Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
How to Stop Killer Robots from Destroying the H...
Search
Brady Brim-DeForest
May 14, 2012
Science
2
140
How to Stop Killer Robots from Destroying the Human Race*
Brady Brim-DeForest
May 14, 2012
Tweet
Share
Other Decks in Science
See All in Science
ABEMAの効果検証事例〜効果の異質性を考える〜
s1ok69oo
4
2.1k
Online Feedback Optimization
floriandoerfler
0
340
教師なしテンソル分解に基づく、有糸分裂後の転写再活性化におけるヒストン修飾ブックマークとしての転写因子候補の抽出法
tagtag
0
120
Direct Preference Optimization
zchenry
0
280
構造設計のための3D生成AI-最新の取り組みと今後の展開-
kojinishiguchi
0
570
【人工衛星開発】能見研究室紹介動画
02hattori11sat03
0
150
Inductive-bias Learning: 大規模言語モデルによる予測モデルの生成
fuyu_quant0
0
100
インフラだけではない MLOps の話 @事例でわかるMLOps 機械学習の成果をスケールさせる処方箋 発売記念
icoxfog417
2
590
Презентация программы магистратуры СПбГУ "Искусственный интеллект и наука о данных"
dscs
0
390
大規模画像テキストデータのフィルタリング手法の紹介
lyakaap
7
1.5k
【健康&筋肉と生産性向上の関連性】 【Google Cloudを企業で運用する際の知識】 をお届け
yasumuusan
0
340
(論文読み)贈り物の交換による地位の競争と社会構造の変化 - 文化人類学への統計物理学的アプローチ -
__ymgc__
1
110
Featured
See All Featured
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.1k
For a Future-Friendly Web
brad_frost
175
9.4k
Side Projects
sachag
452
42k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
740
It's Worth the Effort
3n
183
27k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
126
18k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
Teambox: Starting and Learning
jrom
133
8.8k
Statistics for Hackers
jakevdp
796
220k
Six Lessons from altMBA
skipperchong
27
3.5k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
27
4.3k
Making the Leap to Tech Lead
cromwellryan
133
8.9k
Transcript
HOW TO STOP KILLER ROBOTS FROM DESTROYING THE HUMAN RACE*
None
None
THE SINGULARITY IS COMING
INTELLIGENCE EXPLOSION
1YEAR =31SECS
FIN
3LAWS THE
DON’T HARM HUMANS 1
OBEY HUMANS 2 UNLESS THIS CONFLICTS WITH LAW 1
PROTECT SELF 3 UNLESS THIS CONFLICTS WITH LAW 1 OR
2
THREE LAWS UNSAFE
NO TWO AIs WILL BE ALIKE 1
YOU ARE HERE
AI WILL EXPAND 2EXPONENTIALLY
None
AI MUST BE MADE FRIENDLY 3
EVIL GOOD vs
HOW CAN WE BE SURE?
*ONLY THE ROBOTS WILL KNOW