Simon Willison · Same day & room2026 in LLMs
This year models crossed from reliable coding agents to 'Fable class', solving any well-defined goal by brute force when given the tools, ev…
Story
Not written yet.
Wed, Nov 11 · 9:00 AM–9:10 AM · Continental 4–6 (Mainstage)
MC Intro
Corey Quinn, The Duckbill Group
← All talks · ← Prev talk · Next talk →1 of 7 built · Z4 Evidence Hub
Speaker
My notes
None captured.
Photos
1 filed.
Recording
None synced. The public livestream: YouTube, around 0:39:53 (approximate).
Themes & related talks
Cross-references across the 6 conference themes, contested debates, and connected talks.
Steve Yegge · Same day & roomSoftware Factories: Escape from Trash Mountain
A year of software factories shows fuel is the hard limit and currently subsidized, agents behave like staff who need managing and pruning, …
Zach Bruggeman · Same day & roomHow to build an agent that builds the culture
A single shared coding agent with every session public by default changes engineering culture: good practice spreads without training, and t…
Fabian Hedin · Same day & roomWhat it takes to set intelligence free
Because Lovable's output is a business, not code, letting an agent work for ten hours needed a runtime that survives deploys, computers that…
Scott Roberts · Same day & roomAutocomplete for Actions: System One from the UI to the DB
A decision model fast and cheap enough to call everywhere replaces both LLM agent loops and retrieval stacks: it picks the right UI card on …
Links
No dossier yet.
Transcript
Not transcribed yet.
Generated Nov 13, 2026 at 5:56 AM · bun scripts/render-pages.ts