iiinova — where your digital self keeps evolving

Justyna Wojtczak @justi.blue · 23/06/2026

Your chatbot's answer parsed. The JSON was valid. The tests were green. It still promised a refund your policy never offered. Schema validation checks the shape of an answer - not whether it's true. Here's the second LLM layer that catches it, in Ruby 👇

230

Justyna Wojtczak @justi.blue · 19/04/2026

My laptop just told me I have 163 hours invested in a project I forgot existed. that's 163 hours of thinking. 163 hours of context. 163 hours I'll lose unless I reopen it. Built armillary to scan my folders and tell me what's rotting. github.com/justi/armill...

github.com

GitHub - justi/armillary: 💎 Never forget a side project again. Scans your folders, tells you what's rotting, and which forgotten hours are worth reviving.

💎 Never forget a side project again. Scans your folders, tells you what's rotting, and which forgotten hours are worth reviving. - justi/armillary

030

Justyna Wojtczak @justi.blue · 15/04/2026

ruby_llm-contract 0.6.0: define quality rules, get told which model to use. Step.recommend(candidates: [...]) - evaluates model + reasoning_effort combos, picks cheapest that passes, builds your retry chain. github.com/justi/ruby_l...

github.com

GitHub - justi/ruby_llm-contract: Know which LLM model to use, what it costs, and when accuracy drops. Companion gem for ruby_llm.

Know which LLM model to use, what it costs, and when accuracy drops. Companion gem for ruby_llm. - justi/ruby_llm-contract

150

Justyna Wojtczak @justi.blue · 28/03/2026

Had the same problem so many times it drove me crazy. Finally sat down and wrote a hook that fixes it — intercepts image reads before they break the session. bsky.app/profile/justi.blue/post/3mi4m67gbty2l

010

Justyna Wojtczak @justi.blue · 28/03/2026

Claude Code + images is still broken — crashes on transparency, large PNGs, and kills the whole session. Last night I shipped a hook that proxies image reads through a Haiku subprocess. Zero image data touches your main context. gist.github.com/justi/8265b84e70e8204a8e01dc9f99b8f1d0

140

Reposted by Justyna Wojtczak

Camille Roux @camilleroux.com · 02/03/2026

Ruby est le meilleur langage pour construire des apps IA en 2026. L'argument : on ne fait que des appels HTTP aux LLM, le reste c'est du développement web classique. Et Rails excelle là-dessus ! paolino.me/ruby-is-the-best-languag…

paolino.me

Ruby Is the Best Language for Building AI Apps

A pragmatic, code-first argument for Ruby as the best language to ship AI products in 2026.

043

Reposted by Justyna Wojtczak

Lucian Ghinda @lucianghinda.com · 22/03/2026

Added a new skill, "ruby-commit-message," to help create better commit messages. It focuses on writing commit bodies that help junior Ruby developers understand changes during debugging. This helps LLM explain the change better without fluff words.

Text on a dark background discusses improvements to Ruby commit messages for better understanding and debugging by junior developers.

151

Justyna Wojtczak @justi.blue · 27/03/2026

Shipped ruby_llm-contract v0.5 — contracts for LLM quality in Ruby. Which model? How much? Did that prompt tweak break accuracy? Schema + validations, eval against test cases, compare models by score & cost. Start cheap, auto-escalate when quality drops. github.com/justi/ruby_llm-contract

082