Steerling-8B, a language model that can explain any token it generates
We release Steerling-8B, an 8B-parameter causal diffusion language model that is interpretable by construction — its predictions are routed through concepts you can measure, audit, and control.
Steerling-8B, a language model that can explain any token it generates launched on February 24, 2026 with 328 votes, #61 of 16,627 launches that month and more than 99% of that year's launches.
In plain words
Steerling-8B is a language model designed to explain each token it generates as it produces text. Built for users who want transparency in how AI systems construct responses, it breaks down the reasoning behind individual word choices. The model is intended for anyone curious about the mechanics of language generation, from researchers to developers to those exploring AI behavior. Its main distinction is the built-in explainability feature that makes the token-generation process visible and understandable.
written from the facts on this page · September 2026
From the sources
Author: Guide Labs Team Published: February 23, 2026 We are releasing Steerling-8B, the first interpretable model that can trace any token it generates to its input context, concepts a human can understand, and its training data. Trained on 1.35 trillion tokens, the model achieves downstream performance within range of models trained on 2–7× more data. Steerling-8B unlocks several capabilities which include suppressing or amplifying specific concepts at inference time without retraining, training data provenance for any generated chunk, and inference-time alignment via concept control, replacing thousands of safety training examples with explicit concept-level steering. For the first time,…from guidelabs.ai
Does a similar job
all alternatives →
Tiny Diffusion – A character-level text diffusion model from scratchNov 2025 · github.com · ▲172I previously posted this a month and a half ago: https://news.ycombinator.com/item?id=45876742 I have rewritten it to be much more simple, from 951 lines of code to just 364, with no loss in core functionality or generation quality. I also added a tiny GPT implementation as a comparison (inspired by Andrej Karpathy's code). The two model implementations are ~80% identical, with the core differences being the generate and get_batch functions. The model architecture, training loop, etc, differ in only 19 lines of code. Trained weights are included, so you can just clone and run…
Train a language model to talk like you2020 · colab.research.google.com · ▲209
Chonky – a neural approach for text semantic chunking2025 · github.com · ▲169TLDR: I’ve made a transformer model and a wrapper library that segments text into meaningful semantic chunks. The current text splitting approaches rely on heuristics (although one can use neural embedder to group semantically related sentences). I propose a fully neural approach to semantic chunking. I took the base distilbert model and trained it on a bookcorpus to split concatenated text paragraphs into original paragraphs. Basically it’s a token classification task. Model fine-tuning took day and a half on a 2x1080ti. The library could be used as a text splitter module in a RAG system or…
HuggingFace – Fast tokenization library for deep-learning NLP pipelines2020 · github.com · ▲168💥 Fast State-of-the-Art Tokenizers optimized for Research and Production - huggingface/tokenizers
Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com