Presentations tagged LLMs

Orbital Lasers vs For Loops: Economically Matching Models to Tasks

Stephen Sennett



The Application Layer Is the New Research Lab

Abdul Karim



Our AI Hallucinated in Production: How We Fixed It With Evals

Yicheng Guo



Why Your Coding Agent Forgets Everything

Igor Costa



Token Town (why compute strategy is product strategy)

Sarah Sachs



State of the AI Model Landscape

George Cameron



12TB of AI coding agent logs – what works, what fails

Dave Slutzkin



AI After an Apocalypse

Simon Knox



Agentic SAST: Building an AI Pipeline for Rule Synthesis and Root-Cause Vulnerability Analysis

Danila Sashchenko



The Death of Documentation

Josh Gillies



Building SDKs in the Agentic Era

Mark McDonald



Why Most AI De-Identification Fails in Production, And How We Built One Lawyers Actually Trust

Moin Zaman



Hacking the Model: AI Red Teaming in Practice

Pas Apicella



Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)

Mal Curtis



Legacy Software + Agentic Discovery

Chris Rickard



COBOL and AI: Building a Self-Serve Knowledge Layer for 2,000 Batch Jobs

Matthew Gillard



Edge AI with Direct Device Control

Jeremy Kelaher



Multi-Model Collaboration with Claude Code: How to Measure What Actually Works

Jack Rudenko



When a Small Language Model Beat Our LLM in Production

Avni Bhatt



Towards Long-Horizon Tasks

Zixuan Li



What If You Never Needed an API Key Again? Building a Mesh LLM From Spare Compute

Michael Neale



Panel: Governance & Ethics

Andrew Murphy



Modern Performance Workflows

Umar Hansa



Andrew Fisher in conversation with Sarah Taraporewalla, Geoffrey Huntley and Dave Lemphers

Andrew Fisher