Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
WHERE WE ARE NOW, WHERE WE ARE
HEADING AND HOW TO GET THERE SAFELY
CHATBOTS AND THE PATH TO
ARTIFICIAL INTELLIGENCE
Yisela...
WHAT IS A BOT
A bot is any application that
you communicate with, via
speech or text, in order to
execute commands.
2
INTRO
 The bot revolution can
be compared to the
mobile revolution
 Although it was a
progression, bots are
possible now...
THREE TRENDS DRIVING SMART BOTS
• Messaging-as-OS: Messaging as a new platform
• The app problem: People are reluctant to ...
Yisela Alvarez Trentini | MRM McCann, August 2016 5
1974: Command line 2016: A Slack channel
“Command lines were notorious...
1. The Evolution of Bots
Three cases
6
ELIZA
1966
HOWDY
2015
SAMANTHA
-
STATELESS SEMI-STATEFUL STATEFUL + INTELLIGENT
Shallow tracking of conversations Can read...
1. Stateless Bots
2. Semi-Stateful Bots
3. Stateful Bots
8
STATELESS BOTS
• Each request that a program processes disappears
from the server’s memory.
• Bots are stateless by defaul...
Created by Joseph Weizenbaum (MIT) in
1966.
Acts like a non-directional
psychotherapist in an initial
phsyachriatic interv...
Simple pattern matching techniques (parsing and
substitution of key words)
Yisela Alvarez Trentini | MRM McCann, August 20...
OTHER STATELESS BOTS
Yisela Alvarez Trentini | MRM McCann, August 2016 12
A bot that twits images from
museum collections
...
1. Stateless Bots
2. Semi-Stateful Bots
3. Stateful Bots
13
 Made by XOXCO in 2016 and integrated with
Slack.
 Easy to install, works out of the box.
 A „digital coworker“ to auto...
WHAT SEMI-STATEFUL BOTS ARE GOOD AT
TODAY
 In the workplace: Automating small routine tasks, run
surveys, act as a bridge...
Yisela Alvarez Trentini | MRM McCann, August 2016 16
November 1996
Clippy
 Too
anthropomorphic
but not human.
 “Optimize...
USEFUL VS FUN
Yisela Alvarez Trentini | MRM McCann, August 2016 17
Why people hate the paperclip:
Labels, appearance, beha...
FITNESS ASSISTANT
In 2008, Cory Kidd completed a study with a robot intended to aid in fitness
and weight loss goals, by p...
THE PERCEPTION OF BOTS
 We instinctively treat computers like people and use the
same standards of politeness, gender ste...
THE UNCANNY VALLEY
However, making
making machines
more humanlike is
good up to a point,
after which they
become
discomfor...
WHAT DOES THIS MEAN FOR CHATBOTS?
Project Name | Date 21
PERSONALITY
 Most users will build a relationship
with their bots.
 In conversational UIs, personality is
the new UX. Th...
CHAT BOTS WORKING ALONGSIDE HUMANS
Supervised A.I: In Facebook M, bots gather information for an
eventual interaction with...
1. Stateless Bots
2. Semi-Stateful Bots
3. Stateful Bots
24
A.I. POWERED BOTS: MACHINE LEARNING
For a machine to recognise cats, a person must first provide it with
thousands of phot...
A.I. POWERED BOTS: DEEP NEURAL
NETWORKS
Neural network are
used to simulate
densely interconnected
brain cells.
The comput...
Samatha is an intelligent personal OS from
the movie Her by Spike Jonze.
 Has impressive knowledge of the physical world....
BOTS AND LANGUAGE
Our language is a compact and effective system, but relies
on the assumption of intelligence and a commo...
BOTS AND LANGUAGE
Yisela Alvarez Trentini | MRM McCann, August 2016 29
• Bots need to learn to speak (or think) like us, w...
ONCE OUR BOTS CAN TALK...
• Do we want „always-aware“ systems?
• Should our assistant bots interact with other people’s?
•...
IF YOU EVER MAKE A BOT...
1. A robot may not injure a human being or, through
inaction, allow a human being to come to har...
REFERENCES
• Weizenbaum, Joseph "ELIZA – A Computer Program For the Study of Natural Language
Communication Between Man an...
Nächste SlideShare
Wird geladen in …5
×

Chatbots, Personal Assistants and the Future of Artificial Intelligence

754 Aufrufe

Veröffentlicht am

Chatbots, Personal Assistants and the Future of Artificial Intelligence. Presented by Yisela Alvarez Trentini at UX Camp West 2016, Köln.

Veröffentlicht in: Technologie
  • Als Erste(r) kommentieren

Chatbots, Personal Assistants and the Future of Artificial Intelligence

  1. 1. WHERE WE ARE NOW, WHERE WE ARE HEADING AND HOW TO GET THERE SAFELY CHATBOTS AND THE PATH TO ARTIFICIAL INTELLIGENCE Yisela Alvarez Trentini | MRM McCann, August 2016
  2. 2. WHAT IS A BOT A bot is any application that you communicate with, via speech or text, in order to execute commands. 2
  3. 3. INTRO  The bot revolution can be compared to the mobile revolution  Although it was a progression, bots are possible now due to massive amounts of data and hardware  It’s more of a tech-driven vision, not a response to concrete user demands Yisela Alvarez Trentini | MRM McCann, August 2016 3 Facebook‘s M WeChat Microsoft Win + Azure Google
  4. 4. THREE TRENDS DRIVING SMART BOTS • Messaging-as-OS: Messaging as a new platform • The app problem: People are reluctant to install apps, or apps are becoming redundant • The “conversational interface”: A new model for interacting with online services Yisela Alvarez Trentini | MRM McCann, August 2016 4
  5. 5. Yisela Alvarez Trentini | MRM McCann, August 2016 5 1974: Command line 2016: A Slack channel “Command lines were notoriously intimidating and difficult to get the hang of. Slack is the exact opposite—it’s charming, fun, and easy to understand—yet it runs off the same principle.” Archana Madhavan BACK TO A MINIMAL INTERFACE The future: ?
  6. 6. 1. The Evolution of Bots Three cases 6
  7. 7. ELIZA 1966 HOWDY 2015 SAMANTHA - STATELESS SEMI-STATEFUL STATEFUL + INTELLIGENT Shallow tracking of conversations Can read, comprehend and reason No memory or storage Yisela Alvarez Trentini | MRM McCann, August 2016
  8. 8. 1. Stateless Bots 2. Semi-Stateful Bots 3. Stateful Bots 8
  9. 9. STATELESS BOTS • Each request that a program processes disappears from the server’s memory. • Bots are stateless by default. Apps receive requests, bts receive messages. If the web server were to keep track of the requests it had processed, it would soon collapse under its own weight. • Each message is considered a new interaction. Yisela Alvarez Trentini | MRM McCann, August 2016 9
  10. 10. Created by Joseph Weizenbaum (MIT) in 1966. Acts like a non-directional psychotherapist in an initial phsyachriatic interview. Open, introspective questions. http://www.masswerk.at/elizabot/ Yisela Alvarez Trentini | MRM McCann, August 2016 10 THE FIRST BOT: ELIZA
  11. 11. Simple pattern matching techniques (parsing and substitution of key words) Yisela Alvarez Trentini | MRM McCann, August 2016 11 ELIZA’S INNER WORKINGS
  12. 12. OTHER STATELESS BOTS Yisela Alvarez Trentini | MRM McCann, August 2016 12 A bot that twits images from museum collections A bot that replaces the word „boy“ with „bot“A bot that posts random art assignments 1 2 3
  13. 13. 1. Stateless Bots 2. Semi-Stateful Bots 3. Stateful Bots 13
  14. 14.  Made by XOXCO in 2016 and integrated with Slack.  Easy to install, works out of the box.  A „digital coworker“ to automate:  Asynchronus communication  Plan meetings  Collect lunch orders  Highly effective for a limited scope of tasks. Yisela Alvarez Trentini | MRM McCann, August 2016 14 Howdy https://howdy.ai/
  15. 15. WHAT SEMI-STATEFUL BOTS ARE GOOD AT TODAY  In the workplace: Automating small routine tasks, run surveys, act as a bridge between gaps  Healthcare: Follow-ups and reminders (Sense.ly), answer questions (Your.MD), health coaching  Onboarding: Guiding through materials  Used for evil: Social network spamming, profile clonning Yisela Alvarez Trentini | MRM McCann, August 2016 15
  16. 16. Yisela Alvarez Trentini | MRM McCann, August 2016 16 November 1996 Clippy  Too anthropomorphic but not human.  “Optimized for first use”. Always.  Enabled by default. Every time.
  17. 17. USEFUL VS FUN Yisela Alvarez Trentini | MRM McCann, August 2016 17 Why people hate the paperclip: Labels, appearance, behavior and Social responses to user interface agents Luke Swartz Stanford University 2003
  18. 18. FITNESS ASSISTANT In 2008, Cory Kidd completed a study with a robot intended to aid in fitness and weight loss goals, by providing a social presence with which study participants tracked their routines. Yisela Alvarez Trentini | MRM McCann, August 2016 18  Most used “he” or “she” when talking about their robot  1 never returned the robot Group 1 Pen & Paper Group 2 Touchscreen Group 1 Touchscreen + Robot
  19. 19. THE PERCEPTION OF BOTS  We instinctively treat computers like people and use the same standards of politeness, gender stereotypes, teamwork and reciprocity.  Many said that Eliza helped them, and some asked the people conducting the test to leave them alone with her so they could discuss things in private. It was even considered a low-cost way to handle people with mild psychological problems. Yisela Alvarez Trentini | MRM McCann, August 2016 19
  20. 20. THE UNCANNY VALLEY However, making making machines more humanlike is good up to a point, after which they become discomforting or creepy. Yisela Alvarez Trentini | MRM McCann, August 2016 20
  21. 21. WHAT DOES THIS MEAN FOR CHATBOTS? Project Name | Date 21
  22. 22. PERSONALITY  Most users will build a relationship with their bots.  In conversational UIs, personality is the new UX. The entire app experience is reduced to a few lines of text. Microcopy is now king.  Writers and comedians collaborate with UX to create engaging bots. Yisela Alvarez Trentini | MRM McCann, August 2016 22
  23. 23. CHAT BOTS WORKING ALONGSIDE HUMANS Supervised A.I: In Facebook M, bots gather information for an eventual interaction with a human rep. Yisela Alvarez Trentini | MRM McCann, August 2016 23 While the rep answers, the machine learns. How?
  24. 24. 1. Stateless Bots 2. Semi-Stateful Bots 3. Stateful Bots 24
  25. 25. A.I. POWERED BOTS: MACHINE LEARNING For a machine to recognise cats, a person must first provide it with thousands of photos of cats and not cats. Yisela Alvarez Trentini | MRM McCann, August 2016 25 CAT! Feed the machine thousands of photos of cats (and noncats) Show the machine a photo of a cat, and it should recognise it as such. ? cat cat cat cat cat Not cat Not cat
  26. 26. A.I. POWERED BOTS: DEEP NEURAL NETWORKS Neural network are used to simulate densely interconnected brain cells. The computer can learn things, recognize patterns, and make decisions in a humanlike way. Yisela Alvarez Trentini | MRM McCann, August 2016 26 NOT CAT! CAT! color edges color blobs
  27. 27. Samatha is an intelligent personal OS from the movie Her by Spike Jonze.  Has impressive knowledge of the physical world.  Can understand human emotion and show empathy.  Can reason and debate. Yisela Alvarez Trentini | MRM McCann, August 2016 27
  28. 28. BOTS AND LANGUAGE Our language is a compact and effective system, but relies on the assumption of intelligence and a common social and physical world. Yisela Alvarez Trentini | MRM McCann, August 2016 28 „The trophy will not fit in the brown suitcase because it was too big.“ What was too big? Answer 0: the trophy; Answer 1: the suitcase.
  29. 29. BOTS AND LANGUAGE Yisela Alvarez Trentini | MRM McCann, August 2016 29 • Bots need to learn to speak (or think) like us, without a physical world or the time to learn about it like we have. • Machines also need to understand how humans work on an emotional level: Detect and analyse emotions, extract concepts from dialog, showing empathy. • Symbolic processing (humans) + machine learning (system) • We both need a model of the other, as well of one of the world.
  30. 30. ONCE OUR BOTS CAN TALK... • Do we want „always-aware“ systems? • Should our assistant bots interact with other people’s? • How can we teach the machine introspection? (the ability to communicate the exact process that leads to their choices.) • Is it necessary to make machines human-like? Do they need to converse? Do you talk to a bot, or use one? • What are the dangers of captology and creating bots that can be truly persuasive? • Human Rights Watch is looking for an international treaty to ban military robots with autonomous lethal firing power. How far are we from this? Yisela Alvarez Trentini | MRM McCann, August 2016 30
  31. 31. IF YOU EVER MAKE A BOT... 1. A robot may not injure a human being or, through inaction, allow a human being to come to harm. 2. A robot must obey orders given it by human beings except where such orders would conflict with the First Law. 3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law. 31
  32. 32. REFERENCES • Weizenbaum, Joseph "ELIZA – A Computer Program For the Study of Natural Language Communication Between Man and Machine" in: Communications of the ACM; Volume 9 , Issue 1 (January 1966): p 36-45. • About neural networks: http://www.explainthatstuff.com/introduction-to-neural-networks.html • How Humans Respond to Robots: Building Public Policy through Good Design https://www.brookings.edu/research/how-humans-respond-to-robots-building-public-policy-through- good-design/ • "WHY PEOPLE HATE THE PAPERCLIP: LABELS, APPEARANCE, BEHAVIOR AND SOCIAL RESPONSES TO USER INTERFACE AGENTS", Luke Swartz, June 12, 2003, Honors Thesis for Symbolic Systems Program, Stanford University • C. Kidd and C. Breazeal. A Robotic Weight Loss Coach. Twenty-Second Conference on Artificial Intelligence, 2007. Yisela Alvarez Trentini | MRM McCann, August 2016 32

×