WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2025 • Jul 31, 2025 • Session details

How AI Models Get Smarter

Ankit Patel

Standardized benchmarks won't guarantee production success. Learn how test-time reasoning and agentic workflows are turning structured English into the modern developer's most powerful programming language.

Pause
Mute Enter Fullscreen
#1 about 2 min

Leveraging chip sets and software for artificial intelligence efficiency

Hardware and software advancements enable more efficient large scale mathematical research.

#2 about 3 min

Measuring artificial intelligence capability using the public MMLU benchmark

Standardized multiple choice exams map conceptual boundaries by scoring performance against human expert averages.

#3 about 2 min

Overcoming human limitations in the pre-transformer computer vision era

Reliance on manually labeled data created significant bottlenecks for legacy architecture scaling.

#4 about 4 min

Utilizing the transformer architecture for unstructured raw text datasets

Predicting sequential vectors allows algorithms to absorb vast amounts of unstructured internet knowledge.

#5 about 3 min

Adapting pre-trained models using supervised fine tuning instructional techniques

Converting general linguistic knowledge into functional chat interfaces requires structured conversational demonstrations.

#6 about 5 min

Guiding model behavior utilizing reinforcement learning from human feedback

Deploying distinct reward algorithms automates the alignment of conversational responses with human preferences.

#7 about 2 min

Optimizing efficiency and reducing power consumption in computational hardware

System innovations drastically decrease the overall energy required to process massive architectural workloads.

#8 about 3 min

Enhancing accuracy through reasoning models and test time scaling

Programs that recursively prompt themselves to verify outputs significantly reduce factual errors.

#9 about 1 min

Dropping inference energy per token with high speed architecture

Hardware optimizations minimize the operational cost of generating ongoing programmatic output.

#10 about 2 min

Building modern applications utilizing structured natural language engineering prompts

Developers can orchestrate deep modular workflows simply by writing precise instructional sentences.

#11 about 2 min

Selecting between open source endpoints and proprietary reasoning services

Strategically choosing endpoints ensures the best balance of response quality and continuous functionality.

#12 about 1 min

Evaluating practical output quality independent of standardized quantitative benchmarks

Actual contextual testing inside target applications remains the only method for guaranteeing reliability.

#13 about 3 min

Preventing social engineering exploits with strict operational system guardrails

Applying rigid prompt boundaries keeps interfaces safe against manipulative gaslighting and forbidden inquiries.

#14 about 2 min

Designing modular application agents with integrated python tool chaining

Subdividing major features into smaller tools enables analytical programs to self direct dataset reviews.

#15 about 2 min

Exploring deep learning courses and free online organizational communities

Accessible training programs provide developers with essential templates for deploying real-world predictive utilities.

#16 about 5 min

Resolving core questions about probability and synthetic information distillation

Probabilistic mechanisms naturally create output variance while synthetic questions easily train smaller, efficient models.

Matching moments

2:37 min

Understanding core parameters and mechanics of large language models

Julián Duque Julián Duque · World Congress 2025

5:01 min

Leveraging large language models for code optimization and development

Stephan Gillich Stephan Gillich +3 · World Congress 2024

4:40 min

The increasing complexity and impact of modern AI

Jaap Kersten Jaap Kersten +1 · World Congress 2024

2:18 min

Major breakthroughs shaping the artificial intelligence landscape

Nico Axtmann · World Congress 2022

3:22 min

Evaluating advanced artificial intelligence platforms for daily recruitment

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

4:29 min

Designing AI applications defensively for inevitable failures

Krzysztof Cieślak Krzysztof Cieślak · World Congress 2026 Europe

More from World Congress 2025

GenAI Security: Navigating the Unseen Iceberg thumbnail
24:33
11 months ago

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

Behind the Code: How Women Are Powering the Future of AI thumbnail
30:28
about 1 year ago

Behind the Code: How Women Are Powering the Future of AI

Alexandra Wudel, Laura Moritz, Madalina Florean

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise? thumbnail
28:12
about 1 year ago

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise?

Justus Lumpe, Konstantin Vinogradov, Nils Eiteneyer, Stephan Wirris

AI in Leadership: How Technology is Reshaping Executive Roles thumbnail
28:19
about 1 year ago

AI in Leadership: How Technology is Reshaping Executive Roles

Bernd Datler, Jasmin Kaiser, Jeff Hausmann, Sonja Alvarez

The AI-Ready Stack: Rethinking the Engineering Org of the Future thumbnail
28:09
about 1 year ago

The AI-Ready Stack: Rethinking the Engineering Org of the Future

Alex Laubscher, Jan Oberhauser, Keno Dreßel, Mirko Novakovic

AI Sovereignty: What Does It Take? thumbnail
29:13
about 1 year ago

AI Sovereignty: What Does It Take?

Boris Hecker, Clemens Wasner, Robin Hermann, Sonja Alvarez

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 12:15–12:45

Stage 4

It's Not About the Models

Bob Wambach

VP, Market and Customer Insights

Bob Wambach
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 9

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

September 24, 2026 · 16:10–16:40

Stage 3

Sandboxing the Swarm: Building Secure, Serverless AI Agents with Wasm

Thorsten Hans

Sr. Developer Advocate @ Akamai Technologies

Thorsten Hans
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 5

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 2

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer at IBM

Eric Deandrea

Related videos

Three years of putting LLMs into Software - Lessons learned thumbnail
26:30
World Congress 2025 • about 1 year ago

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 2 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

The LLM Evolution: From Sequence Imitation to Verifiable Reasoning thumbnail
27:27
World Congress 2026 Europe • 2 months ago

The LLM Evolution: From Sequence Imitation to Verifiable Reasoning

Kamen Petroff

Navigating the AI Revolution in Software Development thumbnail
41:05
almost 2 years ago

Navigating the AI Revolution in Software Development

AI & Ethics thumbnail
28:27
World Congress 2025 • about 1 year ago

AI & Ethics

PJ Hagerty

The Limits of LLMs in Real-World Applications thumbnail
31:07
World Congress 2026 Europe • 2 months ago

The Limits of LLMs in Real-World Applications

Deivids Vilkinsons, Guillaume Esnou, Laura Moritz, Mariam Hakobyan

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.