WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Coffee With Developers • Apr 23, 2025

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel , Guillaume Laforge

Mete Atamel and Guillaume Laforge warn that treating LLMs as infallible black boxes will break your app. Learn to build robust, secure RAG pipelines that prevent costly AI hallucinations.

Pause
Mute Enter Fullscreen
#1 about 3 min

Coping with the rapid pace of AI model advancements

The constant release of new models and research papers creates pressure to stay current alongside general developer excitement.

#2 about 2 min

Accelerating coding workflows with AI code generation tools

Artificial intelligence tools speed up boilerplate creation and make exploring new programming languages significantly easier.

#3 about 2 min

Choosing contemporary development environments for AI coding assistants

Modern code editors seamlessly integrate intelligent assistance directly into standalone browser and desktop workflows.

#4 about 3 min

Pioneering structured outputs and robust models in generative AI

Early ecosystem innovations have heavily focused on strict schema enforcement and competitive model benchmarking.

#5 about 3 min

Demystifying fundamental model mechanics and underlying token processes

Digging into implementation details like token behavior and mathematical limitations improves overall model utilization.

#6 about 3 min

Structuring pre-processing and post-processing pipelines for generative requests

Real-world engineering requires careful data chunking, validation, and framework orchestration before finalizing an API request.

#7 about 3 min

Balancing output creativity with strict schema compliance limitations

Multistep prompting techniques preserve creative text generation while simultaneously outputting strictly formatted data types.

#8 about 4 min

Mitigating generated hallucinations with code execution and data grounding

Techniques like running generated Python scripts and private vector searches tether model responses accurately to reality.

#9 about 4 min

Resolving stale model knowledge using external tool access

Granting generative models access to live external APIs and search indices bridges the gap between training dates and current events.

#10 about 5 min

Optimizing token costs through context caching and batch generation

Software engineering paradigms like context caching and request batching significantly reduce the expense and energy waste of repetitive prompts.

#11 about 4 min

Securing confidential data in multi-tenant application deployments

Careful data filtering and automated redaction services prevent the exposure of personally identifiable information in language pipelines.

#12 about 4 min

Evaluating security risks and capabilities of the agentic web

While autonomous agents offer powerful convenience, granting them unregulated system access requires robust sandboxing and oversight.

#13 about 5 min

Embedding invisible artificial intelligence natively into user experiences

The next evolution of smart software integrates context seamlessly operating invisibly rather than relying on disparate explicit chatbots.

#14 about 3 min

Retaining accessible paths to human support within automated workflows

Completely isolating users inside a chatbot loop creates immense frustration when edge case problems require manual intervention.

#15 about 4 min

Finding reliable resources for continued machine learning education

Following curated technical newsletters offers a vastly superior signal-to-noise ratio than relying on spontaneous social media influencers.

Matching moments

1:34 min

Mitigating the inherent challenges of generative AI tools

Mary Grygleski Mary Grygleski · LIVE

7:28 min

Accelerating product features using generative large language models

David Singleton David Singleton +1 · Coffee With Developers

10:17 min

Discussion on AI hallucinations and practical developer workflows

Akmal Chaudhri Akmal Chaudhri · LIVE

5:30 min

Building components of a real-world LLM lifecycle

Maxim Salnikov Maxim Salnikov · LIVE

2:20 min

Integrating generative AI into software development workflows

Chris Wysopal Chris Wysopal · WWC 2024

1:59 min

Building culturally aware LLMs for global audiences

Werner Vogels Werner Vogels +1 · WWC Europe 2026

More from Coffee With Developers

What to Do About Hackathons in the Time of Agents - Mike Swift thumbnail
46:03
9 days ago

What to Do About Hackathons in the Time of Agents - Mike Swift

Mike Swift

Moving from Playing with AI to Implementing AI - Lee Stott thumbnail
18:43
13 days ago

Moving from Playing with AI to Implementing AI - Lee Stott

Lee Stott

Evals vs. Evil - AI and Package Security - Laurie Voss thumbnail
16:57
22 days ago

Evals vs. Evil - AI and Package Security - Laurie Voss

Laurie Voss

Burning Satellites, Talking Plants and Agents Hiring Each Other - Fake or News with Matt Zeunert thumbnail
4:57
27 days ago

Burning Satellites, Talking Plants and Agents Hiring Each Other - Fake or News with Matt Zeunert

Matt Zeunert

Web Scraping, AI Agents, and the Future of Open Source - Kevin Lewis (Apify) thumbnail
40:29
about 2 months ago

Web Scraping, AI Agents, and the Future of Open Source - Kevin Lewis (Apify)

Making Teaching Code Less Academic and More Market-Ready - Peter Ruppel thumbnail
32:22
about 2 months ago

Making Teaching Code Less Academic and More Market-Ready - Peter Ruppel

Upcoming sessions on this topic

Open session

World Congress 2026 North America

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

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

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

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

Who Tests the AI? Building Trustworthy AI Systems at Enterprise Scale

Him Raj Singh

PayPal, Manager, Software Engineer

Him Raj Singh
Open session

World Congress 2026 North America

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Enterprise AI Architect at American Chemical Society

Jofia Jose Prakash

Related videos

Make it simple, using generative AI to accelerate learning thumbnail
26:54
WWC 2024 • almost 2 years ago

Make it simple, using generative AI to accelerate learning

Duan Lightfoot

Lessons Learned Building a GenAI Powered App thumbnail
30:07
WWC 2024 • almost 2 years ago

Lessons Learned Building a GenAI Powered App

Mete Atamel

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails thumbnail
29:00
WWC 2025 • 12 months ago

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

Three years of putting LLMs into Software - Lessons learned thumbnail
26:30
WWC 2025 • 12 months ago

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

AI & Ethics thumbnail
28:27
WWC 2025 • 12 months ago

AI & Ethics

PJ Hagerty

WeAreDevelopers LIVE - Is AI replacing developers?, Stopping bots, AI on device & more thumbnail
1:01:03
LIVE • over 1 year ago

WeAreDevelopers LIVE - Is AI replacing developers?, Stopping bots, AI on device & more

Chris Heilmann, Daniel Cranney, Sebastian Gingter

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.