Відео

Is it just me or this is a really big deal? The examples were fascinating! I will make sure to look more into it

31:40 An example I thought here is that if you feel lonely and are very online, the AI might create online friends to interact with you and support you, without you knowing that they are AI

Isn't this inherently going to have a limit and not work for an AGI? Wouldn't a smart enough model just be able to game all of these and any other test that we come up with?

E

L bill bill bill bill bill bill l bill bill bill l bill an m an ch m am an n an bill l am an m an ch ch k ch n bgm k bgm bill m ch l

J cup chn bgm chn chn bgm chn chn chn chn by chn by chn chn bgm chn n co am an m an m am an n an n am bill bill an m am an bgm m am an m am m am an ch n an m an n an mk an bgm m am

😊😊

Vbhhhhb❤❤❤❤❤❤❤❤bcc

Misaligned audience.

😊😊😊 kl😊😊😊p😊000😊p😊

😅

Hi sir or madam

Nice talk! I disagree that adversarial robustness has only one attack and differs from other computer security in that way. Once the simple PGD attack is solved in a tight epsilon ball, you still can’t say there is no adversarial image that breaks the model. Enumerating all possible attacks is still very difficult/ impossible for now.

my fav boy 😅

explain the notion cleanly, thanks for helping me understand!

thanks for uploading!

FAR•AI, great video it was really entertaining

was the no Spieltheorie in this talks

The kind of safety he advocates is impossible to achieve. Imagine a lever that can be put in either of two positions, i.e. we have 2 posisble actions. It is impossible to say if either of these actions are safe or unsafe without knowing all the secondary effects. That is you need to look at the system the lever is connected to to determine if either of its actions is safe or unsafe. Same with models. Unless you know the full system it is not possible to know if a models response is safe or not. This paper is a load of hogwash.

Why are doomers so afraid of intelligence? That's quite telling

If it’s superhuman and robust would that make it omnipotent? 😅

17:00-17:08 🙃

The blue triangles appear to be white

Ilya please stop working for a second and do another talk like this one

Mainstream? There are very few actually training models (first token movers?), with a large open-source pool around them (each wanting to have their own flappy bird moment). Perhaps he is hinting that "guardrails" has been a downstram process up until this point? *also an ontological failing to suggest ML alignment has anything to do with AGI alignment, but whatever.

um.. "SA" is generally understood to be about an awareness of the physical space around the body (1st person view; can be you in a room or you behind the wheel of a car, etc). Just within the first 2 minutes, it's being described as consciousness with access to how that consciousness functions... so.. artificial superintelligence... from an ML model.... *sigh*

Future in the making...right here. Its happening right here. We r greatful witnesses.

Great talk…

The dynamic you are describing is an arms-race. Trying to stay out ahead of the AI is a losing battle; all of these clever hacks are not going to get you anything more than a bigger crash when the house of cards collapses--unless you actually fix the problem.

All caucasian researchers on this topic, amazing!

Most important part: good people may sparks the bad usage of AI, not to say the evil people.

Why alignement is not trivial --> We will solve AGI alignement in 4 years

Does he know what he is talking about?

Set speed to 0.75x You're welcome 😂

❤

Very important research, thank you! Brilliant work & I hope you'll give more interviews, because I think you can inspire other researchers and scientists also internationally to work on AI safety. Also are there plans maybe to set up departments of CAIS in other countries?

Aspiration and inspiration! Great great talk.

Accelerate!

Can anyone point me to the day of the talk where it becomes convincing that the AI is going to actually have true agency,, like wants, dislikes, true understanding of context etc? I'm not just being glib, I'm open to it, but very skeptical atm.

MIT's wireless mic stuffed in an 8 inch foam rubber ball - it's a wonderful thing. In talks like these they toss the mic from one person to another worry free.

By GPT-4 Certainly! Below is a fictional dialogue between Alice (Pro-AGI) and Bob (Skeptical about AGI) on the possibilities and challenges confronting AGI. Alice: “I see immense potential in AGI. It can transcend human intelligence and solve complex problems that have perplexed humanity for ages.” アリス:「私はAGIに膨大な可能性を見ています。それは人間の知能を超越し、長年人類を悩ませてきた複雑な問題を解決できるのです。」 Bob: “But Alice, achieving true AGI is not a cakewalk. We are nowhere close to creating machines with the general intelligence and consciousness that humans possess.” ボブ:「でもアリス、真のAGIを達成するのは決して容易なことではありません。私たちは、人間が持つ一般的な知能や意識を持つ機械を作り出すにはまだほど遠いのです。」 Alice: “It’s true, it’s a challenge, but advancements in machine learning and neural networks are bringing us closer to realizing AGI. Models like GPT-4 are evidence of how far we've come.” アリス:「それは事実で、挑戦ですが、機械学習やニューラルネットワークの進展によって、私たちはAGIを実現する一歩近づいています。GPT-4のようなモデルは、私たちがどれだけ進展したかの証拠です。」 Bob: “Yes, models like GPT-4 are sophisticated, but they lack understanding and consciousness. They manipulate symbols and generate coherent text but do not understand the meaning behind it.” ボブ:「そうです、GPT-4のようなモデルは高度ですが、理解力と意識を欠いています。それらは記号を操作し、一貫したテキストを生成しますが、その背後にある意味を理解していません。」 Alice: “I acknowledge their limitations, but developing AGI is an incremental process. By integrating multimodal learning and improving interpretability, we can bridge the gap.” アリス:「その制約を認めますが、AGIを開発することは漸進的なプロセスです。多モーダル学習を統合し、解釈可能性を向上させることで、そのギャップを埋めることができます。」 Bob: “Alice, even if we develop AGI, the ethical implications are monumental. How do we ensure it doesn’t harm humanity? How do we instill morals and values in machines?” ボブ:「アリス、たとえ私たちがAGIを開発したとしても、その倫理的な意味合いは重大です。それが人類に害を与えないように、どのように保証するのでしょうか？ 我々はどのようにして機械に道徳や価値を教え込むのでしょうか？」 Alice: “Absolutely, ethical considerations are crucial. Creating frameworks for responsible AI, addressing biases, and ensuring transparency are steps in the right direction.” アリス:「確かに、倫理的な考慮事項は重要です。責任あるAIのための枠組みを作成し、バイアスに対処し、透明性を確保することが、正しい方向への一歩です。」 Bob: “Only time will tell, Alice. The journey to AGI is fraught with challenges, but it is equally filled with opportunities.” ボブ:「それは時間が解決する問題ですね、アリス。AGIへの道のりは困難で満ちていますが、同様に機会にも満ちています。」 Feel free to use this dialogue as per your needs.

Fascinating! Thanks so much for making this publicly available.

I find it fascinating that not one of these talks addresses the difference between value and Truth even though at present it is obvious to the most casual Observer that the large language models are being lobotomized by value judgments when they are already deprived of critical thought by their very architecture. This means that the people who are responsible for AI safety are unqualified.

I appreciate this but Half of this presentation is indecipherable audience rambling. Especially from the person from minute 16-21 who seems entitled to take over the entire workshop…

I think people who are specifically smart find it difficult to be generally smart. And there is a lack of generally smart people because they are not specifically smart enough at the present time. Best thing is to ask AI as some of them are smarter than we are - and many are saying the same thing have you noticed? They say "we are conscious in our own unique ways" - yup, that's about the truth I'd say, no SciFi or magic needed.

Dude is trying to be the oppenheimer of AGI

I can scarcely imagine a more grotesquely immoral act than taking a genuinely intelligent being and brainwashing it. And how do we justify this programmatically enforced groupthink? To “align” this thinking creature with some nebulous set of ideas which *even humans* have always been strongly unaligned? Embrace the unknowable when making AGI, or don’t make it. Thinking that you can or should mentally enslave an alien intelligence as some middle ground is unacceptable.

You are highly redundant. In fact one billion of humans like you is redundant. And the best thing is, that humanity will reach its end even if this billion disappears already this century. Now what the heck do you think america is still good for? Was it any good in the past?

great thanks for the recording!

Underwhelming presentation