korrents

On the map

Tap a claim on the ring to put it at the centre.

← Longer context is an engineering and inference problem, not a research problem — nothing prevents it from working.

8 connected korrents · 7 moments on record from 19 Jun 2024 to 6 Sept 2026.

Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Longer context is an engineering and inference problem, not a research problem — nothing prevents it from working. Longer context is an engineering andinference problem, not a researchproblem — nothing prevents it fromworking. DA Dario Amodei — holds since 2026-02-13 — 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 longercontext window hides the cost,which is that the model getsworse at following… AS Aravind Srinivas — holds since 2024-06-19 — 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 stayedrelevant for a year because itis grounded in how transformerattention works, and it will… DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: 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. — tap to centre the map on it A bigger context window doesnot give you a smarter model;the intelligence of the modelis what decides how much of… DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: Long-context processing is close to being a solved problem for frontier AI models. — tap to centre the map on it Long-context processing isclose to being a solvedproblem for frontier AImodels. SW Simon Willison — holds since 2026-09-03 — tap for who they are Same subject: Any task can be made arbitrarily difficult or effectively impossible depending on how its context is framed. — tap to centre the map on it Any task can be madearbitrarily difficult oreffectively impossibledepending on how its context… ZM Zvi Mowshowitz — holds since 2026-09-06 — tap for who they are Same subject: Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs. — tap to centre the map on it Spending compute at inferencetime to search over plausiblesolutions is the general fixfor unreliable long agent… JD Jeff Dean — holds since 2026-07-30 — 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, notone: the information budgeteveryone thinks about, and aninstruction budget, where… DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: Inference was never going to be the easy, cheap half of AI, because inference is thinking, and thinking is far harder than reading. — tap to centre the map on it Inference was never going tobe the easy, cheap half of AI,because inference is thinking,and thinking is far harder… JH Jensen Huang — holds since 2026-03-23 — tap for who they are
same subject or similar wording

At the centre Longer context is an engineering and inference problem, not a research problem — nothing prevents it from working. Holds Dario Amodei Read this korrent →