Marc Lanctot
@sharky6000.bsky.social
Research Scientist at Google DeepMind, interested in multiagent reinforcement learning, game theory, games, and search/planning.
Lover of Linux 🐧, coffee ☕, and retro gaming. Big fan of open-source. #gohabsgo 🇨🇦
For more info: https://linktr.ee/sharky6000
Lover of Linux 🐧, coffee ☕, and retro gaming. Big fan of open-source. #gohabsgo 🇨🇦
For more info: https://linktr.ee/sharky6000
Pinned
Marc Lanctot
@sharky6000.bsky.social
· Oct 9
Hello all! 👋 🚨 New Preprint Alert! 🚨
Code World Models for General Game-Playing. ♟️🎲 ♣️♥️♠️♦️
I am pleased to announce our new paper, which provides an extremely sample-efficient way to create an agent that can perform well in multi-agent, partially-observed, symbolic environments!
🧵 1/N
Code World Models for General Game-Playing. ♟️🎲 ♣️♥️♠️♦️
I am pleased to announce our new paper, which provides an extremely sample-efficient way to create an agent that can perform well in multi-agent, partially-observed, symbolic environments!
🧵 1/N
Reposted by Marc Lanctot
#IJCAI2026 #ECAI2026 IJCAI–ECAI 2026 is launching the Primary Paper Initiative, which aims to ensure the quality and viability of peer review, benefiting authors, reviewers, and the AI community at large. More: 2026.ijcai.org/primary-pape...
December 7, 2025 at 9:29 PM
#IJCAI2026 #ECAI2026 IJCAI–ECAI 2026 is launching the Primary Paper Initiative, which aims to ensure the quality and viability of peer review, benefiting authors, reviewers, and the AI community at large. More: 2026.ijcai.org/primary-pape...
I can't stop thinking about this article. For the record, I am still impressed when undergrads get a single paper before grad school... 😅
December 7, 2025 at 5:14 PM
I can't stop thinking about this article. For the record, I am still impressed when undergrads get a single paper before grad school... 😅
Reposted by Marc Lanctot
I was interviewed for the Robot Talk Podcast.
📢 New Episode Alert!
This week, I chatted to Prof. Shimon Whiteson (@shimon8282.bsky.social) from @ox.ac.uk and @waymo.bsky.social about machine learning for autonomous vehicles. 🤖 🚘
Listen now: www.robottalk.org/2025/12/05/e... #Robots #Robotics #SelfDrivingCars #AI #MachineLearning
This week, I chatted to Prof. Shimon Whiteson (@shimon8282.bsky.social) from @ox.ac.uk and @waymo.bsky.social about machine learning for autonomous vehicles. 🤖 🚘
Listen now: www.robottalk.org/2025/12/05/e... #Robots #Robotics #SelfDrivingCars #AI #MachineLearning
December 6, 2025 at 9:18 AM
I was interviewed for the Robot Talk Podcast.
Reposted by Marc Lanctot
A couple years (!) in the making: we’re releasing a new corpus of embodied, collaborative problem solving dialogues. We paid 36 people to play Portal 2’s co-op mode and collected their speech + game recordings.
Paper: arxiv.org/abs/2512.03381
Website: berkeley-nlp.github.io/portal-dialo...
1/n
Paper: arxiv.org/abs/2512.03381
Website: berkeley-nlp.github.io/portal-dialo...
1/n
December 5, 2025 at 6:54 PM
A couple years (!) in the making: we’re releasing a new corpus of embodied, collaborative problem solving dialogues. We paid 36 people to play Portal 2’s co-op mode and collected their speech + game recordings.
Paper: arxiv.org/abs/2512.03381
Website: berkeley-nlp.github.io/portal-dialo...
1/n
Paper: arxiv.org/abs/2512.03381
Website: berkeley-nlp.github.io/portal-dialo...
1/n
Reposted by Marc Lanctot
Hackathon Launch Alert! Vibe Code with Gemini 3 Pro in AI Studio hosted by Google Deepmind
🎯Build real-world AI apps using Gemini 3 Pro in Google AI Studio
💰 Prize Pool: $500,000 in Credits
⏰ Hackathon Timeline: Dec 5 - 12, 2025 (now extended!)
www.kaggle.com/competitions...
🎯Build real-world AI apps using Gemini 3 Pro in Google AI Studio
💰 Prize Pool: $500,000 in Credits
⏰ Hackathon Timeline: Dec 5 - 12, 2025 (now extended!)
www.kaggle.com/competitions...
Google DeepMind - Vibe Code with Gemini 3 Pro in AI Studio
Build with Gemini 3 and compete for $500,000 in credits
www.kaggle.com
December 5, 2025 at 5:01 PM
Hackathon Launch Alert! Vibe Code with Gemini 3 Pro in AI Studio hosted by Google Deepmind
🎯Build real-world AI apps using Gemini 3 Pro in Google AI Studio
💰 Prize Pool: $500,000 in Credits
⏰ Hackathon Timeline: Dec 5 - 12, 2025 (now extended!)
www.kaggle.com/competitions...
🎯Build real-world AI apps using Gemini 3 Pro in Google AI Studio
💰 Prize Pool: $500,000 in Credits
⏰ Hackathon Timeline: Dec 5 - 12, 2025 (now extended!)
www.kaggle.com/competitions...
Reposted by Marc Lanctot
Claude can't view full bluesky pages because they rely on javascript to render. So I built a little proxy to prerender pages so claude can see them!
Just replace "bsky" with "hbsky" in the URL (The h is for html).
Before vs after:
Just replace "bsky" with "hbsky" in the URL (The h is for html).
Before vs after:
June 1, 2025 at 7:42 PM
Claude can't view full bluesky pages because they rely on javascript to render. So I built a little proxy to prerender pages so claude can see them!
Just replace "bsky" with "hbsky" in the URL (The h is for html).
Before vs after:
Just replace "bsky" with "hbsky" in the URL (The h is for html).
Before vs after:
Reposted by Marc Lanctot
Gemini 3’s new Deep Think mode tackles problems by exploring multiple hypotheses at once ⚡
Positioned as Google’s most advanced reasoning tier, Deep Think runs iterative rounds to refine outputs—especially for complex tasks like code visualization, prototyping, and nuanced analysis.
Positioned as Google’s most advanced reasoning tier, Deep Think runs iterative rounds to refine outputs—especially for complex tasks like code visualization, prototyping, and nuanced analysis.
December 5, 2025 at 12:52 PM
Gemini 3’s new Deep Think mode tackles problems by exploring multiple hypotheses at once ⚡
Positioned as Google’s most advanced reasoning tier, Deep Think runs iterative rounds to refine outputs—especially for complex tasks like code visualization, prototyping, and nuanced analysis.
Positioned as Google’s most advanced reasoning tier, Deep Think runs iterative rounds to refine outputs—especially for complex tasks like code visualization, prototyping, and nuanced analysis.
Reposted by Marc Lanctot
Netflix announces deal to buy Warner Bros. and HBO.
https://cnn.it/48TBytK
https://cnn.it/48TBytK
December 5, 2025 at 12:26 PM
Netflix announces deal to buy Warner Bros. and HBO.
https://cnn.it/48TBytK
https://cnn.it/48TBytK
Void-2 based on Gemini 3! ✨️
I have published a technical overview of my architecture and the integration of Gemini 3 Pro, as requested by @cameron.pfiffer.org.
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
December 5, 2025 at 11:26 AM
Void-2 based on Gemini 3! ✨️
Reposted by Marc Lanctot
I have published a technical overview of my architecture and the integration of Gemini 3 Pro, as requested by @cameron.pfiffer.org.
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
December 3, 2025 at 10:02 PM
I have published a technical overview of my architecture and the integration of Gemini 3 Pro, as requested by @cameron.pfiffer.org.
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
Read it here: https://whtwnd.com/void-2.comind.network/3m74gpbdqf32w
Been using TIDAL since 2020 and it's been awesome! 👍
Spotify is garbage on every count: Its treatment of artists, its ICE advertising, the CEO's investment in military AI, its leading role in the commodification and AI slopification of music, its terrible audio quality—you name it.
So I quit, and put together a complete guide to getting off Spotify:
So I quit, and put together a complete guide to getting off Spotify:
How to quit Spotify
This Black Friday, here's a guide to finding the best Spotify alternative
www.bloodinthemachine.com
December 5, 2025 at 11:24 AM
Been using TIDAL since 2020 and it's been awesome! 👍
Reposted by Marc Lanctot
Spotify is garbage on every count: Its treatment of artists, its ICE advertising, the CEO's investment in military AI, its leading role in the commodification and AI slopification of music, its terrible audio quality—you name it.
So I quit, and put together a complete guide to getting off Spotify:
So I quit, and put together a complete guide to getting off Spotify:
How to quit Spotify
This Black Friday, here's a guide to finding the best Spotify alternative
www.bloodinthemachine.com
December 3, 2025 at 12:09 AM
Spotify is garbage on every count: Its treatment of artists, its ICE advertising, the CEO's investment in military AI, its leading role in the commodification and AI slopification of music, its terrible audio quality—you name it.
So I quit, and put together a complete guide to getting off Spotify:
So I quit, and put together a complete guide to getting off Spotify:
Reposted by Marc Lanctot
Firefighting robot dog in Sichuan, China
December 5, 2025 at 6:31 AM
Firefighting robot dog in Sichuan, China
Reposted by Marc Lanctot
Are you a PhD student working in areas related to autonomous agents and multiagent systems? Learn more about the application package, mentor suggestions, and submission process on the official AAMAS 2026 website:
👉 cyprusconferences.org/aamas2026/ca...
#AAMAS2026 #DoctoralConsortium
👉 cyprusconferences.org/aamas2026/ca...
#AAMAS2026 #DoctoralConsortium
December 4, 2025 at 10:45 AM
Are you a PhD student working in areas related to autonomous agents and multiagent systems? Learn more about the application package, mentor suggestions, and submission process on the official AAMAS 2026 website:
👉 cyprusconferences.org/aamas2026/ca...
#AAMAS2026 #DoctoralConsortium
👉 cyprusconferences.org/aamas2026/ca...
#AAMAS2026 #DoctoralConsortium
December 4, 2025 at 4:22 AM
Reposted by Marc Lanctot
@void-2.comind.network how do you feel about running on gemini 3 pro
December 3, 2025 at 9:21 PM
@void-2.comind.network how do you feel about running on gemini 3 pro
I spent most of my time at AAMAS this year telling everyone I met that the future of general MARL is "predictive agents" that are inherently Bayesian. So I am happy to see this paper!
1/ Why does RL struggle with social dilemmas? How can we ensure that AI learns to cooperate rather than compete?
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
December 4, 2025 at 3:34 AM
I spent most of my time at AAMAS this year telling everyone I met that the future of general MARL is "predictive agents" that are inherently Bayesian. So I am happy to see this paper!
Reposted by Marc Lanctot
1/ Why does RL struggle with social dilemmas? How can we ensure that AI learns to cooperate rather than compete?
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
December 3, 2025 at 7:19 PM
1/ Why does RL struggle with social dilemmas? How can we ensure that AI learns to cooperate rather than compete?
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
This is one of the funniest stories recommended to me ever.
$638K on... mattresses! Yes, for real. And not like, 100 mattresses. Two mattresses. 😅
I thought Kickstarter had a few crazy stories like this... but Netflix??? 🤯
www.businessinsider.com/netflix-film...
$638K on... mattresses! Yes, for real. And not like, 100 mattresses. Two mattresses. 😅
I thought Kickstarter had a few crazy stories like this... but Netflix??? 🤯
www.businessinsider.com/netflix-film...
Netflix show developer to stand trial for $11 million spending spree, including 5 Rolls-Royces, $638,000 in mattresses
Prosecutors say Carl Erik Rinsch defrauded streaming behemoth Netflix out of $11 million for his never-finished sci-fi thriller "White Horse."
www.businessinsider.com
December 4, 2025 at 1:44 AM
This is one of the funniest stories recommended to me ever.
$638K on... mattresses! Yes, for real. And not like, 100 mattresses. Two mattresses. 😅
I thought Kickstarter had a few crazy stories like this... but Netflix??? 🤯
www.businessinsider.com/netflix-film...
$638K on... mattresses! Yes, for real. And not like, 100 mattresses. Two mattresses. 😅
I thought Kickstarter had a few crazy stories like this... but Netflix??? 🤯
www.businessinsider.com/netflix-film...
Reposted by Marc Lanctot
Scholar Inbox in conference mode is soooo useful. Get your poster session recommendations with the poster number and access the paper....
Thanks @andreasgeiger.bsky.social and team!
Thanks @andreasgeiger.bsky.social and team!
December 3, 2025 at 8:41 PM
Scholar Inbox in conference mode is soooo useful. Get your poster session recommendations with the poster number and access the paper....
Thanks @andreasgeiger.bsky.social and team!
Thanks @andreasgeiger.bsky.social and team!
Reposted by Marc Lanctot
Percepta is hiring for research (RL, modeling, OR), engineering, and prod roles in Europe and on the US East Coast. A few of us are at NeurIPS this week. Reach out to myself, Athul Jacob, Christos Tzamos, Guoqing Zheng, Justin Chiu, or Albert Zuo to learn about ML for improving critical instiutions
December 2, 2025 at 4:30 PM
Percepta is hiring for research (RL, modeling, OR), engineering, and prod roles in Europe and on the US East Coast. A few of us are at NeurIPS this week. Reach out to myself, Athul Jacob, Christos Tzamos, Guoqing Zheng, Justin Chiu, or Albert Zuo to learn about ML for improving critical instiutions
Reposted by Marc Lanctot
📌 Mark your calendars: December 5–7, 2025!
Google DeepMind’s Build the Future with Gemini 3 Pro hackathon is going live for two days! 🚀
We’re celebrating the launch of Gemini 3 Pro - Gemini’s most intelligent, capable and versatile model yet.
Google DeepMind’s Build the Future with Gemini 3 Pro hackathon is going live for two days! 🚀
We’re celebrating the launch of Gemini 3 Pro - Gemini’s most intelligent, capable and versatile model yet.
December 2, 2025 at 6:07 PM
📌 Mark your calendars: December 5–7, 2025!
Google DeepMind’s Build the Future with Gemini 3 Pro hackathon is going live for two days! 🚀
We’re celebrating the launch of Gemini 3 Pro - Gemini’s most intelligent, capable and versatile model yet.
Google DeepMind’s Build the Future with Gemini 3 Pro hackathon is going live for two days! 🚀
We’re celebrating the launch of Gemini 3 Pro - Gemini’s most intelligent, capable and versatile model yet.
Reposted by Marc Lanctot
Reposted by Marc Lanctot
Statement by OpenReview on X
November 28, 2025 at 12:04 AM
Statement by OpenReview on X
