Steven Ge @stevenge.bsky.social · 28/09/2026- The greatest waste isn’t lack of ability, but waiting for a future self. - The brain favors comfort now over rewards later. - Tiny actions break the cycle and build self-trust. I learned these from a video titled "How 90% of People Waste Their Lives", .... while doomscrolling in bed. 010
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 12/09/2026News! My next book is coming. For 3 years I posted daily on the bioinformatics few teach you — the judgment, the traps, the sanity checks. 131
Reposted by Steven GeMichael Love @mikelove.bsky.social · 12/09/2026I wrote a post about how slice_sample() and other slice_* functions work in #tidyomics #Bioconductor tidyomics.github.io/tidyomicsBlo...tidyomics.github.ioSlicing in tidyomics – tidyomicsBlogHow to use dplyr-style slice operations on omics data objects in the tidyomics project. 02213
Steven Ge @stevenge.bsky.social · 09/09/2026I just received 4 free Claude subscriptions for my students via Claude Science. I paid $15 for a premium seat with 5x usage for myself. Must be a PI. Maybe they will be harvesting our data for their own science projects? You can't really trust these guys. www.anthropic.com/news/expandi...anthropic.comExpanding our support for scientistsAnthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems. 030
Steven Ge @stevenge.bsky.social · 21/07/2026For bioinformatics coding, use Codex with gpt-5.6-sol. Beats Claude Code with Opus 4.8 by a long shot. Fable 5 won't even look at anything remotely related to biology. 020
Steven Ge @stevenge.bsky.social · 13/07/2026- Lower the effort setting. Use maximum effort only when it requires deep reasoning. Powerful models are naturally thorough. Make them earn every token. 010
Steven Ge @stevenge.bsky.social · 13/07/2026Regenerate responses strategically. DON'T keep on chatting!!! - Minimize output tokens—they cost 5× more. Ask for only the diff or revised section, not the entire script or document. - Ask for brevity. I often add “Be brief” or “Use bullets” to my prompts. 100
Steven Ge @stevenge.bsky.social · 13/07/2026My 5 strategies for saving tokens—especially with Claude Fable 5: - Use Claude.ai for bounded tasks. Use Claude Code only when it needs to inspect files, edit a repo, run commands, or test its work. - Control the context. Start a new chat when switching tasks. Edit a prompt instead of piling on. 110
Steven Ge @stevenge.bsky.social · 12/07/2026Fable 5 extended again to 7/19. Thank you, Anthropic, for motivating me! I needed deadlines in the summer! 😀 000
Steven Ge @stevenge.bsky.social · 09/07/2026“Explain briefly in plain language, using bullet points.” I’ve been saying this to LLMs a lot recently. These models have become incredibly powerful. But their answers are often long, technical, and overly detailed. Sometimes I simply don’t have the time, patience, or knowledge to read. 000
Steven Ge @stevenge.bsky.social · 09/07/2026I still upload key files to the Claude or ChatGPT websites to get a fresh perspective. Claude Code or Codex can be influenced by what's in the local project folder. CLAUDE.md, AGENTS.md, and project memory files are helpful but could also prime AI. The web offer a fresh, controlled context. 000
Reposted by Steven GeAriaa® @ariaa.bsky.social · 05/07/2026Supposedly the most intelligent of all species...humans. 61125843917
Steven Ge @stevenge.bsky.social · 24/06/2026Don't worry about not keeping up with AI. Nobody is. Identify and solve a problem! Even last year's AI is underutilized! For scientists, discover something new. Or create a tool that helps others. 111
Reposted by Steven GeLeo Hickman @leohickman.carbonbrief.org · 22/06/2026After 18 months of R&D with a team of specialist academics, I'm VERY excited to say that @carbonbrief.org has just launched 'Project Cosmos'... ...the world's largest database of climate research Our hope is this becomes a major new resource interactive.carbonbrief.org/cosmos/index...interactive.carbonbrief.orgProject Cosmos – the world’s largest database of climate change research 8296126
Reposted by Steven GeAalia Mauro @aaliamauro.bsky.social · 22/06/2026On June 5th Israel attacked the home of Lebanese sea turtle conservationist Mona Khalil. Mona was hospitalized with burns and injuries to over 70% of her body. Yesterday, June 19th, Mona died from her injuries. This wasn’t an accident. 35443245
Reposted by Steven Gedavidegardner.bsky.social @davidegardner.bsky.social · 21/06/2026Today's "From the Files" 06-21-26: Mountain Shack. Silverton, CO. 2025 #davidgardnerphotography #liightight #landscape #vertical #grandturkpeak #fall #mountain #structure #shack #fallcolor #aspen 632129
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 20/06/20261/ Many genomics mistakes are hard to catch in the code. They’re in the data you never looked at. Genome browsers can change that. Here’s how. 142
Steven Ge @stevenge.bsky.social · 21/06/2026React is a tool for building interactive web apps that update when users click, search, or filter data. Every dataset deserves a dashboard—especially one you spent years collecting. With AI, you can build one in a few hours. Tutorial: gexijin.github.io/vibe/React_F...gexijin.github.iovibe 010
Steven Ge @stevenge.bsky.social · 21/06/2026Anyone can create data dashboards with AI. Following this tutorial, you can use ChatGPT, React, and VS Code to turn a data file into a simple, interactive dashboard. You do not need to know how to code or understand HTML or JavaScript to get started.gexijin.github.iovibe 122
Steven Ge @stevenge.bsky.social · 21/06/2026More biologists are coding their own analyses. Next: version control. Following this 30-min tutorial, you can learn how to use ChatGPT and GitHub Desktop to build a simple data dashboard. GitHub helps you track changes, collaborate, and share your work. Tutorial: gexijin.github.io/vibe/Git_Bra...gexijin.github.iovibe 022
Reposted by Steven GeTimothy Caulfield @caulfieldtim.bsky.social · 30/05/2026I've been following & researching "precision" medicine / genomics for decades... So much hype. So much underwhelming or narrow applications. This seems genuinely exciting! 👇 Groundbreaking genomic test could spare millions of breast cancer patients chemotherapy www.theguardian.com/society/2026...theguardian.comGroundbreaking genomic test could spare millions of breast cancer patients chemotherapyTrial suggests patients with a low test score could be treated with hormone therapy alone with near-identical outcomes 46432
Reposted by Steven GebioRxiv Microbiology @biorxiv-microbiol.bsky.social · 28/05/2026Ratio Percentile Deviation (RPD): A nonparametric, compositionally robust method for measuring the divergence of a microbial sample from a reference dataset www.biorxiv.org/content/10.64898/20… 062
Reposted by Steven GeDr. Mar @boldnewme.bsky.social · 16/05/2026I love and respect this scientist. Carl Sagan answers a question about creation vs evolution. 36498393322
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 10/05/2026Claude Code shipped /ultrareview and almost nobody is talking about what's actually new about it. It's not "AI reviews your code." We had that. 241
Steven Ge @stevenge.bsky.social · 08/05/2026Confession: I trusted Claude Code too much and moved too fast in my bioinformatics research. AI's execution outpaced my ability to understand. I was prompting & accepting without reading the full responses. The result? Cognitive debt that compounds over time. 000
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 21/04/2026OmicClaw: executable and reproducible natural-language multi-omics analysis over the unified OmicVerse ecosystem www.biorxiv.org/content/10.... 041
Reposted by Steven GeStephen Turner @stephenturner.us · 14/04/20262 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...wired.comYou Should Be More Freaked Out by ShinglesThe viral infection leaves millions with chronic pain, increased stroke risk, and lifelong nerve damage—yet vaccination rates remain dangerously low. 1185
Steven Ge @stevenge.bsky.social · 09/04/2026So instead of choosing one, combine them: Claude Code for direction, Codex for execution. That feels like the most practical AI coding workflow right now. 010
Steven Ge @stevenge.bsky.social · 09/04/2026Codex 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. 110
Reposted by Steven GeSimon Smart @simonsmart.bsky.social · 26/03/2026I’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 002
Steven Ge @stevenge.bsky.social · 22/03/2026The 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. 020
Steven Ge @stevenge.bsky.social · 22/03/2026AI 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.” 110
Steven Ge @stevenge.bsky.social · 22/03/2026I 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” 110
Steven Ge @stevenge.bsky.social · 22/03/2026Vibe 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. 121
Reposted by Steven GeStephen Turner @stephenturner.us · 18/03/2026OmicClaw: executable and reproducible natural-language multi-omics analysis over the unified OmicVerse ecosystem. www.biorxiv.org/content/10.6... 🧬💻🧪 github.com/Starlitnight... 093
Steven Ge @stevenge.bsky.social · 19/03/2026The 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...openai.comIntroducing GPT-5.4 mini and nanoGPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent workloads. 010
Steven Ge @stevenge.bsky.social · 19/03/2026• 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. 030
Steven Ge @stevenge.bsky.social · 19/03/2026• '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 #BuildInPublicyoutu.beI Replaced OpenClaw with Claude Code (It's Not Even Close)YouTube video by Agentic Lab 361
Steven Ge @stevenge.bsky.social · 19/03/2026OpenClaw 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:youtu.beI Replaced OpenClaw with Claude Code (It's Not Even Close)YouTube video by Agentic Lab 350
Steven Ge @stevenge.bsky.social · 17/03/2026--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. 242
Steven Ge @stevenge.bsky.social · 16/03/2026Even the best LLMs are smart MOST of the time. For scientific research and mission-critical decisions, that's not enough. 001
Steven Ge @stevenge.bsky.social · 16/03/2026We 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. 100
Steven Ge @stevenge.bsky.social · 16/03/2026Good 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. 400
Reposted by Steven GeClément Canonne @ccanonne.github.io · 09/03/2026I'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. 2557
Reposted by Steven GeSimon P. Couch @simonpcouch.com · 05/03/2026Today 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... 711431
Reposted by Steven GeStephen Turner @stephenturner.us · 25/02/2026Agentic 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 👀 0102
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 22/02/2026The 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... 0112
Reposted by Steven GeMing Tommy Tang @tommytang.bsky.social · 21/02/20261/ 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. 161
Reposted by Steven GeRami Krispin @ramikrispin.bsky.social · 21/02/2026My 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 #datascienceramikrispin.substack.comTime Series Forecasting in Python, the DuckLack R Library, New Tutorials| Issue 76A weekly curated update on data science and engineering topics and resources. 032
Reposted by Steven GePhysalia-courses@ONLINE @physaliacourses.bsky.social · 14/02/2026In 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 #MessyDataphysalia-courses.orgDealing with messy data in R: data cleaning and visualisation8-10 April 2026 032