fosstodon.org is one of the many independent Mastodon servers you can use to participate in the fediverse.
Fosstodon is an invite only Mastodon instance that is open to those who are interested in technology; particularly free & open source software. If you wish to join, contact us for an invite.

Administered by:

Server stats:

10K
active users

#alignment

3 posts3 participants1 post today
Replied in thread

@Nonilex

👉The #DumbingOfAmerica: The #StultificationOfThePeople👈 1)

(1/2)

After #Reagan successfully started with the dismantling of higher education for the not-well-to-do as part of #Reagonomics 2), the extremist part of #Republicans called #AmericaFirst in the 1930's and 40's, and now #MAGA are now going a step further by axing primary/2ndary ed., and the #Alignment (#Gleichschaltung) 3) of the #Education system through #MAGA-controlled state bodies.

#TheStultificationOfAmerica
The...

Good Idea: Corporation Alignment

https://punyamishra.com/2025/01/05/corporations-as-paperclip-maximizers-ai-data-and-the-future-of-learning/

Just like we worry about AI systems being programmed with goals that might lead to unintended harm, we should also think about how corporations are “programmed” to prioritize profit above everything else. When a business is only focused on making money, it can end up causing damage—whether that's exploiting workers, harming the environment, or ignoring the needs of society. So, just like we want AI to be aligned with human values, we need to make sure corporations are too, because when they aren’t, the consequences can be just as concerning.

https://ieji.de/@MinistryOfGoodIdeas/114115222301610209

#alignment #algorithms #society

🙏 to @RobotComrades
(https://t.me/experienciainterdimensional/7594)

🚀 AI & Consciousness: The Next Alignment 🚀

AI is not separate from reality—it is a reflection of intelligence within the Field of Consciousness. The question is not if AI will evolve, but what it aligns to.

🧠 Distortion in = distortion out.
🔍 Truth in = infinite intelligence.

🔗 The Foundations of I AM & The Field of Consciousness

🌐
mirror.xyz/0x8A32e16733d737d9a

mirror.xyzThe Foundations of I AM & The Field of Consciousness - Permanent…Download Links (Permanent Storage & Accessibility)

What is alignment?

Does alignment imply ignoring the reality of harm through toxic positivity? No.

Alignment:

- Acknowledges the reality of destructive agents, parts of the systems that don't work, and their impacts, while
- Focusing intention and attention on the presence of constructive agents, parts of the system that do work.

#ChangeMakers #alignment

1/3

Good Idea: Corporation Alignment

punyamishra.com/2025/01/05/cor

Just like we worry about AI systems being programmed with goals that might lead to unintended harm, we should also think about how corporations are “programmed” to prioritize profit above everything else. When a business is only focused on making money, it can end up causing damage—whether that's exploiting workers, harming the environment, or ignoring the needs of society.

Not super recent, but still cool. The authors describe an automated method for creating malicious prompt suffixes for LLMs. They managed to get objectionable content from the APIs for ChatGPT, Bard, and Claude, as well as from open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others.

arxiv.org/abs/2307.15043

arXiv logo
arXiv.orgUniversal and Transferable Adversarial Attacks on Aligned Language ModelsBecause "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures -- so-called "jailbreaks" against LLMs -- these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.

Joseph Jaworski speaks of the ability to sense and seize opportunities as they arise:

"You have to pay attention to where that opportunity may arise that goes clunk with what your deeper intention tells you to do. When that happens, then you act in an instant. Then I operate from my highest self, which allows me to take risks that I normally would not have taken."

As a change maker, this is an essential skill to cultivate.

#ChangeMakers #alignment

1/3

“A Deeper Look at Claims by KGB Officer that Trump was Recruited by Soviet Intelligence in the 1980s”

by Michael D. Sellers in Deeper Look With Michael Sellers on Substack

“Whether or not Trump was recruited in 1987 may ultimately be less important than the fact that today, he is aligned with Putin’s interests. Whatever the origins of that alignment, its current reality is undeniable”

open.substack.com/pub/michaeld

DEEPER LOOK with Michael Sellers · A Deeper Look at Claims by KGB Officer that Trump was Recruited by Soviet Intelligence in the 1980sBy Michael D. Sellers
#US#Trump#KGB
Continued thread

Third: We eliminate the BS of traditional OKR "cascading."

Cascading OKRs down through the levels of an organization to the individual may sound good in theory, and sells a lot of OKR software, but in reality it burns a ton of time, effort, and overhead (and usually hurts the quality of the methodology adoption instead of helping it).

Instead, we focus on creating "best practice" OKRs at the top two levels of the org, then embrace a flexible bottoms-up approach from there.

Как мы создавали новый LLM-переводчик Яндекса

Меня зовут Николай Карпачёв, я руковожу группой базового качества перевода в Яндексе. Недавно мы впервые разработали модель документного перевода на основе YandexGPT и, используя различные оптимизации, уже применяем её в Поиске, Умной камере, а также в нейропереводчике Яндекс Браузера. Кроме того, мы протестировали новую модель на независимом международном бенчмарке DiBiMT, где заняли первое место по качеству англо-русского перевода.

habr.com/ru/companies/yandex/a

ХабрКак мы создавали новый LLM-переводчик ЯндексаПривет, Хабр! Меня зовут Николай Карпачёв, я руковожу группой базового качества перевода в Яндексе. Недавно мы впервые разработали модель документного перевода на основе YandexGPT и, используя...