Enias Cailliau

I help developers & entrepreneurs build with GPT | Founding Engineer at Steamship

Turned down Facebook to build winning startups. 

- Build what customers want.

Co-founder & CTO

The power of compounding.

I am obsessed with Machine Learning, Generative AI, LLMs, and more — and I love sharing knowledge as much as I love learning!

Chris Alexiuk

Ilya was right, we're in the Age of Research.

Recursive Language Models (RLMs) from MIT CSAIL (including Mr. DSPy himself!) is yet another banger.

The name buries the lede a bit. The real insight comes from avoiding cramming your 10M token corpus into the context window, treat the prompt as a variable in a Python REPL and let the model programmatically peek at it.

(REPL = Read-Eval-Print Loop - basically an interactive coding environment where you type code, it runs, you see the output. Think Jupyter notebooks or a Python terminal.)

Why it matters:
- Handles inputs 100x beyond context limits
- Model decides what to look at and when
- Sub-LM calls for decomposition and synthesis

It's not magic - you're still bottlenecked by attention span at every call. But giving the model control over its own context management? That's pretty dope.

Feels like fertile ground for optimization. The paper uses a fixed system prompt across all tasks - there's definitely headroom for task-specific strategies, learned routers, or even DSPy-style prompt tuning.

Remember - even if you're just starting in AI today - you're right on time.

Paper: https://lnkd.in/gTQG4JzD
Code: https://lnkd.in/gAGcRyS5

Chris "The Wiz 🪄" Alexiuk

AI @ NVIDIA - 🏗️ Build | 🚢 Ship | 🚀 Share

It's another blog - this time: All about making a Bash Agent learn some new tricks!

Problem: I want my Bash Agent to run LangGraph CLI commands - so it can spin up my Agents. 

Issue: It's not very good at it out of the box. 

Solution: Use Reinforcement Learning (with GRPO) to teach the model powering my agent how to do it.

In the tutorial, I used: 

1. NeMo Data Designer to.....design the data. NGL. 

It was easy to use, and easy to produce the data I needed - would strongly recommend. If you want to learn more, follow Eric Tramel or Johnny Greco.

2. NeMo Gym + Unsloth

Obviously a potent combination - and obviously a blast to use. NeMo Gym is way simpler than you might imagine for how POWAFUL it is. If you want to learn more about *those* tools - well, you're already following Unsloth - so Chris Wing, Wenwen Gao, and Sylendran Arunagiri are the ones to follow for Gym!

3. Our Bash agent that we created for a previous tutorial!

All told - this takes ~3hrs. to work through (but needs an 80GB GPU for right now) and while I used LangGraph Platform CLI - you could use whatever you'd like!

Dr. Greg Loughnane and I are going to talk about "Ralph Wiggum" next Wednesday, yes, really.

If you have no clue what that means: Congrats, you're on the sane part of the internet - but the event will explain why this cutely named while loop has stolen the hearts and minds of engineers 'round the interwebs.

It will also, more importantly, serve as a practical "getting started guide" for Claude Code - tailor made for 2026, and Opus 4.5.

Leveraging these tools, as I've mentioned recently, is something that no longer feels optional - but it can be a bit of an opaque process to get started with them, and so we wanted to do this event to help people get (a bit) up to speed.

It'll also, hopefully, start you down the path to become the mayor of your very own self-built Gas Town.

Given that we're a week out - what would you most like to see us cover? Let me know in the comments!

https://lnkd.in/gNzJquMk

Open video: Ralph Wiggum: Continuous Agent Loops in Claude Code on youtube.com

Ralph Wiggum: Continuous Agent Loops in Claude Code

taplio

The Battle

Enias Cailliau

Chris Alexiuk

Followers

Posts

Engagements

Likes

Performance ScoreChris Alexiuk's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Enias Cailliau

Chris Alexiuk

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Chris Alexiuk's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreChris Alexiuk's LinkedIn Performance