Yi Tay

Happy to share that the @GoogleDeepMind Gemini team is starting a new research team in Singapore! This new team will be focused on advanced reasoning, LLM/RL and improving bleeding edge SOTA models such as Gemini, Gemini Deep Think and beyond. 🔥 This team will be led by yours truly and reports up to Quoc Le (@quocleix)'s broader team in Mountain View which was recently in the center of both IMO gold medal and ICPC gold medal breakthroughs with Gemini Deep Think, amongst many other significant Gemini advancements. 🚀 We’re starting out with a very small but intensely capable force because talent density is key over anything else in the LLM era. Over the past few months, we have gone around and gathered the best of the best talent (in the region and beyond) and I’m confident we’ll have a super cracked team very soon. If you are interested in joining and have made truly exceptional contributions in any domain or area, (engineering and/or research etc) please contact me. This is quite an exciting time, with the Gemini / GenAI team at Google Deepmind leading the charge at the frontier. This is also the best opportunity to be on the critical path to AGI from the sunny island of Singapore. 🏝️ Many thanks to leadership support from @quocleix @JeffDean @benoitschilling, @EugenieRives and @demishassabis for the support of this team. Wonderful and fun image generated by Nano Banana 👇

@Swarooprm7 @GoogleDeepMind You enjoying?

Personal Update: I am back to @GoogleDeepMind. I will continue working on LLM research and product.

@zzlccc Vagueposting skill unlocked haha

rl intuition (up-scaled by the correctness of infra) is all you need when cooking with a strong base model such as gemini✨

@AndrewDai @yinfeiy @ElorianAI Congrats Andrew! And all the best in your adventure!

After almost 12 years in Brain/DeepMind, I’ve finally decided to take the leap. My cofounders: @yinfeiy, Seth and I have kicked-off @ElorianAI. The first multimodal reasoning lab founded and led by former LLM pretraining, data and multimodal leads. youtu.be/YlvfNpOMeOY?si… (1/n)

@_jasonwei congrats jason!

Fun nine months! My first week i remember we had a long dinner in the cafeteria daydreaming about the cool research directions to pursue, then going to back to our desks to write a basic script to inference llama. Now we have a pretty complete stack and our first model is out 🥑

@jennyzhangzt Very cool!! 🫡

Introducing Hyperagents: an AI system that not only improves at solving tasks, but also improves how it improves itself. The Darwin Gödel Machine (DGM) demonstrated that open-ended self-improvement is possible by iteratively generating and evaluating improved agents, yet it relies on a key assumption: that improvements in task performance (e.g., coding ability) translate into improvements in the self-improvement process itself. This alignment holds in coding, where both evaluation and modification are expressed in the same domain, but breaks down more generally. As a result, prior systems remain constrained by fixed, handcrafted meta-level procedures that do not themselves evolve. We introduce Hyperagents – self-referential agents that can modify both their task-solving behavior and the process that generates future improvements. This enables what we call metacognitive self-modification: learning not just to perform better, but to improve at improving. We instantiate this framework as DGM-Hyperagents (DGM-H), an extension of the DGM in which both task-solving behavior and the self-improvement procedure are editable and subject to evolution. Across diverse domains (coding, paper review, robotics reward design, and Olympiad-level math solution grading), hyperagents enable continuous performance improvements over time and outperform baselines without self-improvement or open-ended exploration, as well as prior self-improving systems (including DGM). DGM-H also improves the process by which new agents are generated (e.g. persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. This work was done during my internship at Meta (@AIatMeta), in collaboration with Bingchen Zhao (@BingchenZhao), Wannan Yang (@winnieyangwn), Jakob Foerster (@j_foerst), Jeff Clune (@jeffclune), Minqi Jiang (@MinqiJiang), Sam Devlin (@smdvln), and Tatiana Shavrina (@rybolos).

@qx_dong @NiJinjie @GoogleDeepMind @quocleix Off policy latte distillation is not as tasty 🥲

@YiTayML @NiJinjie @GoogleDeepMind @quocleix nvm, we've distilled from him😆

Life update: I’ve joined @GoogleDeepMind as a research scientist to work on ✨gemini scaling and RL, under the leadership of Yi Tay (@YiTayML) and Quoc Le (@quocleix). I feel extremely fortunate to be on the critical path towards AGI and can't wait to help push the frontier of gemini capabilities! 🚀

@NiJinjie @qx_dong @GoogleDeepMind @quocleix I heard ice latte was made via tool call (aka calling another human for help) today 🥲😂

@qx_dong @GoogleDeepMind @YiTayML @quocleix Thanks qingxiu!

@XueFz You guys enjoying?

Welcome to Gemini bro! Very nice to work together again (again and again) 🙃

@NiJinjie Let's go!

@YiTayML I'm prepared for sailing, captain!

Congrats and welcome @NiJinjie to the center of AGI (🇸🇬 branch). Taking highly technical and capable researchers like this and giving them a chance to be at the frontier to make tons of impact for Gemini has been one of the most rewarding things of founding & building GDM in SG.

@CYH37 @NiJinjie 🙌🙌🙌

@YiTayML @NiJinjie Congrats on one more Golden pick!!!😍

@NiJinjie @GoogleDeepMind @quocleix Welcome to the team and being the 5th person relevant to AGI on this sunny island!

Nano Banana 2, new state of the art in image generation and editing combined with Gemini’s real-world knowledge! You can simulate 3D CAD models purely through images. From sketch to real object!

More Aletheia and Deep Think greatness! 😎

@hyhieu226 @OpenAI @xai take care Hieu.

I have made the difficult decision to leave @OpenAI. Working here and at @xai before was a once-in-a-lifetime experience. I have met the best people. Not the best people in AI. Not the best people in tech. Simply the best people. At these companies, I have helped creating extremely intelligent entities that will meaningfully improve our lives. The work makes me proud. But the intensive work came with a price. I cannot believe I would say this one day, but I am burnt out. All the mental health deteriorating that I used to scoff at is real, miserable, scary, and dangerous. I am going to take a break from frontier AI labs, and will take my family to my home country Vietnam. There, I will try something new, and also search for a cure for my conditions. I hope I will heal. Until then.

Exciting results in AI math research! We use Aletheia agent, powered by Gemini 3 Deep Think, to tackle the FirstProof challenge. Operating completely autonomously, Aletheia successfully solved 6 out of the 10 problems. Check out the full paper for details on the methodology and expert evaluations. arxiv.org/abs/2602.21201

Gemini 3.1 pro is here 😁 Just one week after the Gemini 3 Deep Think launch, the core model/intelligence powering it all is shipped!

Today, we’re continuing to push the boundaries of AI with our release of Gemini 3.1 Pro. This updated model scores 77.1% on ARC-AGI-2, more than double the reasoning performance of its predecessor, Gemini 3 Pro. Check out the visible improvement in this side-by-side comparison, showing Gemini 3.1 Pro’s crisp animation built with pure code. Read more about today’s 3.1 Pro update: blog.google/innovation-and…

@Yining_Ye probably not. aletheia is an agent build on top of this deep think so i would say it counts to some extent.

@YiTayML will you have a tech report？or this is aletheia

Gemini 3 Deep Think is here! 😎 This model is not only super strong in math and coding (IMO gold and 3455 codeforces ELO), it is also gold standard in physics and chemistry olympiads. 😃 Also sets new records on ARC-AGI-2 and HLE. Proud to be a (core) member of the Deep Think team. 🦾😆. Feeling the AGI!

Also a less obvious but noteworthy point is that we are able to serve IMO gold quality now to more users because model improvements lead to requiring a smaller inference time topology than the IMO competition itself. 😀

Yesterday we just shared Aletheia, our math research agent that enables autonomous math research and solving Erdos open problems. Yes, this Gemini 3 deep think was *the* deep think. It's launched! x.com/YiTayML/status…