LLM predictions for 2026, shared with Oxide and Friends

kept by eddie jan 09

Simon Willison predicts LLMs will write undeniably good code in 2026, sandboxing will be solved, and a coding agent security disaster is imminent.

Auto-grading decade-old Hacker News discussions with hindsight
An LLM retroactively grades decade-old Hacker News predictions, sparking debate on hindsight bias, surveillance, and the value of public web archives.
also on #predictions, #tech-community
My 2026 AI Bets (A Time Capsule)
Zach Wills predicts that by 2026, AI coding assistants will evolve into autonomous engineering agents, rendering current IDE copilots obsolete, and that the biggest gains will come from multi-modal models reasoning over entire codebases.
also on #predictions, #ai-coding, #software-engineering
Your job is to deliver code you have proven to work
Software engineers must prove code works through manual and automated testing, shifting accountability away from AI agents to the human submitting the PR.
also on LLM, Simon Willison, #ai-coding, #software-engineering
What's the best programming language for coding agents?
Dan Luu's empirical tests with LLMs on Zstd and Pandoc implementations show that language popularity weakly correlates with better outcomes, but claims about dynamic or token-efficient languages being superior for coding agents do not hold across non-trivial tasks.
also on LLM, #ai-coding, #software-engineering
the browser is the sandbox
The browser's 30-year-old sandbox model can be adapted to safely run AI agents locally, though gaps remain in network isolation and malicious file creation.
also on Simon Willison, #security, #software-engineering