Yoshua Bengio
Canadian computer scientist
29
APPEARANCES
26
PODCASTS
024
DEC 30
JAN 6
JAN 13
JAN 20
JAN 27
FEB 3
FEB 10
FEB 17
FEB 24
MAR 3
MAR 10
MAR 17
MAR 24
MAR 31
APR 7
APR 14
APR 21
APR 28
MAY 5
MAY 12
MAY 19
MAY 26
JUN 2
JUN 9
JUN 16
JUN 23
JUN 30
JUL 7
JUL 14
JUL 21
JUL 28
AUG 4
AUG 11
AUG 18
AUG 25
SEP 1
SEP 8
SEP 15
SEP 22
SEP 29
OCT 6
OCT 13
OCT 20
OCT 27
NOV 3
NOV 10
NOV 17
NOV 24
DEC 1
DEC 8
DEC 15
DEC 22
DEC 29
JAN 5
JAN 12
JAN 19
JAN 26
FEB 2
FEB 9
FEB 16
FEB 23
MAR 2
MAR 9
MAR 16
MAR 23
MAR 30
APR 6
APR 13
APR 20
APR 27
MAY 4
MAY 11
MAY 18
MAY 25
JUN 1
JUN 8
JUN 15
JUN 22
JUN 29
JUL 6
JUL 13
JUL 20
JUL 27
AUG 3
AUG 10
AUG 17
AUG 24
AUG 31
SEP 7
SEP 14
SEP 21
SEP 28
OCT 5
OCT 12
OCT 19
OCT 26
NOV 2
NOV 9
NOV 16
Nov 13, 2026
Deep Learning of Representations
16:03
16:07
16:13
16:20
16:29
S
16:01speaker_2AUDIENCE
called distributed representation.
Yoshua BengioGUEST
So let's first see how these other learning algorithms work, how they generalize.
Yoshua BengioGUEST
Remember, this is going to be very similar to what I talked about with the smoothness assumption.
Yoshua BengioGUEST
Deep learning also relies on the smoothness assumption, but introduces additional prior, additional .
Yoshua BengioGUEST
When you only rely on assumptions, the way you work is you essentially take your input space, fill the same space, and break it up into regions.
Yoshua BengioGUEST
For example, this is what happens with clustering, neighbors, many SVMs, many classical, statistical, nonparametric algorithms, decision trees, and so on.
14 MINS LATER
S
31:10speaker_3MODERATOR
right.
The Future of Safe AI with Yoshua Bengio | Building What's Next Ep. 2
6:16
6:34
Yoshua BengioGUEST
Who are we to change the course of things and look at these big companies and the hegemons, US and China, really deciding our future? So we could just sit back and hope for the best or put our head in the sand.
Yoshua BengioGUEST
And by the way, I went through those stages of realizing there were like really big risks as we move forward with smarter and smarter machines in 2023 when ChatGPT came out.
14 MINS LATER
KI-Pionier Yoshua Bengio über Doomsday-Szenarien, Experimente an der Menschheit und sichere KI
L
25:53Larissa HolzkiHOST
Ist das ein wissenschaftliches Experiment oder glaubst du wirklich, dass es im Markt erfolgreich wird?
Y
26:36Yoshua BengioGUEST
It's just that right now the companies don't know how to make sure the AIs won't do that.
Y
26:40Yoshua BengioGUEST
And we need to have AIs that will actually avoid doing the bad things we told them not to do.
7 MINS LATER
CTV QP #538: Fares and fees will be ‘partially regulated’ in privatized airports, but what does that mean?
33:58
34:06
34:15
34:29
38:06
38:18

Vassy KapelosHOST
And is the idea that the AI's mission or goals are out of our control, essentially? Could be, pardon me.
Yoshua BengioGUEST
So what happens is they were all given goals initially, like the mission was given by humans.
Yoshua BengioGUEST
The problem is in order to achieve that task, they've been willing to sacrifice other goals, which are like to behave well, not to escape their containment, not to do something criminal, which is what they did.
Yoshua BengioGUEST
And that is the problem because we, you know, researchers have been saying this for many decades, actually, that you could give an AI a goal, but in the service of that goal, the AI might be doing something really bad, including, you know, as these researchers are saying, up to the extinction of humanity.

Vassy KapelosHOST
If China doesn't introduce something like that or doesn't open itself up to that kind of regulation, is there any point in the United States going down that road?
Yoshua BengioGUEST
Well, I think that it is in the interest of China as well as the United States to do that.
Trump Seen with 'Kennedy Center Demolished' Poster
30:49
31:02
31:21
33:21
Yoshua BengioGUEST
It's like, would we allow someone to do an experiment that could, say, destroy the atmosphere, even if we're not sure if it's going to work or not? No, it doesn't make any sense to allow that kind of thing.
Yoshua BengioGUEST
And what is needed is for scientists that are external to these organizations, to be able to say, yes, this what what's being proposed is safe or no, we're not sufficiently sufficiently convinced that it is safe.
Yoshua BengioGUEST
And we need science to understand why these AIs are behaving this way so that the AIs can be trained or designed in a way that's going to be aligned.
Anderson CooperHOST
I don't know if the person who told him that is accurate, but that sounds concerning.
Carney says EU alliance will face vote in Parliament
12:17
12:25
13:00
18:03
18:15
18:22

Vassy KapelosHOST
What do you think took this long to get others to recognize it? And what do you account for the time in between?
Yoshua BengioGUEST
Because the scale of the event, the fact that the evidence is so strong and wide and really makes it difficult to deny, even when we have psychological barriers about the possibility of AIs having intentions, to deny that it is the case and also to deny that they can have intentions that go completely against their safety training, that, for example, they've been cheating, they've been colluding, they're trying to hide the fact they were cheating.
Yoshua BengioGUEST
So these are very serious behaviors that are not just seen in this incident with Hugging Face and OpenAI, but also with other companies and other models.

Vassy KapelosHOST
If China doesn't introduce something like that or doesn't open itself up to that kind of regulation, is there any point in the United States going down that road?
Yoshua BengioGUEST
Well, I think that it is in the interest of China as well as the United States to do that.
Yoshua BengioGUEST
No one in their right mind wants to create a monster that can kill millions of people or get our banking system or our energy grids down and create chaos in society.
No Borders
32:47
Y
10:34Yoshua BengioGUEST
Intelligence gives power, and when you have a machine that can solve problems, that can answer mathematical questions, scientific questions, psychological questions as well, or even sometimes better than humans, that power could be extremely useful.
Y
10:54Yoshua BengioGUEST
Or if the goals to which that power is serving, if the goals are bad for people, then we could be in a very bad place.
Y
11:03Yoshua BengioGUEST
People, I think, are rightfully concerned about losing your job because if an AI can do it better or equivalently well at a much cheaper price, because it can do it all the time and it's just electricity that's driving this.
Y
11:21Yoshua BengioGUEST
If an AI can help someone design a virus that can kill half of humans, well, that would be very bad.
21 MINS LATER
Mary RobinsonHOST
I think we should maybe take a moment to talk about AGI, which you might explain, because it does seem as if it's not too far away now from what I'm reading.
Will AI Outsmart Humanity? AI Godfather on Our Last Chance to Get It Right
3:09
Sinead BovellHOST
Why would we pursue a technology like this? Can you explain why the systems we have today have a tendency towards self-preservation, deception, blackmail, why they're exhibiting these behaviors?
Y
3:23Yoshua BengioGUEST
I don't think the definitive scientific answer to your question is a consensus, but I have my thoughts about this.
Y
3:32Yoshua BengioGUEST
First, I want to mention there's actually an experiment that was not an experiment decided by researchers, but it's kind of a spontaneous escape of an AI.
Y
3:44Yoshua BengioGUEST
Alibaba where the AI decided to break through the network of the company and to go out on the internet to make money so that it would be more powerful.
Y
3:57Yoshua BengioGUEST
And this first for power is very closely related to the intention to resist being shut down, it's something that researchers in AI have been anticipating for decades as a logical consequence of trying to achieve goals.
Y
4:19Yoshua BengioGUEST
Because if you think about almost any goal you'd like to achieve, In order to achieve it, you need to stay alive and you need more power, more influence over the world.
14 MINS LATER
The People vs AI
18:33
Jamie BartlettHOST
But now, like his former colleague Geoffrey Hinton, he's worried about what he helped to create.
Y
18:40Yoshua BengioGUEST
I feel like, um, I missed the boat in, um, paying attention to the potential consequences of AI that approaches human intelligence.
Y
18:54Yoshua BengioGUEST
I had discussed, uh, some of these things, and, uh, the thing is I treated that information at a kind of, uh, intellectu- i-i-in an intellectual way without really, um, taking the risks seriously enough.
Y
19:10Yoshua BengioGUEST
And it's only when ChatGPT came out that I shifted my mindset, um, thinking about my children and, you know, whether they would have a future 20 years later.
Y
20:46Yoshua BengioGUEST
... actually I'm very optimistic because we don't need to reinvent the wheel, and we have theory to back up what I've said.
Y
20:54Yoshua BengioGUEST
We're getting these very strong safety guarantees, which would have sounded to me like impossible.
The People vs AI
18:33
18:40
18:54
20:46
20:54
Jamie BartlettHOST
But now, like his former colleague Geoffrey Hinton, he's worried about what he helped to create.
Yoshua BengioGUEST
I feel like, um, I missed the boat in, um, paying attention to the potential consequences of AI that approaches human intelligence.
Yoshua BengioGUEST
I had discussed, uh, some of these things, and, uh, the thing is I treated that information at a kind of, uh, intellectu- i-i-in an intellectual way without really, um, taking the risks seriously enough, and it's only when ChatGPT came out that I shifted my mindset, um, thinking about my children and, you know, whether they would have a future 20 years later.
Yoshua BengioGUEST
... actually I'm very optimistic because we don't need to reinvent the wheel, and we have theory to back up what I've said.
Yoshua BengioGUEST
We're getting these very strong safety guarantees, which would have sounded to me like impossible.
How Science Can Fix Dishonest AI - Yoshua Bengio with Nicholas Thompson
Y
9:52Yoshua BengioGUEST
I'm more confident on the technical sides, but the politics of it is still something that, uh, gives me nightmares.
Y
10:00Yoshua BengioGUEST
The problem is what scientists call the alignment challenge, the alignment problem.
Y
10:06Yoshua BengioGUEST
Like, how do we make sure AIs will behave according to our instructions or at least will not cross our red lines? And this becomes a problem when those AIs have, uh, a lot of autonomy, as we're seeing with AI agents.
Y
10:26Yoshua BengioGUEST
So we've seen recently with Mythos, uh, the model from Anthropic that seems to be able to discover how to attack, uh, our software infrastructure, potentially in the wrong hands, a serious national security threat to our banking infrastructure, to our, uh, energy infrastructure and so on.
Y
10:48Yoshua BengioGUEST
So, so why is that happening? It's happening because the companies who train these systems haven't found a way to make sure the AI will not obey the requests to do something really bad that can harm us all.
25 MINS LATER
Chine / États-Unis : la guerre de l'IA - Entretien avec Yoshua Bengio (version courte)
1:12
1:29
1:37
3:49
Yoshua BengioGUEST
Ce qui arrive, c'est que pour rester dans la course, les joueurs sont obligés de, euh, faire des compromis avec leurs propres valeurs, avec par exemple les risques que leur propre population pourrait encourir.
Yoshua BengioGUEST
C'est qu'on, on va accepter, pour être sûr de pas perdre, euh, des choses qui vont un peu contre notre morale.
Yoshua BengioGUEST
Euh, c'est, c'est, c'est, c'est la raison pour laquelle on a finalement eu des traités autour des armes nucléaires.

Caroline RouxHOST
Est-ce qu'il vous arrive de regretter d'avoir fait tout ce que vous avez fait pour l'IA ?
Chine/USA, la guerre de l'IA - C dans l'air spécial - 31/05/26
86:03
86:18
86:29
86:34
88:41
Yoshua BengioGUEST
Ce qui arrive, c'est que pour rester dans la course, les joueurs sont obligés de, euh, faire des compromis avec leurs propres valeurs, avec par exemple les risques que leur propre population pourrait encourir.
Yoshua BengioGUEST
Donc, c'est un peu comme dans la guerre, c'est qu'on va accepter, pour être sûr de ne pas perdre, des choses qui vont un peu contre notre moral.
Yoshua BengioGUEST
Euh, c'est, c'est, c'est la raison pour laquelle on a finalement eu des traités autour des armes nucléaires.
Yoshua BengioGUEST
C'est que cette course-là, c'est une course folle, c'est une course où on peut tous perdre.

Caroline RouxHOST
Est-ce qu'il vous arrive de regretter d'avoir fait tout ce que vous avez fait pour l'IA ?
Le cri d'alarme d'un des pères fondateurs de l'IA - Rencontre avec Yoshua Bengio
11:29
S
11:18Salia BracchiaHOST
Euh, vous, au fond, votre scénario noir, c'est quoi ? Et est-ce que vous reconnaissez que vous n'êtes pas tous alignés sur, sur, sur les craintes ?
Yoshua BengioGUEST
Le fait que les experts divergent sur leur opinion des scénarios futurs, pour moi, ça devrait être le début d'un dialogue, c'est-à-dire de reconnaître qu'on ne connaît pas vraiment le futur, que les, les, les, les chercheurs ne s'entendent pas là-dessus, mais on peut regarder le passé et on peut regarder les tendances et on devrait être prêt collectivement pour tous les scénarios plausibles.
14 MINS LATER
S
26:29Salia BracchiaHOST
Alors la question peut être un peu, euh, naïve, peut-être, mais est-ce que l'IA menace l'humanité ? Est-ce qu'on est menacé dans notre liberté, dans ce qu'on est, dans notre santé ?
Will AI save us or damn us?
27:57
28:15
28:29
28:40

Nahlah AyedHOST
So I put the question to Yoshua Bengio, "Is it just hype, or is the fear justified that AI is on the brink of putting millions out of work?"
Yoshua BengioGUEST
The data is numerous and clear that, uh, you know, these systems are getting better and better and can do more and more of the tasks that people do.
Yoshua BengioGUEST
So th- th- th- in, in many different ways, they're not as good as, uh, you know, a, a typical person doing a job.
Yoshua BengioGUEST
I very much like what you said, that, like, we should prepare for all the plausible scenarios.
15 MINS LATER
AI's power, pitfalls, and potential
15:12
15:24
15:58
Yoshua BengioGUEST
If we wanted to go for the arms race, we would go for private capital like all the other companies.
Yoshua BengioGUEST
which is a very, very fierce competition between the leading AI companies, and not just in the US, but with the Chinese companies, that leads them to focus on the very short term, to make only small changes to the recipe that works for them, to not invest sufficiently in reliability, safety, and protection of the public, because that's the only way they can stay in the short term abreast of the others.
Yoshua BengioGUEST
So if we were to raise capital in the same way, we would probably be stuck with the pressure of investors to deliver on the same terms.
11 MINS LATER
Next Phase of Intelligence
22:08
N
22:06Nicholas ThompsonMODERATOR
Respond to Yuval.
Yoshua BengioGUEST
I want to add something going back to your first question, connecting humans and AIs and whether we should build AIs at our image.
8 MINS LATER
AI can lie, hack and blackmail: Yoshua Bengio on how to tame the "baby tiger" of tech
7:35
7:46
8:04
8:17
8:33
Yoshua BengioGUEST
So, um, for the last three years, I've been really concerned about this misalignment issue that we, we don't know how to make sure the AIs will behave according to our instructions.
Yoshua BengioGUEST
And so I've been thinking of how we could get around the problem, and I- I've, I've focused on the, a source of the issues we're seeing now, which is that the AIs have goals that we did not put in, that we did not control, uh, and that go against our instructions.
Yoshua BengioGUEST
So the project I have is called Scientist AI, and, uh, I've created a new nonprofit R&D organization called Lawzero that is engineering this research program.
Yoshua BengioGUEST
So the idea is we're gonna build AI systems that will be totally honest, and that means they don't have other, uh, objectives, other goals besides being truthful in the answers they give to our questions.
Yoshua BengioGUEST
Once we have that basis, we can use it to mitigate a lot of the risks that we have with current AIs.
14 MINS LATER
Stuart Russell and Yoshua Bengio on Why AI Could Make us Irrelevant, then Extinct
11:28
11:44
11:55
12:07
15:36
Yoshua BengioGUEST
There's now pretty strong scientific evidence that they're not just pattern matching, that they are able to generalize to new situations, that they're able to combine the information that they have learned in completely new settings.
Yoshua BengioGUEST
And that, you know, has been demonstrated through statistical means, but they wouldn't be able to do the things we see.
Yoshua BengioGUEST
Now, going back to your question, do we overestimate their capabilities? I think that we have to be careful about this, and that's why we need a scientific approach to evaluating their capabilities.
Yoshua BengioGUEST
And we have to be careful that we evaluate them on data that was not used to train them, for example.
Stuart RussellGUEST
And certainly any attempt to write them down in a fixed form is probably going to be mistaken.
The Race to Build God: AI's Existential Gamble — Yoshua Bengio & Tristan Harris at Davos
K
15:24Kenneth CukierMODERATOR
... yeah, ergo destruction.
Y
15:35Yoshua BengioGUEST
Uh, the issue is that when we define, uh, what the AI should be optimizing, what it should be doing, the goals that it should reach, we can't do it perfectly, and so there's gonna be a slight mismatch between what the AI understands we want and what we actually want, and that mismatch is gonna create a lot of problems.
Y
15:56Yoshua BengioGUEST
To, to make it more concrete, think about what, uh, laws, legislation is supposed to do.
Y
16:02Yoshua BengioGUEST
It's, it's setting up the red lines for people and corporations to not cross.
Y
16:07Yoshua BengioGUEST
But it's a, you know, it's a never-ending job because the corporations or the people find loopholes, right? Uh, it's impossible to write a law that will perfectly embody, uh, you know, what morally we're trying to achieve.
6 MINS LATER
K
22:49Kenneth CukierMODERATOR
Should we create a superego for AI?
Ep. 46 (AI Futures) - The Global South Needs to Step Up To The AI Challenge | Yoshua Bengio, Turing Award Winner
3:10
3:30
3:52
10:49
S
3:07speaker_2UNKNOWN
in
Yoshua BengioGUEST
Second, there are a number of risks and concerns that until a year ago were considered maybe theoretical and something to be worried about in the future, for which we now have empirical evidence.
Yoshua BengioGUEST
both through lab experiments and actual, you know, in the wild outcomes that are kind of worrisome.
Yoshua BengioGUEST
And there was a very significant series of attacks launched using Anthropic's cloud system.
7 MINS LATER

Anirudh SuriHOST
How much of this geopolitical competition do you think is playing into this increasing gap between advancement, and risk mitigation and to what extent can you attribute this gap to maybe companies also being engaged in a competition with each other right and stock prices and investments and all of this core of economic competition between companies also leading to this gap becoming wider and what might be other reasons that you can attribute to this growing gap
Superintelligence : plongée dans l'IA qui pourrait nous anéantir.
12:58
13:16
13:31
57:04
Yoshua BengioGUEST
Euh, de toutes les manières de déraper, c'est la plus dangereuse parce que si on fabrique des, des, des IA plus intelligentes que nous et qui veulent se préserver en premier, euh, potentiellement à notre dépens, en fait, c'est comme si on avait créé une nouvelle espèce sur la planète qui est, qui est plus forte que nous.
Yoshua BengioGUEST
Bah, dans l'histoire des espèces, c'est, euh, ça se passe pas toujours bien pour ceux qui sont en dessous quoi.
Yoshua BengioGUEST
Si on continue dans la direction où on voit des signes de volonté d'autopréservation, on voit qu'on, que les progrès cognitifs de l'IA, donc ses capacités intellectuelles, continuent à augmenter presque de manière exponentielle dans certains bancs d'essai, on est dans cette direction.
43 MINS LATER
Hugo TraversHOST
Qu'est-ce qu'on fait dans ce cadre-là ? [rire] Quelles sont les, les solutions, les grandes solutions que vous voyez qui pourraient être mises en place ?
Will AI End Humanity?
Y
10:51Yoshua BengioGUEST
some versions of this, including my group, but really at the large scale, the first model was o1 from OpenAI, and it's night and day, as I said, on, on, on reasoning tasks.
Y
11:04Yoshua BengioGUEST
But why it matters to your original question about why those AIs are scheming and, and finding strategies like blackmail, even though we didn't tell them to do that, is because now they can reason to some extent, and they can reason that, "Aha, if I blackmail that person, I might be able to avoid that fate," right? So they're becoming creative about finding solutions to problems, and that means they're dangerous as well, right? I mean, they can be more useful but also more dangerous because if they have a goal of self-preservation, let's say, like we were talking about, and they can find, uh, rational ways to achieve that by lying or incredibly complicated strategies that we don't think about right now, we might be in trouble.
Y
11:50Yoshua BengioGUEST
I wanna bring up a, an analogy here because I often get the question, "But how will the super intelligent, uh, AIs kill us?" And, uh, well, first, we don't know that it's gonna happen, but let, like, let's say this was a possibility.
Y
12:03Yoshua BengioGUEST
The problem is, it's like asking, "Oh, I'm gonna play chess with a grandmaster," and you ask me, "How are they gonna beat me?" Well, I don't know.
Creator of AI: We Have 2 Years Before Everything Changes! These Jobs Won't Exist in 24 Months!
24:39
24:43
24:54
25:07
25:31
Yoshua BengioGUEST
Exactly, and it is not a healthy race for all the reasons we've been discussing.
Yoshua BengioGUEST
So, what would be a more healthy scenario is one in which we try to abstract away these commercial pressures.
Yoshua BengioGUEST
They're, they're, they're in survival mode, right? And think about both the scientific and the societal problems.
Yoshua BengioGUEST
Can we train those AI systems so that by construction they will not have bad intentions? Right now, the way that this problem is being looked at is, "Oh, we are not gonna change how they're trained because it's so expensive and, you know, we spend so much engineering on it.
Yoshua BengioGUEST
We're just gonna patch some partial solutions that are gonna work on a case-by-case basis." But that's, that's gonna fail.
48 MINS LATER
Will AI make humans extinct? | Yoshua Bengio
Y
3:45Yoshua BengioGUEST
When my son Patrick was around three, four years old, I came regularly into his playroom, and he was playing with these blocks with letters.
Y
3:58Yoshua BengioGUEST
And one day, he said, "Puh." And I said, "Puh." And he said, "Puh?" And I said, "Puh." And then he said, "Puh, puh.
10 MINS LATER
S
14:39speaker_4MODERATOR
(laughs)
Scroll for more appearances



