Yoshua Bengio
LightNews LightNews
banner
yoshuabengio.bsky.social
Yoshua Bengio
@yoshuabengio.bsky.social
8K followers 39 following 170 posts

Working towards the safe development of AI for the benefit of all at Université de Montréal, LawZero and Mila.

A.M. Turing Award Recipient and most-cited AI researcher.

https://lawzero.org/en
https://yoshuabengio.org/profile/ .. more

Videos

Yoshua Bengio is a Canadian computer scientist, and a pioneer of artificial neural networks and deep learning. He is a professor at the Université de Montréal and scientific director of the AI institute MILA. .. more

Computer science 91%
Physics 3%
Posts Replies Media Videos
Pinned
yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Jun 3
Today marks a big milestone for me. I'm launching @law-zero.bsky.social, a nonprofit focusing on a new safe-by-design approach to AI that could both accelerate scientific discovery and provide a safeguard against the dangers of agentic AI.
law-zero.bsky.social LawZero - LoiZéro @law-zero.bsky.social · Jun 3
Every frontier AI system should be grounded in a core commitment: to protect human joy and endeavour. Today, we launch LawZero, a nonprofit dedicated to advancing safe-by-design AI. lawzero.org

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · 9d
OpenReview is a pillar of progress in the AI research community. Now it needs our support.

Along with several of my colleagues, I have pledged to help, and I encourage anyone who can to do the same.

openreview.net/donate
OpenReview
Promoting openness in scientific communication and the peer-review process
openreview.net

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · 10d
I recently sat down with Steven Bartlett on the Diary of a CEO podcast to discuss AI risks, and the solutions I’m working on at @law-zero.bsky.social and @mila-quebec.bsky.social to create a better path forward.

www.youtube.com/watch?v=zQ1P...
Creator of AI: We Have 2 Years Before Everything Changes! These Jobs Won't Exist in 24 Months!
YouTube video by The Diary Of A CEO
www.youtube.com

Reposted by Yoshua Bengio

Reposted by Yoshua Bengio

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · 12d
You can watch my TED Talk here: www.ted.com/talks/yoshua...
The catastrophic risks of AI — and a safer path
Yoshua Bengio — the world's most-cited computer scientist and a "godfather" of artificial intelligence — is deadly concerned about the current trajectory of the technology. As AI models race toward fu...
www.ted.com

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · 12d
I am encouraged to see that the urgency of tackling AI risks is resonating with such a wide audience.
Thank you to TED for the chance to share why we need to prioritize safety in AI, and my vision for a safer path forward.
www.ted.com/playlists/88...
Most popular TED Talks of 2025 | TED Talks
Here are the talks everyone couldn’t stop watching in 2025. From how to spot deepfakes and read minds to breakthroughs in robotics and longer-lasting produce, these ideas captured attention — and spar...
www.ted.com

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · 17d
TIME recently invited me to share my perspective on the past year in AI development.
We've seen major growth in AI capabilities & risks, but as
@law-zero.bsky.social continues its research, I'm increasingly confident that technical solutions are possible to make AI safer.
time.com/7339687/yosh...
We're Not Ready for AI's Risks
It’s possible that we’re nearing the limits of our current approach to frontier AI, says Yoshua Bengio
time.com

Reposted by Yoshua Bengio

Reposted by Yoshua Bengio

Reposted by Yoshua Bengio

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Nov 26
We're glad to have you at LawZero, Iulian. Bienvenue dans l'équipe!
law-zero.bsky.social LawZero - LoiZéro @law-zero.bsky.social · Nov 26
We are thrilled to welcome Iulian Serban to LawZero as Senior Director, Research and Development.

As former founder of Korbit, he brings deep expertise in GenAI, software security, and research to our mission.

Full press release: lawzero.org/en/news/lawz...

Reposted by Yoshua Bengio

law-zero.bsky.social
LawZero - LoiZéro @law-zero.bsky.social · Nov 26
We are thrilled to welcome Iulian Serban to LawZero as Senior Director, Research and Development.

As former founder of Korbit, he brings deep expertise in GenAI, software security, and research to our mission.

Full press release: lawzero.org/en/news/lawz...

Reposted by Yoshua Bengio

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Nov 25
For example, research shows that:
· When given 10 attempts, attackers can use malicious prompts to bypass leading systems' safeguards about half the time.
· Inserting as few as 250 malicious documents into a model's training data can introduce vulnerabilities.
(6/6)

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Nov 25
Yet significant challenges remain and the real-world effectiveness of many safeguards is uncertain. ⬇️
(5/6)

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Nov 25
· A growing number of companies adopting Frontier AI Safety Frameworks, describing safety and security measures they will take as their AI models become more capable,
· Technical safeguards are beginning to inform transparency measures in governance frameworks.
(4/6)

yoshuabengio.bsky.social
Yoshua Bengio @yoshuabengio.bsky.social · Nov 25
Over the past year, we’ve seen meaningful progress:
· Improvements in adversarial training methods to make models more resistant to potentially harmful requests,
· Better tools for tracking AI-generated content.
(3/6)