIDIA, Microsoft and other leading labs, we published the first EDEN model: a metagenomic foundation model with 28 billion parameters. From that one architecture, EDEN already designs across modalities that have almost nothing in common, at scales spanning a single binding site to an entire microbial community: programmable gene insertion, antimicrobial peptides active against priority pathogens, and synthetic microbiomes at gigabase scale. Each of those came from the same model, not a fleet of specialised ones. A general model trained on enough of biology can beat the purpose built specialist at its own task, the way a general language model came to write better than systems hand built for a single kind of text.

That generality was bought through scale, of both information and compute. Using NVIDIA BioNeMo, NVIDIA MegatronLM, and NVIDIA accelerated computing infrastructure, we trained EDEN on one of the largest collections of evolutionary genomic data ever assembled, and we found that scaling laws govern biological models the way they govern language models. In 2020, OpenAI and others showed that model performance follows predictable power law scaling in parameters, data and compute. The same holds in biology: across orders of magnitude in scale, EDEN's loss falls as a clean power law in compute, and the 28 billion parameter run lands within a few percent of the extrapolation from far smaller models.

The antimicrobial work, aimed at antibiotic resistance, shows what that means in practice. EDEN designed peptides against pathogens on the WHO priority list, the multidrug resistant organisms running out of treatments. In our work with Cesar de la Fuente-Nunez at the University of Pennsylvania, 97% showed micromolar activity in vitro, and the majority of those cleared human cytotoxicity testing. A lead candidate then matched a last line antibiotic in a mouse model, with no optimisation, structure prediction or binding experiments along the way.

EDEN designed it, we tested it, and it performed in a living animal at the level of a drug of last resort. Drug discovery has always meant iterative screening, which scales linearly against a disease biology that scales combinatorially. Here, a model trained on evolutionary genomic data produced a candidate that worked directly in vivo. That is the line between a promising screen and a real path to the clinic.

3. Communication: Putting the model in the room

Information and computation give you a model that has learned biology. They do not, on their own, give a researcher, a clinician, or ultimately a patient, a simple way to use it. A model that can design a recombinase from a 30 base pair prompt, or dial in a peptide against a resistant isolate, is only as useful as someone's ability to put the right question to it, read what comes back, and decide the next step. For most of biology's history, that translation layer has been a researcher writing bespoke code for one model at a time. The agentic era is removing that bottleneck.

This is where our work meets NVIDIA’s vision for agentic life sciences. As datasets keep growing and biological models and scientific agents keep improving, the leap from a patient-specific question to an effective therapeutic candidate stops feeling like science fiction.

The wet lab still matters, though its role is shifting. It is becoming the place where we validate what the model designed, not the place where we discover by brute force. You cannot pipette your way to a general understanding of biology. You can, and must, confirm in the lab what a model trained on four billion years of evolution proposes.

The three parts compound

The Bitter Lesson was, in the end, a lesson in humility: the admission that the world is more complex than our theories of it, and that progress comes from confronting that complexity rather than compressing it away. At Basecamp, we approach Mother Nature with the same humility. We do not presume to know the rules of life. We do the hard work of uncovering them, sequencing the unsequenced, sampling the unsampled, reading four billion years of evolution as the most sophisticated body of design the world has ever produced. We believe that if we listen closely enough, biology will teach us how to design medicine.

We have yet to find the limits, and we do not know whether a trillion genes will be enough for everything we have set our sights on. What we do know is that every time we have increased the evolutionary information available to these models, they have become more capable. The answer is not any one of these parts alone but their combination: BaseData for the information, EDEN to compute over it, and frontier agentic capabilities to put these models in the hands of all.

We believe that this is the path to medicines that are designed rather than discovered: programmable enough to target a specific disease mechanism, personalised enough to fit a specific patient, and curative rather than merely managing symptoms for life. The mice that responded to an EDEN designed peptide is one early step on that path.

Contact Us

We collaborate with the top teams across biopharma and are building biodiversity partnerships across the globe. Reach out - we'd love to hear from you.

Looking to join the team? Click here

Privacy Policy