Guide Labs

Engineering interpretable AI systems that are easy to understand, trust, and debug.

[Guide Labs @guidelabsai]

Today we’re announcing a finding that breaks a core assumption in AI: that bigger models are harder to understand.

We show the opposite. When interpretability is built into training, models become MORE understandable as they become more capable.

[Guide Labs @guidelabsai]

See our break down of CDE's architecture, design decisions, performance tradeoffs, and debugging tips in our latest blog: https://t.co/ft3eYm0vhy

Explore the open-source code: https://t.co/J2Cr1nq2ft
Designed by Muawiz Chaudhary (@ScatteringSepoy) and Andreas Madsen (@andreas_madsen).

#MLOps #DataScience

[Guide Labs @guidelabsai]

Introducing the Causal Diffusion Engine (CDE): the inference engine behind Steerling-8B.

CDE serves an interpretable diffusion LLM with concept explanations and steering alongside every generated token, with no added latency.

Interpretability doesn’t have to slow down inference.

[Guide Labs @guidelabsai]

Where CDE falls short: batching. Each block step waits on the slowest request in the batch, and the sampler adds GPU→CPU syncs.

Next up: a forward-step runner and a sync-free sampler, which should unlock big throughput gains

[Guide Labs @guidelabsai]

Join us in shaping actually interpretable AI.

Quick-start instructions (beginner, intermediate, advanced) and fully searchable details about GuideLoom: https://t.co/jIzPAfoNOR

💻 Code: https://t.co/rMcxLSjAw0
📦 PyPI: https://t.co/Hk1JsMBzY6
✍️ How we built GuideLoom: https://t.co/zIEslIY0FT

#InterpretableAI #MLOps #MachineLearning

[Guide Labs @guidelabsai]

It’s live: the first open-sourced dataloader for training interpretable language models at scale, GuideLoom.

We’ve been using it to train models ranging from 100M params → 32B params, and now it’s yours.

GuideLoom stores your data (as documents, token streams, or token streams with annotations on spans of tokens) + during training, a PyTorch DataLoader shuffles across the entire dataset, lets every GPU read its own samples in parallel, and resumes from the exact batch after a restart.

pip install guideloom[torch]

[Guide Labs @guidelabsai]

It’s built for scale + lean by design—the only core dependencies are NumP-y, PyTorch, and Numba).

[Guide Labs @guidelabsai]

Our research at #COLM on tracing a language model's output to its training data.

[Dan Ley @dan_w_ley]

Introducing PRISM: Prototype Language Models, language models designed to make next token predictions traceable to the pre-training data in a single forward pass! We’ll be presenting at #COLM.

[Guide Labs @guidelabsai]

At Guide Labs we've discovered that first testing small-scale models can help estimate how a property changes with compute...we're setting the stage for a new paradigm of AI design.

Opacity isn't a law of nature.

Blog: https://t.co/CqxDHeWtKe

Full technical report: https://t.co/tl7CN789eX

#InterpretableAI #LLMOps

[Guide Labs @guidelabsai]

UPDATE: Steerling-8b has broken through the assumption that larger models + more data are harder to interpret →

Interpretability can be forecasted before an expensive run, and we can estimate ROI from params and data.

Instead of a black box you have to reverse-engineer afterward, Steerling-8b’s concept attribution has shown:
- the larger the interpretable model, the more disentangled its representations
- training more data makes the model’s representations more human-aligned

[Guide Labs @guidelabsai]

But a single compute number alone does not clarify how the effect of model size differs from the amount of training data. Equal-compute runs differ systematically.

Separating params v. tokens allows us to identify the impact of a specific interpretability property.

Both data + model size affect how much the model’s output depends on human-understandable concepts. When increasing compute, Steerling-8b routes a larger share of its prediction through its interpretable embeddings.