Jonathan Lai

Post training @GoogleDeepMind, Gemini Reasoning, training algorithms, RL, opinions are my own

[Jonathan Lai @_JLai]

@prateeky2806 @GoogleDeepMind Finally where you belong!

[Jonathan Lai @_JLai]

@denny_zhou Once the model's innovations are better than ours we can finally end our 997 and go on vacation.

[ARC Prize @arcprize]

Gemini 3 models from @Google @GoogleDeepMind have made a significant 2X SOTA jump on ARC-AGI-2 (Semi-Private Eval)

Gemini 3 Pro:
31.11%, $0.81/task

Gemini 3 Deep Think (Preview):
45.14%, $77.16/task

[Google DeepMind @GoogleDeepMind]

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything.

It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵

[Jonathan Lai @_JLai]

@XingyouSong Bitter lesson strikes again! RLM’s are such an elegant solution. Congratulations Richard and Yash!

[Jonathan Lai @_JLai]

@yacineMTB It’s more like how a dog learns new tricks, i.e. trying random actions until human gives it a treat. Humans can learn more efficiently by leveraging reasoning.

[Jonathan Lai @_JLai]

@agihippo Pixel 10 Fold m8

[Yi Tay @YiTayML]

Excited to share that I'll be hosting some of the world's best AI researchers and engineers for our @GoogleDeepMind Gemini event next week in Singapore 🇸🇬!

Join @JeffDean, @quocleix, @benoitschilling, @melvinjohnsonp and @denny_zhou for a day of technical conversations, panels and talks about AI, reasoning and our mission to build a world class AI frontier lab in Singapore.

If you're in town and would like to attend, please check the RSVP link below👇. Note, subject to capacity constraints and you'll need to be approved to join.

[Jonathan Lai @_JLai]

@denny_zhou @jamesjyan117153 Reasoning underpins AGI. I am grateful for the opportunity to contribute to reasoning in Gemini.

RL for LLMs was an enormous breakthrough, and there are more fundamental algorithmic breakthroughs yet to come!

[Jonathan Lai @_JLai]

@ankesh_anand @XingyouSong 👨🏻‍🍳🫡

[Jonathan Lai @_JLai]

Huge congrats @prateeky2806 and all!! 🎉 It was great to work with everyone here!

[Tu Vu @tuvllms]

Excited to share that our paper on model merging at scale has been accepted to Transactions on Machine Learning Research (TMLR). Huge congrats to my intern @prateeky2806 and our awesome co-authors @_JLai, @alexandraxron, @manaalfar, @mohitban47, and @TsendeeMTS 🎉!!

[Tu Vu @tuvllms]

Excited to share that our paper on model merging at scale has been accepted to Transactions on Machine Learning Research (TMLR). Huge congrats to my intern @prateeky2806 and our awesome co-authors @_JLai, @alexandraxron, @manaalfar, @mohitban47, and @TsendeeMTS 🎉!!

[Jonathan Lai @_JLai]

@BorisMPower @demishassabis We actually published our first Thinking / Reasoning model before the o-series was announced. Math-Specialized 1.5 Pro.

[Oriol Vinyals @OriolVinyalsML]

Today we have published our updated Gemini 1.5 Model Technical Report. As @JeffDean highlights, we have made significant progress in Gemini 1.5 Pro across all key benchmarks; TL;DR: 1.5 Pro > 1.0 Ultra, 1.5 Flash (our fastest model) ~= 1.0 Ultra.

As a math undergrad, our drastic results in mathematics are particularly exciting to me!

In section 7 of the tech report, we present new results on a math-specialised variant of Gemini 1.5 Pro which performs strongly on competition-level math problems, including a breakthrough performance of 91.1% on Hendryck’s MATH benchmark without tool-use (examples below 🧵).

Gemini 1.5 is widely available, try it out for free here https://t.co/GJXW8lduNk & read the full tech report here: https://t.co/Pltp92WcNo

[Jonathan Lai @_JLai]

@Swarooprm7 Congrats Swaroop! Looking forward to seeing what you and MAI cook up!

[Jonathan Lai @_JLai]

@Swarooprm7 All the best on your next endeavor Swaroop! 🫡

[Tu Vu @tuvllms]

🚨 New paper 🚨

Excited to share my first paper w/ my PhD students!!

We find that advanced LLM capabilities conferred by instruction or alignment tuning (e.g., SFT, RLHF, DPO, GRPO) can be encoded into model diff vectors (à la task vectors) and transferred across model versions.

💡You don’t necessarily need to fine-tune from scratch again for every new base model version. Instead, fine-tune once and add the diff vector to updated versions! ♻️♻️♻️. This can also offer a stronger and more computationally efficient starting point when further training is feasible.

📰: https://t.co/q2pPZcHGdY
More 👇

[Ankesh Anand @ankesh_anand]

shoutout to the believers!

[Tsendsuren @TsendeeMTS]

Gemini-ийн шинэ загварыг туршаад үзээрэй. Код бичих дээр нилээн сайжирсан байгаа.

[Jonathan Lai @_JLai]

A historic elo margin on LMSYS and also crushed almost all reasoning and STEM benchmarks!! So proud of this team!!

[Arena.ai @arena]

BREAKING: Gemini 2.5 Pro is now #1 on the Arena leaderboard - the largest score jump ever (+40 pts vs Grok-3/GPT-4.5)! 🏆

Tested under codename "nebula"🌌, Gemini 2.5 Pro ranked #1🥇 across ALL categories and UNIQUELY #1 in Math, Creative Writing, Instruction Following, Longer Query, and Multi-Turn!

Massive congrats to @GoogleDeepMind for this incredible Arena milestone! 🙌

More highlights in thread👇

[Sundar Pichai @sundarpichai]

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever.

Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on @lmarena_ai by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. 

Find it on Google AI Studio and in the @geminiapp for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.