| ▲ | bz_bz_bz 2 hours ago | |
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.” | ||
| ▲ | simonw 2 hours ago | parent | next [-] | |
The Cursor FastRender project started in December, so it wasn't influenced by my prediction in January. | ||
| ▲ | jordanb an hour ago | parent | prev | next [-] | |
> 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.. | ||
| ▲ | zabzonk 2 hours ago | parent | prev [-] | |
> 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. | ||