Pinned Tweet
Joe Leo and I have officially launched a very special first episode of The Ruby AI Podcast: "Beyond Chat: Phoenix Tests, Ruby Agents & the AI Tipping Point"
In the pilot episode, we chat about shipping real AI products in Ruby, how Phoenix got started, and why Ruby syntax actually makes this weird new world fun to build in.
Hope you'll come along for the ride.
(And send us your favorite AI coding mishaps—we might just feature them in a future episode!)
therubyaipodcast.com
In the pilot episode, we chat about shipping real AI products in Ruby, how Phoenix got started, and why Ruby syntax actually makes this weird new world fun to build in.
Hope you'll come along for the ride.
(And send us your favorite AI coding mishaps—we might just feature them in a future episode!)
therubyaipodcast.com
1
3
8
1,263
The Ruby AI Podcast just passed 10k downloads! 30 episodes in. @jleo3 and I started this to talk honestly about building with AI in Ruby, and we can't thank you enough for listening. Here are the top 5 episodes
2
3
12
851
#5: @searls on real AI dev workflows. Agile habits vs agentic ones, and whether these tools reinforce good practice or let us skip it. therubyaipodcast.com/2388930/episod…
1
0
2
41
10,000 is a nice number, but the best part has been exposing the joy that Ruby brings, even as agents take over the typing. Keep listening, and we'll keep showing up❣️ 🙇
0
0
2
28
Valentino Stoll retweeted
Twenty-six years later, coding agents have broken most of eXtreme Programming's assumptions, but not its best ideas. So I rewrote XP for the age of agents. x.com/i/article/2105…
27
37
1,760
333,275
"Papa's Got a Brand New Pane" 😂
markdown.codenamev.com
markdown.codenamev.com
Introducing: Get Up Offa That Markdown!
My result from asking my agent to "use scarpe to make me a simple markdown viewer"
Incredible work on this revival project @schwad_rb ! 👏 True joy.
github.com/codenamev/get-…
0
0
2
177
Introducing: Get Up Offa That Markdown!
My result from asking my agent to "use scarpe to make me a simple markdown viewer"
Incredible work on this revival project @schwad_rb ! 👏 True joy.
github.com/codenamev/get-…
My result from asking my agent to "use scarpe to make me a simple markdown viewer"
Incredible work on this revival project @schwad_rb ! 👏 True joy.
github.com/codenamev/get-…
2
2
9
1,129
Niiiiiiice
Introducing "Agents on Rails Files": engineering-side insights, findings, stories—the dark side of rubyonrails.org/ai.
The first post in the series shares the tips and tricks on writing black-box (e2e) evals and... compares Rails with Rust!
evilmartians.com/chronicles/the…
0
1
5
415
Valentino Stoll retweeted
You gave Claude Code a goal at 10pm and then go to bed. A heartbeat woke it every half hour, but it kept working through the night: lanes, reviews, merges, deploys... but what decisions did it make, exactly? x.com/i/article/2112…
24
18
103
7,114
Valentino Stoll retweeted
ICYMI, the 39th edition of Ruby AI News is out now. The edition features a continued look at the future of Rails, RubyLLM 2.1, decision models, impatient programming, and much more
rubyai.beehiiv.com/p/ruby-ai-news…
rubyai.beehiiv.com/p/ruby-ai-news…
0
3
8
331
If you're a software engineer, this is a MUST watch. @fractaledmind, Leading all Product Engineering at @zardotapp, gives the best articulation of how to reasonably apply AI to software development that I've heard yet. I've seen first hand how incredibly well this all works in practice 👏
youtu.be/OmrdvAzCSIc?si…
youtu.be/OmrdvAzCSIc?si…
1
4
14
1,394
So good 😂
As all programmers start taking the work of their coding agents completely for granted, the AI notices who still reads every line. 😍
New slopcore from yours truly!
h/t @anabology for Claudia
0
0
1
151
Valentino Stoll retweeted
My conversation with the Ruby AI podcast folks about software security and Hot Cell (a new, more secure backend for Active Storage) is out!
therubyaipodcast.com/2388930/episod…
therubyaipodcast.com/2388930/episod…
0
1
9
471
Valentino Stoll retweeted
RubyLLM 2.1 is out now and it's missing nothing from LangChain/LangGraph/LangSmith.
- Up to 58x faster and 58x less memory
- Built-in MCP support with MCP Apps up to the latest spec
- Support for Jev and other Decision Models
- a new Evaluation framework
- OpenTelemetry tracing
he capabilities of the big Python frameworks, in a beautiful language like Ruby, integrated seamlessly into your Rails applications.
rubyllm.com
- Up to 58x faster and 58x less memory
- Built-in MCP support with MCP Apps up to the latest spec
- Support for Jev and other Decision Models
- a new Evaluation framework
- OpenTelemetry tracing
he capabilities of the big Python frameworks, in a beautiful language like Ruby, integrated seamlessly into your Rails applications.
rubyllm.com
15
41
250
9,244
Valentino Stoll retweeted
A great abstraction used to save time for the people who knew about it.
Now it shapes every line a coding agent writes.
Now it shapes every line a coding agent writes.
0
2
9
629
Valentino Stoll retweeted
Just so we are all on the same page:
* The Rust version has hundreds of commits, with multiple optimizations rounds, over several days. The others have 1 or 2 commits from an initial agentic rewrite
* Based on the available documentation, different things were asked from each attempt. The agents.md from Go mentions the Rust version was the canonical example. The Elixir one mentions it was the Rails one
* While we don’t have the full prompts, it seems they were vague, allowing the agents to make non-language architectural decisions that impact results (such as how closely it should replicate Rails’ drawbacks)
It is actually amazing how quickly we can have full-blown rewrites up and running. But if we want to take conclusions from the data presented, it is important to understand the process behind it.
* The Rust version has hundreds of commits, with multiple optimizations rounds, over several days. The others have 1 or 2 commits from an initial agentic rewrite
* Based on the available documentation, different things were asked from each attempt. The agents.md from Go mentions the Rust version was the canonical example. The Elixir one mentions it was the Rails one
* While we don’t have the full prompts, it seems they were vague, allowing the agents to make non-language architectural decisions that impact results (such as how closely it should replicate Rails’ drawbacks)
It is actually amazing how quickly we can have full-blown rewrites up and running. But if we want to take conclusions from the data presented, it is important to understand the process behind it.
The agents finished porting Campfire to Laravel and Django too. I'm sure there are optimizations that could be found there too, but the whole point is to get a sense of how frontier agents do with different environments out the box. github.com/basecamp/once-…
39
86
1,111
52,522