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
150
Andrey Vinitsky: Babe Are You OK? You've Barely Touched The Dashboard You Claimed Was Mission Critical
turingfest
PRO
0
97
Finbarr Taylor:From Scotland to Silicon Valley: Lessons Learned Raising $100m & Building a Global SaaS Business
turingfest
PRO
0
69
Megan Caywood: A Product Playbook to Building a Unicorn
turingfest
PRO
0
50
Jason Miller: Branding in the Age of AI
turingfest
PRO
0
72
Petra Wille: Lessons on Storytelling for Product Builders
turingfest
PRO
0
74
Meri Williams: Career Vectors: Navigating Modern Careers
turingfest
PRO
0
99
Todd Olson: How AI Supercharges Product-led Growth
turingfest
PRO
0
61
Rand Fishkin: Zero-Click Marketing
turingfest
PRO
0
85
Other Decks in Technology
See All in Technology
テストを軸にした生き残り術
kworkdev
PRO
0
220
機械学習を扱うプラットフォーム開発と運用事例
lycorptech_jp
PRO
0
670
S3アクセス制御の設計ポイント
tommy0124
3
210
20250910_障害注入から効率的復旧へ_カオスエンジニアリング_生成AIで考えるAWS障害対応.pdf
sh_fk2
3
280
Android Audio: Beyond Winning On It
atsushieno
0
3.4k
LLM時代のパフォーマンスチューニング:MongoDB運用で試したコンテキスト活用の工夫
ishikawa_pro
0
170
OCI Oracle Database Services新機能アップデート(2025/06-2025/08)
oracle4engineer
PRO
0
180
組織を巻き込む大規模プラットフォーム移行戦略 〜50+サービスのマルチリージョン・マルチプロダクト化で学んだステークホルダー協働の実践〜 / Platform migration strategy engaging all stakeholders
toshi0607
2
200
「全員プロダクトマネージャー」を実現する、Cursorによる仕様検討の自動運転
applism118
22
12k
バイブスに「型」を!Kent Beckに学ぶ、AI時代のテスト駆動開発
amixedcolor
3
590
Oracle Cloud Infrastructure IaaS 新機能アップデート 2025/06 - 2025/08
oracle4engineer
PRO
0
110
共有と分離 - Compose Multiplatform "本番導入" の設計指針
error96num
2
1.2k
Featured
See All Featured
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.6k
Large-scale JavaScript Application Architecture
addyosmani
513
110k
Gamification - CAS2011
davidbonilla
81
5.4k
YesSQL, Process and Tooling at Scale
rocio
173
14k
Designing for humans not robots
tammielis
253
25k
Making Projects Easy
brettharned
117
6.4k
Practical Orchestrator
shlominoach
190
11k
Statistics for Hackers
jakevdp
799
220k
Side Projects
sachag
455
43k
Unsuck your backbone
ammeep
671
58k
Making the Leap to Tech Lead
cromwellryan
135
9.5k
The Straight Up "How To Draw Better" Workshop
denniskardys
236
140k
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