New legal dataset up on the Huggingface Hub! Over the weekend I worked to finalise a snapshot of the official legal documents hosted by the Guantanamo Military Commissions. This is mostly court filings and transcripts from all the cases, around ~52GB of data.

When asking models to draft prompts (esp for things of more consequence like long-running processes / tasks), is it better to ask a model from the same family to write the prompt, or to use a different model family?

Published my first little environment on the PrimeIntellect Environments Hub yesterday evening. Very happy to finally have that out and complete! (links and more comments below, and a blog to follow I guess)

Latest ZenML release has a lovely new feature: an SSH orchestrator and stack component.

Have been working on reproducing my old ISAF press releases finetuning work that I originally did for the Hamel/Shreya course a couple of years back. I figured it's as good a way to get to grips with agentic RL as any, and so the first thing I did was to get to know my data a bit better.

Trying to understand the recent 'model routers are all you need' discourse. Obv frontier APIs / endpoints can be flaky and you probably want to have some kind of a (tested) fallback.

Sometimes you have to do a bit of data cleaning first before you get to the fun stuff. This week (aside from being sun-addled from the heatwave) I worked on that. It should unlock the real RL stuff that I am focusing on. (The temperature drop should also help with that) alexstrick.com/posts/2026-...

Wrote my first RL environment this evening. A very simple on, mind, but 'verifiers' (by @PrimeIntellect and @willccbb) makes it very easy to slot in the pieces.

I'm now transitioning from the part of my agentic RL exploration where I learned the high-level concepts to seeing what people are doing in practice.

Whenever a frontier lab drops a new model you always see their employees posting things like "you’ll be surprised by how good we made our new model! throw your hardest problems at it".

Doing a bit of a self-study RL course at the moment and one of the really useful tweaks I always have my 'teacher' do is to revisit the early FastAI lessons from @howard.fm and to really live up to those invitations to make things interactive, to get a sense for how things work intuitively.

Published a new post on our Kitaru adapter for Claude Agent SDK. Claude owns the agent loop. Kitaru records the completed invocation as durable workflow state: result, artifacts, waits, and replay boundary. One completed invocation = one checkpoint.

OpenAI Agents SDK is a great harness. When you move your agent to production, you're probably going to need and want more. That's where Kitaru comes in... We build an adapter so you can keep your OpenAI Agents SDK code, but throw in some durability and other goodies on top.

Had fun chatting with Hamza for this CNCF webinar last week, all about Kitaru, durable agent harnesses + agent runtimes. The video is embedded in the link in the thread. If you have agents in production and are experiencing growing pains around the runtime layer of the stack, we'd love to talk!

Just made a bumper release this evening: 25 new format adapters covering the major cloud annotation platforms, autonomous-driving and aerial datasets, document layout, synthetic data, and the long tail of academic/community formats.

"Your Harness, Your Memory" by Harrison Chase argues that memory belongs inside your agent harness, not behind a third-party API. We've been building exactly that, and Kitaru 0.4.0 shipped it this morning. kitaru.ai/blog/kitaru...

Kitaru agents now have memory

Durable, versioned memory for agents is now built into Kitaru — across Python, the typed client, the CLI, and MCP.

kitaru.ai

We just shipped migration skills to allow you to migrate off 11 ML/data platforms to ZenML: Airflow, Argo, AzureML, Dagster, Databricks, Flyte, Kedro, Metaflow, Prefect, SageMaker, Vertex AI. Each has hand-curated concept maps baked in showing what maps 1:1 and what needs redesign.

I've been building panlabel — a fast Rust CLI that converts between dataset annotation formats — and I'm a few releases behind on sharing updates. v0.3.0: Hugging Face ImageFolder support v0.4.0: auto-detection UX overhaul + Docker

Last month I migrated our ZenML website from Webflow to Astro in a week during a Claude Code / Cerebras hackathon. 2,224 pages, 20 CMS collections, 2,397 images. The site you see now is the result. Didn't win the hackathon but got a production website out of it, so I'll take that trade.

panlabel 0.2 is out. It's a CLI tool (and Rust library) for converting between different dataset annotation formats. Now also available via Homebrew.

I've been trying to push myself to use Codex Spark more, mostly because the speed changes the workflow in ways I'm still wrapping my head around.

This, all weekend long. #antidote www.youtube.com/watch?v=5vK...

Alysa Liu's STUNNING performance wins gold for USA! 🥇 | Winter Olympics 2026

Stream every moment of the Olympic Winter Games Milano Cortina 2026 live on TNT Sports and discovery+ 🇮🇹 ⛷️TNT Sports marks a new era in sports broadcastin...

youtube.com

If your product doesn't have an MCP server or public API in 2026, you're legacy software. I've noticed a shift in how I filter tools now. I'm basically only reaching for products that are AI-native i.e. whether I can integrate them into my AI-assisted workflows.

There's a lot to be gained from dual-model workflows for agentic engineering. Claude Code to take a first pass, Codex to review. Or 5.2-Pro to make a detailed plan and then Sonnet to implement.

If you've copied or downloaded a ChatGPT Deep Research report as markdown, you'll have noticed that they include all sorts of gunk in the file that you don't want. Here's a skill and a script that strips all that stuff out. (Also OpenAI please just fix this 🙏) github.com/strickvl/sk...

skills/clean-research-report at main · strickvl/skills

Claude Code skills and sub-agents for productivity - strickvl/skills

github.com

New blog post: running Recursive Language Models in production with ZenML. www.zenml.io/blog/rlms-i...

RLMs in Production: What Happens After the Notebook - ZenML Blog

Learn how ZenML's dynamic pipelines turn the Recursive Language Model pattern into a production-ready system with per-chunk observability, cost tracking, and budget controls.

zenml.io

A break from the usual programming (pun intended). Over the past few weeks I've been building something that has nothing to do with ML pipelines or developer tooling: a macOS menu bar app called Felt that sends gentle prompts throughout the day inviting you to notice what's happening in your body.

How do ML teams actually share GPU clusters when demand outstrips supply? Three dominant allocation models keep appearing:

What does a minimum viable "grown-up" GPU governance stack actually look like?

There's an assumption baked into GPU governance discussions: make utilisation visible and people stop hoarding.