Andrew Severin Bioinformatician and Team Manager AI enthusiast Author of ChatGPT 4 Professors (https://nitter.cf/t.co/0puLGwRVth ) tweets are my own
Iowa State University
Joined October 2011
- Tweets6.7K
- Following413
- Followers1.9K
- Likes1.7K
Andrew Severin retweeted
Searching 32 million records in 30 milliseconds is insane!
@typesense is a crazy fast open-source search engine that supports natural language search. It's like Elasticsearch but much easier to set up, configure, and use.
You can do all of this with Typesense:
• Fuzzy search: Typo-tolerant fuzzy search-as-you-type
• Vector search: Return records that are similar to each other
• Semantic search: Return records that are conceptually related
• Geo Search: Return records that are close to a given lat/long
Typesense's Natural Language Search is pretty cool:
It turns a sentence into a structured search query, then runs it against your data. For example:
The query "Find me a BMW under $40,000, newer than 2020, with the lowest mileage first" will produce the following:
• Filters: brand = BMW, price < 40000, year > 2020
• Sort: mileage ascending
Typesense will then apply these filters and sorting rules to the data.
They offer client libraries in Python, JavaScript, PHP, Ruby, Go, Rust, Swift, .NET, Java, and pretty much any other programming language.
You can start searching in less than a minute:
1. Run their Docker image (or one of their native binaries)
2. Import your data
3. Start searching!
GitHub repository: fandf.co/4ytzmmE
I recorded a quick video to show you a demo. I promise you haven't seen anything this fast!
Thanks to the team for partnering with me on this post.
Andrew Severin retweeted
Trying laptop-free dev for the first time. Works surprisingly well; iPad Pro + blink terminal + mosh + tailscale to my Mac Studio running Claude Code in tmux is a great stack. In hindsight I wish I got the bigger iPad so I’d have a larger keyboard, but oh well. #bonusgreyhoundpic
Andrew Severin retweeted
IMO, the bio storyline buries the lede on a massive change in the economics of science?
It took $3k-$4k of inference costs and 21 hours of AI work to do something that would have taken ~10 weeks of grad work and a total GSR salary cost of ~$9k?
So 80x faster, 2-3x cheaper?
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: anthropic.com/news/claude-di…
Andrew Severin retweeted
The MoTrPAC consortium has been studying the molecular effects of exercise. In a new paper with Conrad Oakes, we take a careful look at their rat dataset, leading to discoveries that highlight the importance of proper bioinformatics & stats. 1/ link.springer.com/article/10…
Andrew Severin retweeted
I know it is a lot for instructors who never asked for AI to change things, but if you teach and have not updated your expectations over the last 6 months over what AI can do (a lot more), its error rate (a lot less), and its ubiquity among your students (near total), you need to
Andrew Severin retweeted
Can modern databases scale scientific analyses beyond RAM?
During my PhD, I explored whether matrix, spatial, and genomic operations could share a database execution layer without changing the APIs scientists rely on.
Today, I’m excited to finally share dbverse, a composable database framework built around that idea.
Across benchmarks, dbverse delivers up to 1,000× speedups and scales end-to-end spatial omics analyses to millions of cells on a 16 GB M4 Mac mini.
Paper: biorxiv.org/content/10.64898…
1/🧵
Andrew Severin retweeted
Models trained using genetic markers + gene expression + phenotypes can be better predicting phenotype solely from genetic markers than models trained using only genetic + phenotype data from the start. Kontolati et al, out two days ago. doi.org/10.1111/tpj.71076
Andrew Severin retweeted
My friend applied to 200 tech jobs in two years. No MIT. No Stanford.
Last month Anthropic offered him $750,000.
I asked him how he broke in from zero.
He sent me the exact video that got him in. Anthropic's 2 hour course on "How to become an AI engineer in 2026"
Their core team shows exactly how to architect & build AI agents from scratch.
I watched it last night.
Halfway through, I realized I could break into an AI lab in weeks, not years.
Bookmark this and read the article below.
• 00:00 - AI agents with graph engineering
• 06:41 - AI agent architecture
• 14:31 - building AI agent loops live
• 1:15:24 - AI agentic RAG
• 2:20:42 - Anthropic interview process
Andrew Severin retweeted
we built pdf-inspector so agents can process PDFs without waiting on OCR. it classifies any PDF in ~20ms and extracts clean markdown locally
→ 200 PDFs processed in 2.8s
→ top quality in extracting tables + graphs
→ built in rust
→ open source
github.com/firecrawl/pdf-ins…
Andrew Severin retweeted
A nice python package for creating Publication-Ready Scientific Plots github.com/faridrashidi/cnsp…
if you use R, take a look at rpkgs.datanovia.com/ggpubr/
Andrew Severin retweeted
I had Fable build another thing I always wanted, a full procedural fantasy kingdom generator with economics, trade routes, population growth, wars, lineages, and occasional dragons. First, I worked with it on a plan, then it made it.
You can play it here: annals-kingdom.netlify.app/
Andrew Severin retweeted
Wait what, Nvidia released cuda-oxide?! An official Rust-to-CUDA compiler?!!
How did I not know about this?! This is so exciting!
Andrew Severin retweeted
Your "hallucination-free" RAG system trusts its retrieval layer.
Researchers just proved that 5 documents, planted in a database of 2.6 million, can hijack the LLM's answer 97% of the time.
The attacker never touches your model. They never see your retriever. They just write a document.
This is PoisonedRAG. 🧵
Andrew Severin retweeted
If you're on NovaSeq calling somatic variants without a matched normal, check for unexpected T>G enrichment before assuming biology.
paper: link.springer.com/article/10…
Andrew Severin retweeted
M5 Max using MLX 🔥
- 3323/121 tps single request
- 4810/550 tps batch 32 requests
Andrew Severin retweeted
Terminal Genome Viewer github.com/zeqianli/tgv
Another one that is around for a while: ASCIIGenome github.com/dariober/ASCIIGen…
Andrew Severin retweeted
Andrej Karpathy wrote something that every Claude Code user has felt but couldn't articulate.
Three quotes. Read them slowly.
"The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."
"They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do."
"They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."
You've seen all three. Probably this week.
Someone turned these three observations into a single CLAUDE[.]md file. Four principles, one install, directly addresses each quote:
1./ Think before coding
Don't assume. Don't hide confusion. State ambiguity explicitly. Present multiple interpretations rather than silently picking one. Push back if a simpler approach exists. Stop and ask rather than guess.
2./ Simplicity first
No features beyond what was asked. No abstractions for single-use code. No "flexibility" that wasn't requested. No error handling for impossible scenarios. The test: would a senior engineer say this is overcomplicated? If yes, rewrite it.
3./ Surgical changes
Don't "improve" adjacent code. Don't refactor things that aren't broken. Match the existing style even if you'd do it differently. If you notice unrelated dead code, mention it, don't delete it. Every changed line should trace directly to the request.
4./ Goal-driven execution
Transform "fix the bug" into "write a test that reproduces it, then make it pass." Transform "add validation" into "write tests for invalid inputs, then make them pass." Give it success criteria and watch it loop until done.
This last one is Karpathy's key insight captured directly: "LLMs are exceptionally good at looping until they meet specific goals... Don't tell it what to do, give it success criteria and watch it go."
It's a single file. Drop it into any project.
Andrew Severin retweeted
AI coding assistants just passed a threshold: domain experts can now rewrite established scientific software in days. 💻 This wave of rewrites is coming for #bioinformatics. The question isn't whether to embrace this capability, but how to do it responsibly.
We've published a set of best-practices principles to try to help people to approach rewrites in the right way.
🌐 Principles: hubs.la/Q04b7NY10
📕 Blog post: hubs.la/Q04b7Mqx0
💻 Contribute: hubs.la/Q04b7Hvr0
Andrew Severin retweeted
Oh wow, you can now build a complete AI data analyst in under a couple of hours!
100% Open-source.
It's a CLI that maps your database schema to context files, so you can use an agent or model to query your data.
All of your data stays on your computer. This is not a SaaS, and you don't need API keys to access it.
No SaaS. No API keys.
