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
Fergal Reid - Building products in the age of Ai
Search
Turing Fest
PRO
July 05, 2023
Technology
0
190
Fergal Reid - Building products in the age of Ai
Turing Fest
PRO
July 05, 2023
Tweet
Share
More Decks by Turing Fest
See All by Turing Fest
Andy Budd: The Growth Equation: 7 Essential Steps to Finding Product Market Fit
turingfest
PRO
0
140
Andrey Vinitsky: Babe Are You OK? You've Barely Touched The Dashboard You Claimed Was Mission Critical
turingfest
PRO
0
94
Finbarr Taylor:From Scotland to Silicon Valley: Lessons Learned Raising $100m & Building a Global SaaS Business
turingfest
PRO
0
56
Megan Caywood: A Product Playbook to Building a Unicorn
turingfest
PRO
0
49
Jason Miller: Branding in the Age of AI
turingfest
PRO
0
69
Petra Wille: Lessons on Storytelling for Product Builders
turingfest
PRO
0
70
Meri Williams: Career Vectors: Navigating Modern Careers
turingfest
PRO
0
98
Todd Olson: How AI Supercharges Product-led Growth
turingfest
PRO
0
59
Rand Fishkin: Zero-Click Marketing
turingfest
PRO
0
84
Other Decks in Technology
See All in Technology
Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
kzykmyzw
0
370
【 LLMエンジニアがヒューマノイド開発に挑んでみた 】 - 第104回 Machine Learning 15minutes! Hybrid
soneo1127
0
150
モダンな現場と従来型の組織——そこに生じる "不整合" を解消してこそチームがパフォーマンスを発揮できる / Team-oriented Organization Design 20250825
mtx2s
6
2.7k
どこで動かすか、誰が動かすか 〜 kintoneのインフラ基盤刷新と運用体制のシフト 〜
ueokande
0
200
実践アプリケーション設計 ②トランザクションスクリプトへの対応
recruitengineers
PRO
4
840
知られざるprops命名の慣習 アクション編
uhyo
11
2.7k
Yahoo!ニュースにおけるソフトウェア開発
lycorptech_jp
PRO
0
450
フルカイテン株式会社 エンジニア向け採用資料
fullkaiten
0
8.6k
Goss: New Production-Ready Go Binding for Faiss #coefl_go_jp
bengo4com
0
1.1k
Yahoo!広告ビジネス基盤におけるバックエンド開発
lycorptech_jp
PRO
1
290
ZOZOTOWNフロントエンドにおけるディレクトリの分割戦略
zozotech
PRO
18
5.7k
事業価値と Engineering
recruitengineers
PRO
6
3.9k
Featured
See All Featured
Speed Design
sergeychernyshev
32
1.1k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
Designing Experiences People Love
moore
142
24k
Thoughts on Productivity
jonyablonski
69
4.8k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.5k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
50
5.5k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Java REST API Framework Comparison - PWX 2021
mraible
33
8.8k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
Transcript
Building products in the Age of AI @fergal_reid
GPT / LLMs • Internet sized change • Change in
capability • Change in how we build and use AI
None
None
None
Level 1: GPTs are incredible! Level 2: GPTs make things
up and aren’t trustworthy. Level 3: GPTs can be incredible when used right
See them as engineering components Separate out aspects accidentally bundled
What is GPT?
Training objective: token prediction
Training objective: token prediction
None
None
• A sequence model • That uses ‘attention’ • Gradient
descent
• A sequence model • That uses ‘attention’ • Gradient
descent
Not a useful model • Human = genes and evolution
? • Distrust: ‘It de fi nitely can’t do X because its just trained to predict the next word’
Model: Database + Reasoning Engine • The reasoning engine is
key • Often, the database is a liability
Reasoning capabilities
None
None
Model: ‘Interpolative’ vs ‘Extrapolative’ tasks
None
• Less reliable at extrapolation • Favour interpolation • Perform
a task, given a context • ‘Retrieval Augmented Generation’
Model: Human intuition Ask a human to answer a historical
question vs Give them a history book and ask them the question
Note: Context window limited • Thousands of words • Can’t
put a whole KB, or context, in it • Synergizes well with Vector Search
How we build with GPTs
None
None
None
None
30 November 2022: ChatGPT
First features we built • Summarisation • Edit tone of
voice • Expand from shorthand
None
None
• 5th Dec: Rolling • 20th Dec: Internal use •
~13th Jan: Customer beta • 31st Jan: Launch with testimonials Timeline
Model: Easy vs Hard AI features
• ‘Easy’: • Out-of-box accuracy high • Cost of error
low • E.g. ‘Draft me a summary’
• ‘Hard’: • Out-of-box accuracy low • Cost of error
high
Development Tactics
• Fast customer contact • Assume you can build v1
of most ML with powerful LLM • Make cheap later • “LLMs aren’t all of AI” • How we build software has changed
Hard feature: Fin • GPT-powered question answering Bot
• An LLM can seem inert • However, can easily
be turned into an agent
My key points • Internet sized change • Good model:
DB+Reasoning • Changes how we build ML • Feature dif fi culty varies
Guessing what’s next
• V1: text tools, working around clunky interfaces • V2:
features reasoning can enhance • V?: End to end problems where intelligence can help • Don’t underestimate the reasoning capability, very sophisticated
• Breakneck progress • Smaller models, open? • Exciting but
overhyped today • Productisation • Larger models
Thank you! @fergal_reid