Analytical chemist in industry working on materials characterization and data science. Interested in #rstats, modeling, & sustainability. Owner of many pets.https://bsky.app/profile/jameshwade.bsky.socialhttps://bsky.app/profile/jameshwade.bsky.social/post/3mewda7rx4s2cCoding agents can explore codebases. But you can't optimize them, compose them, or put them in a pipeline. RLMs can do all of that. They're DSPy modules, not agents. I built a shiny app to understand how they work.15 Feb 2026 20:01 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3mewda7rx4s2chttps://bsky.app/profile/jameshwade.bsky.social/post/3meepkrrlhc2iI built an R package that turns Shiny apps into UIs that render directly inside Claude Desktop or ChatGPT. It's called shinymcp. Drop-downs, plots, tables all inline in the chat. github.com/jameshwade/shinymcp08 Feb 2026 19:53 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3meepkrrlhc2ihttps://bsky.app/profile/jameshwade.bsky.social/post/3mbueo6ydy22nMy holiday project was building dsprrr, a package for declarative LLM programming in R, inspired by DSPy. The core idea is to treat LLM workflows as programs you can systematically optimize, not prompt strings you tweak by hand.07 Jan 2026 21:05 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3mbueo6ydy22nhttps://bsky.app/profile/jameshwade.bsky.social/post/3lb6wnoph4s26Jumping on the #rstats "we're so back" train 🚂 Here's two fun (unrelated) things I scrolled upon tonight: 📊 tinyplot - base R plotting system with grouping, legends, facets, and more 👀 https://github.com/grantmcdermott/tinyplot 🔎 openalexR - Clean API access to search OpenAlex https://docs.ropensci.org/openalexR/articles/literature-search.html18 Nov 2024 03:02 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3lb6wnoph4s26https://bsky.app/profile/jameshwade.bsky.social/post/3laamiyh43k2jWorst prank *ever* [contains quote post or other embedded content]06 Nov 2024 01:41 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3laamiyh43k2jhttps://bsky.app/profile/jameshwade.bsky.social/post/3laaf27z6sc2jHaving a hard time focusing on code today. Instead of refreshing news sites, tell me about an R package or function that made your life easier recently? I finally figured out how group_modify() works, and it's been a game-changer for some nested data madness. #rstats #dataBS05 Nov 2024 23:27 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3laaf27z6sc2jhttps://bsky.app/profile/jameshwade.bsky.social/post/3l7op7s7qlc2sIf you’ve been waiting try out LLMs with code, now is the time to do it. [contains quote post or other embedded content]29 Oct 2024 22:42 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3l7op7s7qlc2shttps://bsky.app/profile/jameshwade.bsky.social/post/3l7oez7rhyz2xYou can now build a chatbot in shiny in less than 20 lines of code. shinychat and elmer make this much easier than it was even a month ago. elmer nails LLM abstractions. Go check them out if you haven't already!29 Oct 2024 19:39 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3l7oez7rhyz2xhttps://bsky.app/profile/jameshwade.bsky.social/post/3l7o77injbc23I had fun giving a talk at #rpharma about how to integrate AI into your shiny apps. You can check out my talk here: jameshwade.github.io/r-pharma-talk/29 Oct 2024 17:55 +0000at://did:plc:4o2dkjtccxe6wowsmug5v4fa/app.bsky.feed.post/3l7o77injbc23