Google DeepMind

The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us:

[Google DeepMind @GoogleDeepMind]

A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝

On the latest episode of our podcast, host @fryrsquared sits down with @NeelNanda5 to explore interpretability – the science of reverse engineering how neural networks learn and think.

Timecodes:
00:00 Introduction
02:41 Motivation for interpretability research
04:01 Mechanistic interpretability
08:14 Chain of thought monitoring
18:14 Interpretability techniques
35:00 Auditing models for safety
48:53 What comes next for interpretability

[Google DeepMind @GoogleDeepMind]

These examples showcase how the Predicting the Past Skill can push forward historical research using advanced AI models and complex workflows - with no coding required.

Find out more → https://t.co/jP3WKZA0g8

[Google DeepMind @GoogleDeepMind]

Here’s how we used the Predicting the Past Skill in Google @Antigravity to track down a Roman ring thief, map an ancient cult across Europe, and reconstruct the networks of people visiting a Greek oracle. 🧵

[Google DeepMind @GoogleDeepMind]

🔮 Who visited the Oracle of Dodona?

By analyzing collections of ancient lead tablets, the Skill mapped visitors traveling from across the ancient world. It reconstructed the community of oracle visitors, turning scattered fragments into a connected network.

[Google DeepMind @GoogleDeepMind]

Watch → https://t.co/b0mIyhmgZc
Spotify → https://t.co/5xWzSKWmA9
Apple Podcasts → https://t.co/jyYwdMxqGC
Or listen wherever you get your podcasts! 🎧

[Google DeepMind @GoogleDeepMind]

A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝

On the latest episode of our podcast, host @fryrsquared sits down with @NeelNanda5 to explore interpretability – the science of reverse engineering how neural networks learn and think.

Timecodes:
00:00 Introduction
02:41 Motivation for interpretability research
04:01 Mechanistic interpretability
08:14 Chain of thought monitoring
18:14 Interpretability techniques
35:00 Auditing models for safety
48:53 What comes next for interpretability

[Google Cloud @googlecloud]

AlphaEvolve is now GA on Google Cloud!

Co-developed with @GoogleDeepMind, AlphaEvolve is a Gemini-powered evolutionary agent that autonomously designs and discovers highly optimized code to solve your hardest problems and algorithmic bottlenecks across industries: https://t.co/Mai0TgNZEZ

[Shane Legg @ShaneLegg]

To whom do the fruits of advanced technological innovation belong?

A new paper on this key societal question from @IasonGabriel and @Dr_Atoosa in my post-AGI research group.

[Google DeepMind @GoogleDeepMind]

The Predicting the Past Skill is a collaborative research partner. 🏛️

We teamed up with @TSommerschield on 3️⃣ case studies to prove it. By blending specialized AI with Gemini’s reasoning, we showed how historians can explore ancient data in entirely new ways.

Explore the platform → https://t.co/jP3WKZA0g8

[Google DeepMind @GoogleDeepMind]

🏛️ We’re unveiling a new way to converse with the ancient world.

By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets historians study Greek and Latin texts using plain English. 🧵

[Google DeepMind @GoogleDeepMind]

Using AI for history analysis has 3 core challenges:
🔹 Creating custom analysis and visuals for every inscription.
🔹 Cross-source mapping to find large-scale patterns.
🔹 Utilizing advanced AI tools with no coding skills.

Our Antigravity skill shifts all these complex workflows into plain English.

[Google DeepMind @GoogleDeepMind]

As @Apptronik expands their Robot Park facility, our research partnership means real-world data collected by the latest Apollo 2 humanoid platform will help train and advance Gemini Robotics. 🤖

Find out more → https://t.co/mo9QykKn4H

[Tom Zahavy @TZahavy]

I am excited to share our latest work from the Discovery team at @GoogleDeepMind: COrigami, an end-to-end pipeline for co-designing origami with Gemini! 

Origami is a unique mix of math, art and design. Creating origami involves turning abstract concepts into real-world objects, using the math of flat foldability. To tackle this, COrigami calls Gemini to generate a semantic stick figure—an abstract JSON code—refined through a visual feedback loop. It then calls custom packing, solving, shaping, and simulation tools. Driven by another self-improving reinforcement learning (RL) loop, the system produces visually recognisable models represented as SVG crease patterns.

Despite scarce data availability, this approach demonstrates how combining RL with frontier models like Gemini can assist human creativity and produce physical art. The generated patterns serve as mathematically grounded starting points for origami artists to fold and shape into a final, physical design. The models below were produced by our system and then folded and shaped by @brandon_w0ng.  

Read the full paper here: https://t.co/ttiDUJ6OXI

[Iason Gabriel @IasonGabriel]

What does it mean to be an ethicist and a philosopher working in an AI company?

What questions do we explore – and can we affect positive change?

For a deep exploration of these themes, check out a new long-read by Bobby Baird in the @guardian today...

[Google DeepMind @GoogleDeepMind]

Find out more → https://t.co/feTpTwfnmC

[Google DeepMind @GoogleDeepMind]

We’re shipping 2 major releases:

🔘 Nano Banana 2 Lite: our fastest and cheapest Gemini Image model
🔘 Gemini Omni Flash: now available via the Gemini API and in @GoogleAIStudio to help developers generate and edit high-quality videos.

[Google DeepMind @GoogleDeepMind]

Pair these models together using the Interactions API. 🤝

Quickly generate an image with Nano Banana 2 Lite, then immediately animate it using Gemini Omni Flash.

Plus, you can maintain session history to stack up to three sequential edits.