✳flâneur — a map of the web's best reading

Andrew Pignanelli

andrewp.co · 886 words · saved by 1 readers

It’s now been 5 months since my article on memory, and the forward looking claims in it are seeming pretty accurate. Below are the predictions I have for 2026. Some are more thought through than others: Coding is, for all intents and purposes, solved in the next generation of models. Everything related to coding that isnt “solved” is more of a harness/context problem than anything else. This means everything from backend, reliability and deployment, security, and frontend is able to be handed off to an agent. The exception is actual business logic and user experience, which still doesn’t feel right till two more generations of visual and spatial reasoning improve. Browser agents become highly effective and are used for the long tail of problems that cant be solved by purpose built software. As a result of this, bot protection becomes a really big thing people have to fight/worry about to get this tooling to work and companies like browserbase make a shit ton of money doing so. Everythi

2026 Predictions: Everything works now and that's insane 12/23/2025 It’s now been 5 months since my article on memory, and the forward looking claims in it are seeming pretty accurate. Below are the predictions I have for 2026. Some are more thought through than others: Coding is, for all intents and purposes, solved in the next generation of models. Everything related to coding that isnt “solved” is more of a harness/context problem than anything else. This means everything from backend, reliability and deployment, security, and frontend is able to be handed off to an agent. The exception is

Explore this link on the map →

related reading