Come check out o1-mini: SoTA math reasoning in a small package https://t.co/iftuVLkkZ6 with @ren_hongyu @shengjia_zhao @Eric_Wallace_ & the rest of the OpenAI team

Science is best shared! Tell us about what you’ve built or discovered with Tinker, so we can tell the world about it on our blog. More details at

We also replicate the "Distillation for personalization" results from @_kevinlu and @thinkymachines by improving the code performance of a model with SFT and then recovering it's IFEval scores with distillation.

thanks to multi-tenancy and the incredible engineering effort of the team, tinker is now both a joy to use, and super cheap! hope to see you try it out 🙂

excited to see what academics build using tinker!

On-policy + Reverse KLD = MiniLLM ( https://t.co/MSlVNWGclo). Really nice blog by @thinkymachines. Exciting to see it being offered as a service!

We just added 4 new models to Tinker from the gpt-oss and DeepSeek-V3.1 families. Sign up for the waitlist: https://t.co/CAsOcUduwR

@agarwl_ @Alibaba_Qwen @IdanShenfeld @jyo_pari @__howardchen ...it also happens to still work effectively using only a single prompt, and can be 10-100x cheaper compared to running SFT or RL.

@agarwl_ @Alibaba_Qwen this "continual learning" problem was previously identified by @IdanShenfeld @jyo_pari @__howardchen, who have shown that on-policy methods regress significantly less than SFT when performing domain adaptation https://t.co/1jwQ7lBZuW

in our new post, we walk through great prior work from @agarwl_ & the @Alibaba_Qwen team exploring on-policy distillation using an open source recipe: you can run our experiments on Tinker today! https://t.co/7pVk87qTDH i'm especially excited by the use of on-policy

Personally, I love this plot because it so crisply shows the value of active (RL) vs passive (SFT) experience for embodied agents: just 1% of active (RL) interaction gives you jump from orange to blue which you can't approach by just pouring in more passive SFT data (orange).

Tinker provides an abstraction layer that is the right one for post-training R&D -- it's the infrastructure I've always wanted. I'm excited to see what people build with it. "Civilization advances by extending the number of important operations which we can perform without

anyone who's tried running RL on top of language models knows how painful it is -- building on top of new research, tinker makes finetuning frontier LLMs easy and performant! it's the latest in a long-standing dream to use finetuning to democratize training and personalization.

I used to be really excited about the properties of LoRA's for compositionality and personalization back in the stable diffusion days ( https://t.co/sP5qqVR9tC) -- turns out they are still promising! come check out @johnschulman2 's modern analysis on LoRA's for modern LLM

Efficient training of neural networks is difficult. Our second Connectionism post introduces Modular Manifolds, a theoretical step toward more stable and performant training by co-designing neural net optimizers with manifold constraints on weight matrices.

Today Thinking Machines Lab is launching our research blog, Connectionism. Our first blog post is “Defeating Nondeterminism in LLM Inference” We believe that science is better when shared. Connectionism will cover topics as varied as our research is: from kernel numerics to

I recently joined @thinkymachines -- super excited to work with the team, I think we have the highest density of research talent in the world 🙂 we have a very ambitious roadmap ahead, the right team to work on it, & I think now is a great time to join; you should reach out to

GPT-5 is what you’ve been waiting for – it defines and extends the cost-intelligence frontier across model sizes today. it’s been a long journey, and we’ve landed pivotal improvements across many axes in the whole GPT-5 family. and hey no more model picker (by default)!

this was a first-class effort worked on by amazing researchers, and the results speak for themselves I'm proud of OpenAI for this release – open-weights models are huge for Broadly Distributing the Benefits of AI research glad this model made it out alive 🙃

come check out the team’s latest models, with substantial contributions from @SuvanshSanjeev & @minyoung_huh 🙂 we are a stone’s throw away from gpt5-level performance running locally on your phone

Ads aren't inherently good or evil. They are fundamentally a market for attention. Attention is humanity's ultimate scarce resource. Our goal should be to allocate it as efficiently as possible.