Tap a claim on the ring to put it at the centre.
← A bigger context window does not give you a smarter model; the…
8 connected korrents · 5 moments on record from 19 Jun 2024 to 30 Jul 2026.
Everything filed under AI agents
AI agents Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions. — tap to centre the map on it Every announcement of a longer context window hides the cost, which is that the model gets worse at following… Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — tap for who they are
Same subject: Four things about a context window decide what an agent does next: its size, whether the information in it is correct, whether information is missing, and the trajectory it is already on. — tap to centre the map on it Four things about a context window decide what an agent does next: its size, whether the information in it is… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. — tap to centre the map on it What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred… Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: The point of context engineering is to do as much work as possible in the smart zone — roughly the first hundred thousand tokens of the context window. — tap to centre the map on it The point of context engineering is to do as much work as possible in the smart zone — roughly the first… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive. — tap to centre the map on it Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. — tap to centre the map on it AI does not remove a job so much as change what it consists of, and knowing exactly where a model's… Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — tap for who they are
Same subject: Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore. — tap to centre the map on it Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The scarce skill is now context switching across parallel agents, not sustained deep work. — tap to centre the map on it The scarce skill is now context switching across parallel agents, not sustained deep work. Last stated 6 months ago
4 Mar 2026
BC
Boris Cherny — holds since 2026-03-04 — tap for who they are
At the centre
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds DH Dex HorthyRead this korrent →
Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions.
Holds AS Aravind Srinivas
Four things about a context window decide what an agent does next: its size, whether the information in it is correct, whether information is missing, and the trajectory it is already on.
Holds DH Dex Horthy
What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters.
Holds JD Jeff Dean
The point of context engineering is to do as much work as possible in the smart zone — roughly the first hundred thousand tokens of the context window.
Holds DH Dex Horthy
Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive.
Holds DH Dex Horthy
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
Holds DF Dylan Field
Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore.
Holds DH Dex Horthy
The scarce skill is now context switching across parallel agents, not sustained deep work.
Holds