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
Rogue Agents - Stop AI from misusing APIs
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Dominik Kundel
PRO
January 23, 2024
Programming
0
280
Rogue Agents - Stop AI from misusing APIs
Dominik Kundel
PRO
January 23, 2024
Tweet
Share
More Decks by Dominik Kundel
See All by Dominik Kundel
AWS re:Invent '24 - Rogue Agents - Stop AI from misusing APIs
dkundel
PRO
0
97
AI for Marketers Sept '24 - How AI Agents will change your
dkundel
PRO
0
300
AGI Builders July '24 - Rogue Agents - Stop AI from misusing APIs
dkundel
PRO
0
230
AI Engineer World's Fair '24 - Cooking with Fire without
dkundel
PRO
0
230
SIGNAL 2021 - Live Developer Mode
dkundel
PRO
0
190
OpenJS World - What the AST?
dkundel
PRO
0
490
WFHConf - Move to TypeScript at your own Pace
dkundel
PRO
0
360
SFNode '20 - How to move your project to TypeScript
dkundel
PRO
0
350
Node+JS Interactive '19 - When Porgs Scream at Webpack and Other Stories
dkundel
PRO
0
370
Other Decks in Programming
See All in Programming
Beyond the Basics: Signal Forms
manfredsteyer
PRO
0
110
あなたはユーザーではない #PdENight
kajitack
4
300
オブザーバビリティ駆動開発って実際どうなの?
yohfee
3
670
Go1.26 go fixをプロダクトに適用して困ったこと
kurakura0916
0
320
「やめとこ」がなくなった — 1月にZennを始めて22本書いた AI共創開発のリアル
atani14
0
340
go directiveを最新にしすぎないで欲しい話──あるいは、Go 1.26からgo mod initで作られるgo directiveの値が変わる話 / Go 1.26 リリースパーティ
arthur1
2
440
受け入れテスト駆動開発(ATDD)×AI駆動開発 AI時代のATDDの取り組み方を考える
kztakasaki
2
510
New in Go 1.26 Implementing go fix in product development
sunecosuri
0
260
atmaCup #23でAIコーディングを活用した話
ml_bear
4
720
Head of Engineeringが現場で回した生産性向上施策 2025→2026
gessy0129
0
210
The Past, Present, and Future of Enterprise Java
ivargrimstad
0
350
new(1.26) ← これすき / kamakura.go #8
utgwkk
0
1.5k
Featured
See All Featured
More Than Pixels: Becoming A User Experience Designer
marktimemedia
3
340
From π to Pie charts
rasagy
0
140
Designing for Timeless Needs
cassininazir
0
150
Building Adaptive Systems
keathley
44
2.9k
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.3k
A Tale of Four Properties
chriscoyier
162
24k
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
290
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
270
A Soul's Torment
seathinner
5
2.4k
Site-Speed That Sticks
csswizardry
13
1.1k
Bash Introduction
62gerente
615
210k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.7k
Transcript
Rogue Agents Stop AI from misusing APIs TechTalks SF -
Jan ‘24 Dominik Kundel d-k.im/rogue-agents Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
console.log(` Hi! I’m Dominik Kundel `); dkundel.com @dkundel
[email protected]
github/dkundel
Product Lead @ Twilio && JavaScript Hacker Dominik Kundel | @dkundel
How can we have AI interact with APIs? Dominik Kundel
| @dkundel
How can we have AI safely interact with APIs? Dominik
Kundel | @dkundel
How can we have AI interact with APIs? Dominik Kundel
| @dkundel
Dominik Kundel | @dkundel How to connect AI to APIs
Platforms Frameworks Native LLM Functions 🦜🔗
Dominik Kundel | @dkundel Platforms Frameworks Native LLM Functions 🦜🔗
Source: LangChain Documentation
Dominik Kundel | @dkundel Platforms Frameworks Native LLM Functions 🦜🔗
Source: LangChain Documentation
What’s the problem? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Unpredictable Dominik Kundel | @dkundel
Dominik Kundel | @dkundel Easily Impressionable
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Rules are “suggestions”
Dominik Kundel | @dkundel Source: Simon Willison - Prompt injections
explained
Dominik Kundel | @dkundel Source: Simon Willison - Prompt injections
explained
Dominik Kundel | @dkundel The problems with LLMs Unpredictable Easily
Impressionable Rules “suggestions”
Dominik Kundel | @dkundel
How do we “LLM-proof” our APIs? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel LLM
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel LLM
What security measures? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel Security Measures
Dominik Kundel | @dkundel Security Measures Data Validation
Dominik Kundel | @dkundel Security Measures Data Validation Rate Limiting
Dominik Kundel | @dkundel Security Measures Data Validation Authentication Rate
Limiting
Dominik Kundel | @dkundel Security Measures
Dominik Kundel | @dkundel Security Measures Authorization
Dominik Kundel | @dkundel Security Measures Authorization Least Privilege
Dominik Kundel | @dkundel Security Measures Authorization Eliminate con fi
dential & unnecessary data Least Privilege
Dominik Kundel | @dkundel Do threat modeling!
Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Security mechanisms outside AI world
Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Security mechanisms outside AI world
Dominik Kundel | @dkundel Takeaways? Toddler-proof your home API!
console.log(` 💖 Thank You! 🎉 `); dkundel.com @dkundel
[email protected]
github/dkundel
d-k.im/rogue-agents Dominik Kundel | @dkundel | #workfromhomeconf |