anish

PM at Deepmind. I work on Gemini Omni

Opinions my own

[anish @oddclaw]

Working on a few edits and most of my time is going into making the AI b-roll look just a little worse so it matches the real footage 🙃

[anish @oddclaw]

@supreetpal Long time ago. Never finished 🫪

[anish @oddclaw]

605 deaths before beating the Ender Dragon is very relatable.

[elvis @omarsar0]

Banger paper from Google DeepMind on long-horizon multi-agent coding.

(bookmark it)

They report that, to the best of their knowledge, this is the first end-to-end autonomous completion of Minecraft by AI agents.

They report that four Gemini 4 Argon agents beat Minecraft end-to-end. They defeated the Ender Dragon in 27 hours and 14 minutes with no human intervention.

Each agent controlled one player through the standard Mineflayer library. No one assigned roles, wrote game logic, or scouted a seed in advance. The agents planned, wrote, and debugged every program themselves, and coordinated through in-game chat and a shared memory.

Over the run, they wrote 2,783 programs and died 605 times. They split the work, shared what they learned, and recovered each other's items after deaths.

If you build agents for long software or enterprise tasks, this is a useful case study. The team had to keep one plan consistent across thousands of dependent steps for more than a day.

https://t.co/h1Z87NYKqp

Chat with Paper: https://t.co/beTXikB3S8

[anish @oddclaw]

@AIatMeta Running a model this size on two Mac Studios is a actually a neat milestone for local workflows.

[anish @oddclaw]

My favorite demo of Argon so far. This model has so many capabilities but one of them is is editing videos.

Everything from finding the right take, to constructing a narrative - this model can actually handles it all.

[Khulan Dav ✦ @khulandav]

Gemini 4 Argon is insanely good at VIDEO EDITING and MOTION DESIGN 🔥

It understood my reference video and files really well because of its multimodal understanding, and looking at video frame by frame, code and image assets.

I had this unedited, unreleased video on my laptop, so decided to jazz it up and "re-imagine" it with Argon.

This video was entirely created inside Antigravity which is a great harness for creative work like this!

NOTE: this is not an official launch video, just my experiment.

[anish @oddclaw]

@SynKavish We appreciate the detailed observations and testing. Keep them coming !

[anish @oddclaw]

@egeberkina Very cool! @nbrichtova @whimsicolenicol

[I Am Devloper @iamdevloper]

Ten years of Sad Affleck memes and it turns out he'd just been trying to install CUDA drivers the whole time.

[anish @oddclaw]

Its very interesting to see how different models interpret "realistic"

[Johnn @john_my07]

GPT Image 2.5 on ChatGPT vs Nano Banana 2.1 on Gemini App

Prompt:
Create an ultra-realistic, high-end cinematic portrait of a beautiful young woman, framed in a tight head-and-shoulders composition. She faces the camera directly with a calm yet intense expression and a confident, captivating gaze.

Use dramatic low-key studio lighting with a strong directional light illuminating one side of her face while the opposite side gradually disappears into deep, atmospheric shadow. Keep the background completely black and seamless, creating a striking contrast around her silhouette.

Her eyes are deep brown with subtle geometric catchlights. Give her naturally textured, slightly damp-looking hair with individual strands visible and realistic volume. She wears a simple, elegant black crew-neck top with no visible logos or patterns.

Capture extremely realistic skin with visible pores, fine facial texture, subtle imperfections, delicate peach fuzz, natural lips, and detailed eyelashes. Avoid overly smooth or plastic-looking skin.

Photographed with a cinematic 35mm lens aesthetic, shallow depth of field, soft optical falloff, realistic tonal range, subtle analog film grain, and premium editorial photography quality. The final image should feel like an authentic photograph captured in a professional studio — sophisticated, raw, atmospheric, and completely photorealistic, with no obvious AI-generated appearance.

[anish @oddclaw]

@ybhrdwj ** only if you take uber black

[Christopher Fryant @cfryant]

A thread of texture and detail tests with the new Nano Banana 2.1.

4k native outputs, no upscaling of any kind.

[central dogma specialist @takimunk]

nb 2.1 mogs image 2.5 for editing. huge unblocker for my video workflow

[Nicole Segaran @whimsicolenicol]

👋 Hi folks!

I’m the new 🍌 PM.

Check out our latest image model! Nano Banana 2.1 outperforms our previous models across image gen and editing capabilities. And it makes great drawings of raccoons eating croissants!

Moved to the Bay to work on this, so hope you guys enjoy 😊

[anish @oddclaw]

Hi friends, we have a new image model.

[Dmitry Lyalin @LyalinDotCom]

Hello Nano Banana 2.1!

[Oliver Wang @oliver_wang2]

Enjoy our latest model update, Nano Banana 2.1! It improves things tool use and instruction following (especially multi-turn), giving you more reliable and useful generations and edits.

[Todd Dailey @twid]

I'm in on this Nano Banana 2.1 cat meme. (bonus, that's my actual cat Miso.)

[anish @oddclaw]

@adhidesign @GoogleDeepMind @antigravity Welcome :)

[anish @oddclaw]

100% true

[Nataniel Ruiz @natanielruizg]

i can confirm this is the case for me as well

[Zachary Nado @zacharynado]

brutal