Codex CLI is fast. Claude Code is thoughtful. Codex wins on speed and cost. Claude wins on judgment. What stood out to me is that Claude Code better understands the project as a whole: the files, the context, and what I actually want done.

I’m giving a seminar on 20th April about refactoring crsu.shinyapps.io/MetaInsight/ to use {shinyscholar}, producing crsu.shinyapps.io/MetaInsight_... Details and sign up: www.eventbrite.co.uk/e/crsu-webin... A shorter version is also coming to R/Medicine in May #rstats #metaanalysis #openscience

Vibe Writing: how I co-write with Claude Code, one sentence at a time. It’s not “AI, write my paper.” It’s me thinking out loud while AI handles the mechanics. I direct. AI drafts. I said, “move this to methods” → Claude saw it was already covered there and cut the redundancy.

OmicClaw: executable and reproducible natural-language multi-omics analysis over the unified OmicVerse ecosystem. www.biorxiv.org/content/10.6... 🧬💻🧪 github.com/Starlitnight...

The new GPT-5.4 Mini is slightly less intelligent but faster and costs only 30% of GPT-5.4 and 15% of Opus 4.6. It would be great for many applications. This also makes running local models hard to justify solely on economic grounds. openai.com/index/introd...

OpenClaw is impressive, but you can build a more transparent AI agent with just Claude Code and Bash. Roman's video shows how to create custom agents for real-world workflows, like getting an email summary at 9 a.m. or managing email via Telegram. What clicked for me:

--dangerously-skip-permissions in Claude Code worked fine for months — until today. Claude wiped all the scripts in one of my subfolders, and I hadn’t committed several hours of work yet. Lessons: Commit often. Use YOLO mode with caution.

Good news: Claude Code can run complex data analyses on its own for hours. Bad news: it makes many decisions quietly along the way. Hard-coded parameters, filtering choices, and assumptions. Most are fine, but a single bad parameter can derail the entire workflow.

I'm wondering if the reason many people are so keen on this "science through repeated prompts" idea is because that's already how they operate with their students (or, outside of academia, their team). Try this vague idea. Try again. Come back next week after trying more. Make this into a paper.

Today we're releasing AI for RStudio. It's really, really good—I'd encourage you to point it at the messiest data sources you have and see what it can do. www.simonpcouch.com/blog/2026-03...

Agentic AI and the rise of in silico team science in biomedical research www.nature.com/articles/s41... 🧬💻🧪 rdcu.be/e5HDu Looking forward to reading this one from @moorejh.bsky.social lab and colleagues 👀

The best AI coding tool in the world now has a free course. Not $500. Not $99. Free. Resources have never been more abundant. It's the will to learn that has never been more rare. Stop scrolling. Start building → anthropic.skilljar.com/claude-code...

1/ RNA‑seq batch effects are one of the easiest ways to fool yourself in genomics. They can create beautiful, completely wrong biology if you’re not careful.

My weekly newsletter is out! This week's agenda: 🔹 Open Source of the Week - The DuckLack R project by Travis Gerke, ScD 🔹 New learning resources 🔹Book of the week - Time Series Forecasting in Python by Marco Peixeiro ramikrispin.substack.com/p/time-serie... #rstats #python #ai #datascience

In many R courses, data are clean & everything just works. But real life is messy—and that’s where problems start 👉 Our course with @cecibaldoni.bsky.social -Dealing with Messy Data in R in April: clean, join & visualise real datasets with tidyverse & ggplot2 💻📊 shorturl.at/zdmht #Rstats #MessyData

A human pan-disease blood atlas of the circulating proteome | Science www.science.org/doi/10.1126...

ragnar 0.3.0 is now on CRAN! 🚀 An R toolkit for RAG from your docs: faster ingestion, better retrieval, Azure OpenAI + Snowflake embeddings, and MCP serving. tidyverse.org/blog/2026/01... #rstats #rag #ai

TIL: Before Hans Asperger or Leo Kanner, a Jewish-Ukrainian psychiatrist named Grunya Sukhareva defined autism in 1925. Both men did not cite her work. She also had documented how it affected women and girls, where the men did not. en.wikipedia.org/wiki/Grunya_...

My weekly newsletter is out! ramikrispin.substack.com/p/issue-67-t... #python #ai #llm

Excited to share "Claude Code for Everyone"—a set of step-by-step, hands-on tutorials to help you put AI to work on your laptop. It isn’t just an AI coding tool for developers; it is a powerful local AI agent to support research, writing, editing, and more. Check it out: gexijin.github.io/vibe/

Claude Code for Everyone The following tutorial by Prof. Steven Ge (@stevenge.bsky.social ) provides a step-by-step guide for setting up and working with Claude Code. This includes different routes by OS (Mac and Windows) and programming languages ( #Rstats and #Python). gexijin.github.io/vibe/

80-mer DNA aptamer as a selective marker for #Senescence Targeting EDA-Fibronectin Kd 500~1000 pM Label senescent cells in naturally aged🐭🫁 Aptamer binding ⬇️in 21-mo INK-ATTAC🐭 with p16 cells eliminated #Aging_Cell 2025 onlinelibrary.wiley.com/doi/10.1111/...

Excited to share "Claude Code for Everyone"—a set of step-by-step, hands-on tutorials to help you put AI to work on your laptop. It isn’t just an AI coding tool for developers; it is a powerful local AI agent to support research, writing, editing, and more. Check it out: gexijin.github.io/vibe/

Claude Code is more than coding. To prove it: here’s how I built ~100 tutorials in about a week by packaging my workflow into slash commands (reusable prompts)—write, review, and translate. It automates workflows. How I did it: gexijin.github.io/vibe/Buildin... Tutorials: gexijin.github.io/vibe/

To be effective, data science agents need to be able to read plots reliably. @sara-altman.bsky.social and I wrote about some concerning findings on LLMs' ability to interpret plots when the content contradicts their expectations on the @posit.co blog. posit.co/blog/introdu...

This is my R development setup — built on VS Code and running both Claude Code and OpenAI’s Codex inside a Docker container. It also supports Shiny apps and has been working great for me. I am on Windows. These coding agents were initially designed for Linux, I think. github.com/gexijin/vibe

The data is searchable on this site that the Renthal lab put together (thanks to Shams in Will's lab for leading this): painseq.shinyapps.io/u19humandrga...

New iDEP feature: instantly annotate k-means clusters with enriched pathways. Fewer clicks, better insights. Explore your data! Give it a spin on your RNA-seq data: bioinformatics.sdstate.edu/idep/

GitHub Copilot Chat in Positron Assistant 🤖 Positron Assistant now supports GitHub Copilot for both completions and chat! Add GitHub Copilot as a model provider for access to its models, chat participants, and tools. Learn more: positron.posit.co/assistant

I put out a patch release of mirai today. Version 2.5.2 really improves the OpenTelemetry integration so you can more easily see into your async workflows. Other key ecosystem packages will roll out with this enabled - next up: Shiny! mirai.r-lib.org #Rstats

In this video, I show how to use iDEP to interpret bulk RNA-seq data. Start with QC plots and exploratory analyses before identifying differentially exp. genes and pathways. We picked up on high mitochondrial rRNA counts, one male mixed in with 7 female mice. www.youtube.com/watch?v=ta1o...

I kicked off a new newsletter focused on time series analysis and forecasting. My goal is to use it as both a framework and motivation to write my upcoming books on time series and forecasting. If you are interested, please sign up here: theforecaster.substack.com #timeseries #rstats #python

The Department of Statistics at the University of Nebraska–Lincoln is under threat of closure, with tenured faculty facing dismissal. This is a small but globally impactful department. Please consider writing a letter of support. Your voice could make a real difference.

5 tools to visualize genomic datasets 🧵 1. Karyoploter bernatgel.github.io/karyoploter...

I had a 26GB TSV file. R choked. So I turned to UNIX. And it worked. 1/ You only need 500 columns. But the file is 26GB. R freezes. Memory bleeds. You need the data—but you don’t need the pain. Here’s what I did.

My weekly newsletter is out! ramikrispin.substack.com/p/the-cagent...

My weekly newsletter is out! ramikrispin.substack.com/p/the-snakem... #llm #ai #python

My Docker Model Runner tutorial is also available on Medium (for paid subscribers). Alternatively, for non-subscribers, it is open in my newsletter. medium.com/data-science... AIOps newsletter: theaiops.substack.com #ai #docker #datascience

Understand NGS sequencing files bioinf.comav.upv.es/courses/seq...

My weekly newsletter is out! This week: 🔹 Open Source of the Week - The PandasAI project 🔹 New learning resources 🔹 Book of the week - Learning SQL by Alan Beaulieu 📌 Join 30k subscribers and subscribe for weekly updates. ramikrispin.substack.com/p/the-pandas... #ai #python #datascience #sql

Hello #dataBS (& especially #TidyTuesday) fam! I'm trying to organize a thing to help me keep TidyTuesday running smoothly, but first I need to get a bit of a runway. Every week I curate a TT dataset, and it's wearing me down. Please see github.com/rfordatascie... for some ways you can help! #RStats

Life-saving idea! Pass it on!

My weekly newsletter is out! This week's agenda: 🛠️ The social-media-kit project 📝 New learning resources 📚Book of the week - Models Demystified by Michael Clark and Seth Berry 📌 Join 30k subscribers and subscribe for weekly updates. ramikrispin.substack.com/p/new-book-m... #datascience #ai

I NEED to tell you the story of Tae Heung “William” Kim. He's a graduate student at Texas A&M where he's working on a vaccine for Lyme disease. He's a *legal permanent resident* of the United States. And he's been in ICE detention for 12 days & counting, transferred Tuesday to South Texas.

I will present on AI-powered data science platforms on Monday, July 21, at 11 am EST at the Univ of Virginia. Zoom link: kohl.aaec.vt.edu/events/data-...

Orbital - new OSS from Posit, looks super practical application for ML pipelines 👇🏼 posit.co/blog/introdu... #python #rstats #datascience

New blog post: @posit.co Positron Assistant provides inline completions with GitHub Copilot and chat/agent using Claude 4 Sonnet. Demo: using agent mode to create an #Rstats package with Roxygen2 docs and testthat unit tests. doi.org/10.59350/gkj...

🚨 BREAKING 🚨 The National Science Foundation has sent an email out to its members to collect signatures for a dissent declaration similar to the NIH’s Bethesda Declaration and the EPA’s Declaration of Dissent. This comes on the heels of Lee Zeldin putting 139 EPA declaration signers on admin leave

Mayor Brandon Scott has reduced crime in Baltimore by 62%, and now has the lowest homicide rate in Baltimore history. How did he do it? NOT be spending more on police. He did it by MAJOR investment in afterschool and literacy programs. Socialism works