Top all-time · #3467
Abhishaike Mahajan
Personal blog · owlposting.com · on HN as abhishaikescienceai
Abhishaike Mahajan writes Owl Posting, a personal blog at owlposting.com about science and ai. Since 2024, 21 different Hacker News readers have linked it 158 times, most often “Reasons to be pessimistic (and optimistic) on the future of biosecurity”. It is still writing: the last post was on 2026-09-21, and you can follow it by feed.
essays about biology and ml, written for and by owls. Click to read Owl Posting, by Abhishaike Mahajan, a Substack publication with tens of thousands of subscribers.
Most-linked posts?
- Reasons to be pessimistic (and optimistic) on the future of biosecurity6 people · 7 mentions · first linked 2026-03-16
- The ML drug discovery startup trying really, really hard to not cheat6 people · 6 mentions · first linked 2025-12-23
- How to build a cancer vaccine, and whether they will work this time5 people · 7 mentions · first linked 2026-06-08
- Creating 'new knobs of control' in biology4 people · 4 mentions · first linked 2026-04-10
- Ask not why would you work in biology, but rather: why wouldn't you?4 people · 4 mentions · first linked 2025-10-03
- Why do drugs work at all?3 people · 6 mentions · first linked 2024-08-09
- What happened to pathology AI companies?3 people · 5 mentions · first linked 2025-04-05
- The unreasonable effectiveness of plasmid sequencing as a service3 people · 4 mentions · first linked 2024-10-07
- There aren't enough smart people in biology doing something boring3 people · 4 mentions · first linked 2024-10-21
- Generative ML in chemistry is bottlenecked by synthesis3 people · 4 mentions · first linked 2024-09-16
What Hacker News says?
Monsieur, if I may offer a vaaaguely similar story on how things may progress https://www.owlposting.com/p/a-body-most-amenable-to-experim...
Comment linking /p/a-body-most-amenable-to-experimentation
on “GPT-5.2”Submitted Endometriosis is an interesting disease as a story · 392 points
HN discussionBy using historic data. You should strictly segregate training and testing data, to be sure that your model has internalised decision-making principles. [0] It is definitionally true that any given moment in history is unprecedented, and that old thinking is invalidated by paradigm shifts. But not every single variable is randomised. The launch of the PC didn't embarrass every executive, for example. 0: https://www.…
Comment linking /p/an-ml-drug-discovery-startup-trying
on “CEO fired developers to make room for AI. Developers create open source AI CEO”Submitted Administering immunotherapy in the morning seems to matter. Why? as a story · 239 points
HN discussionA biology/machine-learning blog! https://www.owlposting.com/ Rediscovering an old love for writing that I thought had left me after highschool, now applied in the field I work in! Recommend starting your own blog if you're on the fence + being consistent about posting, it's extremely worth it
Comment linking /
on “Ask HN: What are you working on (August 2024)?”Submitted A primer on the current state of longevity research as a story · 179 points
HN discussionFor a more technical dive into startups that have been chugging along with AI in pathology for ~decade, check out this: https://www.owlposting.com/p/what-happened-to-pathology-ai-c... > One pathology AI founder told me that it wasn’t hospitals or diagnostic labs that showed the most promise. It was R&D groups within Big Pharma. Those scientists and executives wanted new tooling. They were often sitting on massive in…
Comment linking /p/what-happened-to-pathology-ai-companies
on “The A.I. Radiologist Will Not Be with You Soon”Submitted Mapping the off-target effects of every FDA-approved drug in existence as a story · 162 points
HN discussion+1 to this! I've also written a potentially helpful coverage piece on extracting conformations from cryo-EM data: https://www.owlposting.com/p/a-primer-on-ml-in-cryo-electron...
Comment linking /p/a-primer-on-ml-in-cryo-electron-microscopy
on “A Primer on Molecular Dynamics”Submitted A primer on why microbiome research is hard as a story · 91 points
HN discussionYes, mRNA vaccines are promising for many but not all cancer types, and there are many ongoing clinical trials. There's also a lot we yet don't know about how to design them. Here's a great blog post on this, "How to build a cancer vaccine, and whether they will work this time": https://www.owlposting.com/p/how-to-build-a-cancer-vaccine-a... Here's the blog post I wrote on personalized mRNA vaccines: https://hedonic…
Comment linking /p/how-to-build-a-cancer-vaccine-and
on “Moderna reports first positive Phase 3 for mRNA neoantigen therapy in melanoma”Submitted A Primer on Molecular Dynamics as a story · 90 points
HN discussionApologies, I do kinda auto-repost my articles here without thinking whether they are paywalled (nearly everything I’ve written isn’t) here is an unpaywalled link that anyone can access: https://www.owlposting.com/p/8157b515-56ce-40a4-a7f0-da6d46f... edit: please subscribe if you enjoyed this! lots of really crazy articles + podcasts in this subfield are planned for the upcoming month :) all free!
Comment linking /p/8157b515-56ce-40a4-a7f0-da6d46f928b9
on “A 2026 look at three bio-ML opinions I had in 2024”Submitted RNA structure prediction is hard. How much does that matter? as a story · 70 points
HN discussionSubmitted Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging as a story · 66 points
HN discussionSubmitted There aren't enough smart people in biology doing something boring as a story · 66 points
HN discussionSubmitted Will protein design tools solve the snake antivenom shortage? as a story · 63 points
HN discussionSubmitted Creating the largest protein-protein interaction dataset in the world as a story · 61 points
HN discussionSubmitted The unreasonable effectiveness of plasmid sequencing as a service as a story · 48 points
HN discussionSubmitted Why computational predictive toxicology is hard as a story · 24 points
HN discussionSubmitted The optimistic case for protein foundation model companies as a story · 18 points
HN discussionSubmitted The ML drug discovery startup trying really, really hard to not cheat as a story · 7 points
HN discussionSubmitted Cancer has a surprising amount of detail as a story · 7 points
HN discussionSubmitted We don't know what most microbial genes do. Can genomic language models help? as a story · 6 points
HN discussionSubmitted How do you make a 250x better vaccine at 1/10 the cost? Develop it in India as a story · 6 points
HN discussionSubmitted Reasons to be pessimistic (and optimistic) on the future of biosecurity as a story · 5 points
HN discussionSubmitted How to build a cancer vaccine, and whether they will work this time as a story · 5 points
HN discussionSubmitted Human art in a post-AI world should be strange as a story · 5 points
HN discussionSubmitted Ask not why would you work in biology, but rather: why wouldn't you? as a story · 5 points
HN discussionSubmitted Comments on 'Endometriosis is an interesting disease' as a story · 5 points
HN discussion
