Bay 12 Games Forum

Please login or register.

Login with username, password and session length
Advanced search  
Pages: 1 ... 3 4 [5]

Author Topic: AI risk re-re-revisited  (Read 7075 times)

SirQuiamus

  • Bay Watcher
  • Keine Experimente!
    • View Profile
Re: AI risk re-re-revisited
« Reply #60 on: September 26, 2016, 09:14:25 am »

Spoiler: lel (click to show/hide)
Logged

Ispil

  • Bay Watcher
    • View Profile
Re: AI risk re-re-revisited
« Reply #61 on: September 26, 2016, 09:16:11 am »

pfff
Logged
"Those who can make you believe absurdities can make you commit atrocities." - Voltaire

"I have never made but one prayer to God, a very short one: 'O Lord, make my enemies ridiculous.' And God granted it."- Voltaire

I transcribe things, too.

Ispil

  • Bay Watcher
    • View Profile
Re: AI risk re-re-revisited
« Reply #62 on: September 26, 2016, 02:02:38 pm »

Pardon the double post, but now I'm legitimately curious whether it's possible to prove bijectivity here.

Does Turing complete <=> mathematically chaotic? Is the logistic map a computer?
Logged
"Those who can make you believe absurdities can make you commit atrocities." - Voltaire

"I have never made but one prayer to God, a very short one: 'O Lord, make my enemies ridiculous.' And God granted it."- Voltaire

I transcribe things, too.

Max™

  • Bay Watcher
  • [CULL:SQUARE]
    • View Profile
Re: AI risk re-re-revisited
« Reply #63 on: September 26, 2016, 03:46:59 pm »

Hmmm, this seems to be asking a similar question by discussing properties of quantum chaotic turing machines: http://www.mrmains.com/bio/academic_files/pmath370/project.pdf
Logged
Engraved here is a rendition of an image of the Dwarf Fortress learning curve. All craftsdwarfship is of the highest quality. It depicts an obsidian overhang which menaces with spikes of obsidian and tears. Carved on the overhang is an image of Toady One and the players. The players are curled up in a fetal position. Toady One is laughing. The players are burning.
The VectorCurses+1 tileset strikes the square set and the severed part sails off in an arc!

SirQuiamus

  • Bay Watcher
  • Keine Experimente!
    • View Profile
Re: AI risk re-re-revisited
« Reply #64 on: October 31, 2016, 06:32:29 am »

I was offline for a few days and missed it, but Scott has posted the results, such as they are.

Spoiler (click to show/hide)
Logged

martinuzz

  • Bay Watcher
  • High dwarf
    • View Profile
Re: AI risk re-re-revisited
« Reply #65 on: November 02, 2016, 03:08:37 pm »

The Google Brain project reports that two of it's AI have developed an encrypted language to communicate with each other, with a third AI unable to break it's code.

The three AI, 'Alice', 'Bob', and Eve were provided with a clear task: Alice was tasked with sending a secret message to Bob, Bob was tasked with decoding it, and Eve was tasked to snoop in on the conversation.

None of the AI were given any information on how to encode messages or which techniques to use.
Alice and Bob were given a code key, which Eve had no access to.

At first, Alice and Bob were pretty bad at encrypting decoding messages, and Eve was able to snoop in on the badly encrypted messages.
However, after 15000 generations of evolving code, Alice developed an encryption strategy which Bob was quickly able to decode, while Eve was no longer able to crack the encryption.

While examining the encrypted messages, researchers noted that Alice used unknown and unexpected methods of encryption, very different from techniques used by human encryption software.

The researchers say that the results seem to indicate that in the future, AI will be able to communicate with each other in ways that we, or other AI cannot decrypt.
However, AI still has a long way to go. Even though the techniques used were surprising and innovative, Alice's encryption method was still rather simple compared to present day human encryption systems.

As it stands, they describe their research as an interesting excercise, but nothing more. They don't foresee any practical applications, as they do not know exactly what kind of encryption technique Alice used.

https://arxiv.org/pdf/1610.06918v1.pdf
Logged
Optimists have just used up the last bit of hope. Run for your lives!

Enjoy the freedom to explore the limits of your constraints

http://www.bay12forums.com/smf/index.php?topic=73719.msg1830479#msg1830479

TheBiggerFish

  • Bay Watcher
  • Somewhere around here.
    • View Profile
Re: AI risk re-re-revisited
« Reply #66 on: November 03, 2016, 03:34:24 pm »

Cool.
Logged
Sigtext

It has been determined that Trump is an average unladen swallow travelling northbound at his maximum sustainable speed of -3 Obama-cubits per second in the middle of a class 3 hurricane.

PanH

  • Bay Watcher
    • View Profile
Re: AI risk re-re-revisited
« Reply #67 on: November 04, 2016, 04:21:22 am »

Pretty cool indeed. Not sure if it has been mentioned but there's something similar with an AI translator (by Google too). I'll try to find a link later.
« Last Edit: November 04, 2016, 04:23:45 am by PanH »
Logged
Pages: 1 ... 3 4 [5]