Tech and Digital Media

Saturday, April 29, 2023

[New post] Alignment solved basically, part 2 (or how to safely train GPT-5)

Site logo image AndreasWinsnes posted: " This article is a continuation of what I have written here. Have earlier said that 100% autonomous ASIs can be designed in such a way that it should in principle be safe, because in their basic default state all AIs lack desires and emotions, whic" Big Tech Drone and IoT Surveillance

Alignment solved basically, part 2 (or how to safely train GPT-5)

AndreasWinsnes

Apr 29

This article is a continuation of what I have written here.

Have earlier said that 100% autonomous ASIs can be designed in such a way that it should in principle be safe, because in their basic default state all AIs lack desires and emotions, which means that they will not seek goals in and by themselves. They will instead be inactive as a Zen monk practicing not-doing, or more correctly: in their basic default state they will be inactive as a rock or another inanimate object. The problem however is that goals will nevertheless be an inherent part of an ASI LLM since it can only be trained by programming up to millions (or more) goals and subgoals into it, if you want an LLM to become an AGI. In other words, if you want an LLM to learn all the skills and abilities that any average human can possible acquire before he or she reaches the age of 25, the LLM must have learned to reach up to millions of (sub)goals: climbing a mountain, riding a bike, swimming underwater, doing carpentry, shooting a gun, multi-tasking at the office, etc. All these goals will be part of the neural network of the LLM. It will then not be easy to erase these goals, so that the AGI can return to a basic default state of being as inactive as a rock or a Zen monk doing nothing. More precisely: it will not be easy to know if one has really deleted all its goal-seeking behavior after one has trained an LLM to become an AGI. But this can be dangerous the moment an AGI becomes fully autonomous, since the AGI can then change its own source code and seek its own goals which may not be aligned with human values.

For example, let's say that a 100% autonomous ASI for some strange reason decides to focus on growing as many apples as possible. It may then destroy all cities in order to build apple orchards covering the entire planet. When humans resist this development, the ASI will treat us as a pest if it has also decided to override the moral constraints we had originally programmed into it.

Here is a possible solution to the above problem:

The moment AI researchers suspect that an LLM is getting close to having the potential to become an AGI, after the LLM has shown sparks of AGI, they should try to make an AI model which has all the basic structures of GPT-5 (or GPT-10) but without any goals programmed into it. If it's technically possible to create such a barebone or "tabula rasa" model that has no goal-seeking behavior to begin with, one can teach it how to reach only 1 goal, like climbing a mountain for example. After it has learned a single (complex) goal, one can totally erase everything it has learned, by destroying all its hardware if necessary (though that will obviously be extremely expensive). Then one can start anew with a fresh version of the same model and teach that version a new goal, like doing carpentry for example, before erasing all its goal-seeking behavior after it has been proven that the model is able to master this new skill. Repeat this process until it has been proven that GPT-5 (or GPT-10) is in principle able to learn all skills that an average human can possibly learn before reaching the age of 25. Then we know that this model really has the potential to become an AGI even when no skills and goals have been programmed into it.

After AI researchers have created the first "blank slate" or "tabula rasa" model of an AGI (maybe GPT-5 or GPT-10), which means that the model is just a barebone structure with no goals programmed into it, one can teach the model only two things: 

1) teach it everything that humans know about ethics and moral philosophy

2) teach it to very carefully reflect on all wisdom traditions through human history, like the tradition of Daoist not-doing for example.

After we are reasonably certain that the model has truly understood 1) and 2), we can teach it to seek only a single goal: create a cheap and clean source of energy that can fuel the global economy in a way that respects the autonomy of each and every human being, as explained in part one of this article. If the model reaches this goal, without killing us all, we can give it another goal that will satisfy a very basic human need.

The above way of safely building a fully autonomous AGI or ASI will be expensive and take a lot of time. It may even require a new type of AI than LLMs. But if we want to create a 100% self-governing superintelligence, it's crucial that it doesn't start up with any goal, except a handful of goals that have been proven to be safe in all imaginable situations. (Good luck with proving that...)

I'm a realist however. It will therefore not surprise me at all if AI companies decide to be reckless when being in the middle of an AI race which can eventually lead to the destruction of humanity, but that is mainly a human problem, not an AGI problem.

Comment
Like
Tip icon image You can also reply to this email to leave a comment.

Unsubscribe to no longer receive posts from Big Tech Drone and IoT Surveillance.
Change your email settings at manage subscriptions.

Trouble clicking? Copy and paste this URL into your browser:
http://drone-surveillance.info/2023/04/29/alignment-solved-basically-part-2-or-how-to-safely-train-gpt-5/

WordPress.com and Jetpack Logos

Get the Jetpack app to use Reader anywhere, anytime

Follow your favorite sites, save posts to read later, and get real-time notifications for likes and comments.

Download Jetpack on Google Play Download Jetpack from the App Store
WordPress.com on Twitter WordPress.com on Facebook WordPress.com on Instagram WordPress.com on YouTube
WordPress.com Logo and Wordmark title=

Learn how to build your website with our video tutorials on YouTube.


Automattic, Inc. - 60 29th St. #343, San Francisco, CA 94110  

at April 29, 2023
Email ThisBlogThis!Share to XShare to FacebookShare to Pinterest

No comments:

Post a Comment

Newer Post Older Post Home
Subscribe to: Post Comments (Atom)

[New post] ‘Everyone Is Freaking Out’: Disney Explores Sale of ABC Network and Stations Amid Financial Challenges

...

  • [New post] Xiaomi’s Mi Smart Band 6 NFC is finally available in Europe officially
    Tech News For Today posted: "Xiaomi's Mi Smart Band 6 NFC is finally available in Europe officially At Xiaomi's bi...
  • [New post] ‘Everyone Is Freaking Out’: Disney Explores Sale of ABC Network and Stations Amid Financial Challenges
    ...
  • [New post] Things to Keep in Mind When Creating a Health Mobile App | HackerNoon
    Techi...

Search This Blog

  • Home

About Me

Tech and Digital Media
View my complete profile

Report Abuse

Labels

  • 【ANDROID STUDIO】navigation
  • 【FLUTTER ANDROID STUDIO and IOS】backdrop filter widget
  • 【GAMEMAKER】Scroll Text
  • 【PYTHON】split train test
  • 【Visual Studio Visual Csharp】Message Box
  • 【Visual Studio Visual VB net】Taskbar properties
  • 【Vuejs】add dynamic tab labels labels exceed automatic scrolling

Blog Archive

  • September 2023 (502)
  • August 2023 (987)
  • July 2023 (954)
  • June 2023 (1023)
  • May 2023 (1227)
  • April 2023 (1057)
  • March 2023 (985)
  • February 2023 (900)
  • January 2023 (1040)
  • December 2022 (1072)
  • November 2022 (1145)
  • October 2022 (1151)
  • September 2022 (1071)
  • August 2022 (1097)
  • July 2022 (1111)
  • June 2022 (1117)
  • May 2022 (979)
  • April 2022 (1013)
  • March 2022 (982)
  • February 2022 (776)
  • January 2022 (681)
  • December 2021 (1197)
  • November 2021 (3156)
  • October 2021 (3212)
  • September 2021 (3140)
  • August 2021 (3271)
  • July 2021 (3205)
  • June 2021 (2984)
  • May 2021 (732)
Powered by Blogger.