Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor.
Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon.
We're grateful for our research partner working with us to study looped transformers.
Goodfire explored how layers pass information to future loops, and which interpretability tools allow us to understand the model's inner workings.
Looped models are weird. A layer can write to itself or read from "future" layers.
@thinkymachines gave us early access to Inkling 2 Mini so we could study its inner mechanisms. We uncover how it coordinates information flow across layers, blocks, and loops.
Studying Inkling 2
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index.
Our own @johnschulman2 sat down with @sarahdingwang to talk all things RSI: how AIs accelerate progress, how we measure it, and where human taste and intuition fit in the picture.
For decades, the idea of AI improving itself was just a thought experiment. Today, AI is already helping researchers at frontier labs run experiments, write code and test ideas faster. So how far are we from AI that can do the research on its own?
In our first episode of Working
Training with fewer bits is faster, but quantization error can interfere with learning.
Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout.