Tinker

@tinkerapi

I tink, therefore I am. Post-training API by @thinkymachines

San Francisco

thinkingmachines.ai/tinker

Replies Reposts Media

Pinned
Tinker
@tinkerapi
Jul 15
Inkling is our first open model from @thinkymachines and is now available on Tinker! Check out these quotes from Tinker customers on their experience with Inkling: @_Mantic_AI: "Not only does Inkling outperform Kimi K2.6 on our forecasting evals, it does so with half the output
Thinking Machines
@thinkymachines
Jul 15
Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. thinkingmachines.ai/news/introduci… Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵
9
Tinker
@tinkerapi
11h
We've shared research on fine-tuning forecasters, now you can try it for yourself: a cookbook recipe for training a model to predict event probabilities given reference information. Start with the provided dataset from @ProphetArena, then try your own. github.com/thinking-machi…
3
Tinker
@tinkerapi
Sep 4
Can you explain LLM behavior? If you can predict how the output changes with a different prompt, you're on the right track. Two recent papers used Tinker to test applications of counterfactual simulatability for interpretability: arxiv.org/abs/2602.20710 alphaxiv.org/pdf/2608.16747
Adam Karvonen
@a_karvonen
Aug 21
Replying to @a_karvonen
The causes vary widely: specific words in the prompt, quirks of the model (a misremembered fact about an actor), or abstract properties (a user's angry tone).
5
Tinker
@tinkerapi
Sep 3
Specializing a model doesn't mean a loss of general ability. @bespokelabsai trained Inkling on debugging a singular repo and produced a model that's better at coding across the board, while using fewer tokens to get the answer right.
Alex Dimakis
@AlexGDimakis
Sep 3
How to post-train a model to personalize it on your code repo? In our latest research in Bespoke Labs, we post-trained a model to improve its performance on a given Github repository. Starting from Inkling base, we use supervised fine-tuning (SFT) with trajectories coming from
Tinker
@tinkerapi
Sep 3
We previously highlighted @lightningrodai's data recipe for training forecasters. Their new work with @PTetlock and @VSatopaa adds another key piece: choosing the rule for scoring predictions, and how each one trades off accuracy and error.
Ben Turtel
@BTurtel
Sep 2
New preprint from @lightningrodai, this time with Philip Tetlock and Ville Satopää! We post-train 5 versions of the same LLM, changing only the scoring rule used as the RL reward. Similar aggregate scores, but very different BIN profiles. A good Brier score alone doesn't tell
1