2 years ago I went to bed feeling great, woke up next morning with a painful ear and hearing loss (which became permanent). Because of a shingles infection in my auditory nerve. Get the vaccine if you're eligible www.wired.com/story/shingl...
So instead of choosing one, combine them: Claude Code for direction, Codex for execution.
That feels like the most practical AI coding workflow right now.
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.
Poster for the seminar: MetaInsight v7: Making a comprehensive app for network meta analysis reproducible
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
The whole session took minutes, instead of hours.
Vibe writing isn’t letting AI write your paper.
It’s writing with a tireless partner.
I use Claude Code in VS Code paired with Obsidian to write manually with Grammarly. All markdown files.
AI as a sounding board.
“Should I discuss covariates here?” → Claude suggested adding a sentence.
I edit. AI checks.
"Go through my edits" → Claude caught a typo and a tense mismatch.
AI reviews for readability.
“Review this paragraph for flow and readability.”
I flag the problem. AI diagnoses it.
“The flow isn’t working” → Claude identified the issue, gave options, and I chose one.
I shape the argument. AI executes.
“Discuss comorbidity first” → “Then post-mortem” → “Add references” → “Mention GTEx wasn’t designed for disease” → “Condense”
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...
• You can even replace Claude Code’s system prompt
• Commands, skills, and subagents are, at their core, reusable prompts
That’s the direction I’m most excited about: agentic workflows that are simple, inspectable, and truly yours.
• 'claude -p' lets you run Claude Code as a headless command
• It can be triggered by schedulers like cron or by other events
• 'claude -p -r' helps preserve context across sessions
youtu.be/ODKMmKCgrvw?...
#AI #ClaudeCode #CodingAgents #Automation #BuildInPublic
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.
Even the best LLMs are smart MOST of the time. For scientific research and mission-critical decisions, that's not enough.
We need to supervise:
1. Plan thoroughly and iterate. Have it explain the core logic, then refine the plan with feedback.
2. Inspect the code. Have it list all hard-coded values and key decisions, then review the implementation carefully.
3. Verify what the data looks like at each stage.
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.
A screenshot of an RStudio window. On the left-hand side is a new pain called Posit Assistant. The Posit Assistant had recently run code making a lat-lon plot of Washington state, colored by whether the point had been marked as forested or not.
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...
Thanks Carlo! The students were great!
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_...
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/
