[bz_bz_bz]

Blame Simon Willison ;)

“A common complaint today from AI coding skeptics is that LLMs are fine for toy projects but can’t be used for anything large and serious.

I think within 3 years that will be comprehensively proven incorrect, to the point that it won’t even be controversial anymore.

I picked a web browser here because so much of the work building a browser involves writing code that has to conform to an enormous and daunting selection of both formal tests and informal websites-in-the-wild.

Coding agents are really good at tasks where you can define a concrete goal and then set them to work iterating in that direction.

A web browser is the most ambitious project I can think of that leans into those capabilities.”

https://simonwillison.net/2026/Jan/8/llm-predictions-for-202...

“The browser and this project were co-developed and very symbiotic, only because the browser was a very useful objective for us to measure and iterate the progress of the harness. The goal was to iterate on and research the multi-agent harness—the browser was just the research example or objective.”

https://simonwillison.net/2026/Jan/23/fastrender/

[simonw]

The Cursor FastRender project started in December, so it wasn't influenced by my prediction in January.

[zabzonk]

> Coding agents are really good at tasks where you can define a concrete goal and then set them to work iterating in that direction.

Wholly based on other people's work. Which is OK.

[jordanb]

> Coding agents are really good at tasks where you can define a concrete goal and then set them to work iterating in that direction.

Specifically ones that are in the training data.

> A web browser is the most ambitious project I can think of that leans into those capabilities.”

I assume Linux and gcc are in the training data, so additional options may be OSes and compilers..