LOADING

How can we trust our agents?

In my talk I will argue that we can do much better by relying in a systematic way on types and capabilities.

Martin Odersky
The inventor of the Scala language, a professor at EPFL in Lausanne, Switzerland, and a founder of Lightbend
About This Talk

AI agents are taking over many tasks that required humans before. This could be very good for productivity but how can we possibly trust our agents? There are a multitude of known ways an agent could go wrong, including prompt injections or plain hallucinations. The current techniques to control agent behavior are patchy and rudimentary, they certainly don't instill trust.

In my talk I will argue that we can do much better by relying in a systematic way on types and capabilities. We can use them to make not only bad states but also bad actions unrepresentable. This points us to a possible future where an inherently untrustworthy LLM agent can be trusted to stay within defined parameters when put in the right environment.

more great talks

Might Be Interesting

Day 2
  —  
10:10 am
arrow pointing right icon

Can we have the Standard Library for Macros?

Do you like it when compiler generates the boring code for you? Fast, mundane, boring-but-error-prone code? Do you need to implement such a code generator yourself? Have you found out that Shapeless/Mirrors bend your brain a bit too much?

Day 2
  —  
9:35 am
arrow pointing right icon

Flexible Modeling: Keeping Your Domain Pure with Scala 3

In this talk, we will walk through a concrete example of a boilerplate-heavy domain. By replacing common Scala 2 workarounds with Opaque Types, Extension Methods, Enums, and Union Types, we will demonstrate how to achieve a strictly typed, decoupled architecture without the noise.

Day 2
  —  
9:00 am
arrow pointing right icon

NamedTuples in Action

I would like to present the use of NamedTuples to implement some cool things in SQL Libraries

Day 1
  —  
11:50 am
arrow pointing right icon

Scala and C – tight as brothers

Scala Native can interact with C code and libraries, greatly expanding the library ecosystem beyond pure Scala offerings. Let's see the low level and high level tools that make it possible, talk through challenges of encoding various C concepts in Scala, and demonstrate what popular C libraries look like when used alongside idiomatic Scala code.

Day 1
  —  
9:35 am
arrow pointing right icon

The world after Scala 3.9 LTS

In this talk, I will introduce the highlights of what to look forward to in Scala 3.9 LTS, as well as how to think about the upcoming new release.

Day 1
  —  
4:50 pm
arrow pointing right icon

Effects as Capabilities

When writing software, we currently seem to have to choose between an imperative style - easy to read and write, hard to reason about - and a monadic style - hard to read and write, easy to reason about.This talk is about being greedy and getting the best of both worlds, because we deserve it.

See All Events
Join us!

We're looking for amazing speakers.
CFP is open till 10.01.2023

Fill in Call for Papers
location icon

Location

Centrum Konferencyjne POLIN, Poland
stay in touch icon

Follow Us

Contact Us