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.
https://t.co/VR02tw73fJ
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.
https://t.co/CIMECSEpD0
Inkling 2 Small from @thinkymachines is free on OpenRouter for a limited time.
It pairs vision with agentic coding, using visual feedback to build and refine websites, games, and 3D designs.
Use it at $0 inside agentic harnesses like Claude Code, Codex and Hermes Agent.
https://t.co/lQnCrRfhCA
Inkling 2 Small is available on @opencode, free for a limited time.
It was trained for agentic coding and knowledge work; we look forward to seeing how it works for you!
https://t.co/lKvI62T0ZX
This is a step towards our goal of building customizable intelligence, with more to come.
We would like to thank @NVIDIAAI for their support, as well as our partners who helped us test and benchmark Inkling 2 Small.
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.
https://t.co/VR02tw73fJ
Inkling 2 Small excels on long-horizon tasks, checks its work visually, and adapts to different harnesses and environments. Try fine-tuning it on Tinker, or let Inkling 2 Small orchestrate the fine-tuning workflow on its own.
Tinker lets customers turn their expertise into cutting-edge models that they own. One year after launch, we look back at what we’ve shipped and what our users are building.
https://t.co/fWTOG5U3k1
Our own @johnschulman2 talks with Dwarkesh about where human judgment still matters as models improve and self-improve: teaching them to handle messy real-world tasks, applying taste to what works in the long run, and, above all, specifying what we actually want.
New episode with @johnschulman2, @oneill_c and @BerenMillidge.
I got together with some of the most insightful AI researchers I know who are at the openish companies, because I wanted to hear the details of what's actually happening at the frontier and what comes next.
0:00:00 – Steelmanning the case against RSI
0:18:39 – What’s driving the Chinese labs’ progress
0:28:06 – How will automated AI researchers be trained
0:33:51 – Will long-horizon RL elicit AGI?
0:45:24 – The sim-to-real gap
1:00:33 – How much progress is explained by data?
1:18:03 – Why is RL working so well?
1:24:54 – Move 37 and entropy collapse
1:28:31 – Rapid-fire timelines
Cleaning data and aligning the reward function for RLVR takes expertise and effort upfront, but the result is a model that's state-of-the-art on a complex task.
Guest post by researchers at UIUC and Bridgewater, in collaboration with our team.
https://t.co/1UHTXFcZnW
LLMs with scaffolds have lagged on text-to-SQL, a task that relies on human judgment. By folding expert judgment into every part of RLVR on Tinker, @maxYuxuanZhu and @ddkang (UIUC and Bridgwater) trained the first text-to-SQL model to beat the human mark.
https://t.co/JxEQC31rX9
Today, we are launching Tinker grants of up to $50,000 in credits for safety research on open-weight models. We share some project ideas that excite us below; if you’re working on a safety project that could be accelerated by additional Tinker credits, we want to hear from you!
We want to improve Inkling’s agentic performance. To help us understand its real-world behavior, we are making it available for free on OpenRouter (only with agentic harnesses) for the next few weeks, starting now. We’ll use the data, disassociated from accounts, to better it.
Releasing weights indiscriminately isn't safe. Neither is keeping capable models inside a few labs.
We think there's a path between them. We haven't mapped all of it. Our new post covers the part we can see: how we assessed Inkling, and why access should widen in stages.
https://t.co/zGFbuXNr0Y
Another open-weight release from @thinkymachines 👀 Inkling-Small is here.
With native reasoning over audio and images and variable thinking effort, it's a great choice for fine-tuning, with NVIDIA NeMo on NVIDIA DGX Station.
NVFP4 checkpoint here: https://t.co/oJDeCVGy5p
Inkling and Inkling-Small are both available on Tinker with a limited-time discount, and all Tinker models can now be chatted with on Tinker Playground. As always, we're keen to see what you build.
Today, we are releasing Inkling-Small.
Inkling-Small achieves comparable performance to Inkling at a quarter of its size. It features 276B total parameters, 12B active. We are making the full weights available.
https://t.co/BtYNcpkDRA
Fine-tune it on Tinker today, or chat with it in text, image, and audio on Tinker Playground.
Like Inkling, it's natively multimodal. It’s encoder-free, with audio and images processed jointly with text. It nearly matches Inkling across multimodal evals, and it can use Python to crop, zoom, and inspect images while reasoning over documents and charts.